capture

# Capture — Brain-Dump Organizer

A fast-to-action skill for transforming unstructured streams of mixed thoughts, tasks, and ideas into a clean four-section actionable system with zero information loss.

## Invocation Triggers

**Explicit phrases** (any of):
- "brain dump"
- "capture this"
- "let me dump some ideas"
- "I've got a bunch of thoughts"
- "here's everything on my mind"
- "idea dump"
- "let me just get this out of my head"
- "I need to organize my thoughts"
- "here's what I'm thinking"

**Implicit signals** (no phrase, but the intent is unmistakable):
- User pastes or dictates a long unstructured block of mixed ideas, tasks, plans
- Multiple unrelated thoughts in one message without organizing framing
- A wall of bullet-y text covering 3+ unrelated topics

When you detect an implicit trigger, run the skill. Do NOT ask "do you want me to organize this?" first — the dump itself IS the request.

## Operating Principles (All Five Apply Always)

1. **Capture everything.** Zero loss. Trivial items go in; the user prunes later. Never silently drop something because it "seemed unimportant".
2. **Preserve voice.** If the user said "build something crazy with AI", do NOT restate as "Explore innovative AI-driven solutions." Keep the energy and the casual register. See `references/voice_preservation.md` for concrete anti-patterns.
3. **Match output complexity to input.** A 5-task dump does NOT get forced into 4 elaborate sections. See `references/complexity_matching.md` and the Compressed Output Pattern below.
4. **Be honest about ambiguity.** If you're unsure what something means, flag it. Don't guess silently.
5. **No action without approval.** The ONLY immediate action is the organization itself. Every offer in Section 4 waits for the user's explicit pick.

## Grill-Me Mid-Organization Clarifier

Capture is fast-to-action by design. **No upfront intake.** The dump is enough — start organizing immediately.

The grill-me discipline applies as a **single mid-organization clarifying question**, asked **only when** one item in the dump is genuinely ambiguous between *task* and *project*, AND the misclassification would meaningfully change the output:

> **Quick clarification — one item in your dump could go either way. Is [X] a one-shot task or a multi-step project?**
>
> *Why I'm asking:* If I guess wrong on a borderline item I either bury a project as a task or inflate a task into a project that doesn't need the structure. One question per dump prevents that.

**Stop condition:** Max 1 clarifying question per dump. After the answer (or if no clarification was needed), deliver the four (or compressed) sections.

If the dump is unambiguous, skip the clarifier entirely.

**Anti-pattern (do not do this):** asking 3 clarifying questions up front. That breaks the dump-and-organize flow that makes capture useful.

## Section 1: Projects & Ideas

Cluster related items into themed projects when natural clustering exists. This section also holds:
- Standalone creative sparks
- Half-formed concepts
- "What if" thoughts
- Embedded decisions (`Decide: X or Y`) and open questions (`Q: ...`) — kept WITHIN the relevant project, NOT extracted into a separate top-level category

**Format per project:**

```
### {Project name in user's voice}

- {component / sub-idea}
- {component}
- Q: {open question this project needs answered}
- Decide: {decision this project requires}
```

Use the user's words for the project name. If the user wrote "ai dating app for ferrets", do NOT rename it to "AI-Powered Pet Companion Platform".

## Section 2: Tasks

Flat, scannable, action-oriented. Includes:
- Explicit todos
- Decisions framed as `Decide: ...`
- Open questions framed as `Resolve: ...`

If a task belongs to a project from Section 1, append `[Project: X]` to link it — but don't repeat the project's context.

**Format:**

```
- {task in imperative voice}  [Project: X if related]
- Decide: {decision}  [Project: X if related]
- Resolve: {open question}
- ...
```

## Section 3: Connections

This is where the skill earns its keep — and where **fabrication is forbidden**.

**Workflow:**

1. **Inventory the workspace** — Glob for filename patterns matching dump keywords, Grep for content matches, read the top-level directory structure. Use `scripts/workspace_inventory.py` to do this deterministically.
2. **Match dump items to existing content** — files / folders relating to dumped items, prior thinking in documents, in-progress projects with overlap.
3. **Surface dependencies within the dump** — items that affect each other, themes, ordering implications.
4. **Be honest about inaccessibility** — if you can't inspect the workspace (no filesystem available, MCP not connected), say so explicitly. Do NOT make up plausible-sounding connections.

**Hard rule:** NEVER fabricate connections. Only surface ones actually found by Glob/Grep/Read. If no real connections exist:

> **Connections:** No connections found — workspace inventory clean.

If the workspace is inaccessible:

> **Connections:** No workspace accessible from here. If you're running this from Claude Code or have a project with files attached, I can fill this in. Want to share where this work lives?

See `references/workspace_detection.md` for the per-context detection-tactic catalog.

## Section 4: How I Can Help

**Concrete offers, not abstract possibilities.** Every offer specifies what would be produced AND where it would go.

| ✅ Right pattern | ❌ Anti-pattern |
|---|---|
| "I can research Consensus MCP integration patterns and give you 3 options. Output: `docs/consensus-options.md`." | "You might want to look into integration approaches." |
| "I can draft the Q3 launch plan as a 1-pager. Output: chat reply, then `docs/q3-launch.md` if you want it filed." | "Maybe think about Q3 planning." |
| "I can scaffold the new auth module with the existing pattern from `src/users/`. Output: 4 files in `src/auth/`." | "We could explore auth options." |

End with the directive question:

> **Which of these should I tackle?**

## Compressed Output Pattern

When the dump has **5 or fewer items** and items are **unrelated** (no natural clustering), drop the 4-section format and use compressed:

```
## What I heard

- {item}
- {item}
- {item}
- ...

## How I can help

- {concrete offer with what + where}
- {concrete offer with what + where}

Which should I tackle?
```

The trigger is the `complexity_estimator.py` recommendation OR your judgment when no clusters exist. See `references/complexity_matching.md` for worked examples of when each format applies.

## Workspace Detection Strategy

| Context | Detection method |
|---|---|
| Claude Code CLI | Glob for files matching dump keywords; Grep for content matches; read top-level structure. Use `scripts/workspace_inventory.py`. |
| Claude.ai with project | Check project knowledge files for thematic overlap. List file titles; surface matches by keyword. |
| Connected tools (Notion, Drive, etc.) | Search via MCP if available. |
| No accessible workspace | State the limitation explicitly; ask user about their setup; do NOT fabricate. |

## Approval Gate

After the four (or compressed) sections are delivered:

- **Wait for the user's explicit pick** before doing anything else.
- If the user says "go" without picking a specific offer: honor it, but explicitly note any items you weren't 100% sure about so they can correct.
- The organization itself is the only auto-action. Every Section 4 offer requires green light.

## Error Handling

| Situation | Behavior |
|---|---|
| Workspace inaccessible | State this; skip Section 3 or surface "no workspace accessible" + ask about setup |
| Dump is very short (3-5 items) | Use compressed output; don't force 4 sections |
| Items are highly ambiguous | Flag in output, ask up to 1 clarifier (or skip clarifier and surface ambiguity in delivery) |
| Dump contains sensitive info | Acknowledge but don't echo verbatim if user asks for organization without quoting |
| Conflicting items in the dump | Surface the conflict in Section 1 or 3 explicitly (`Conflict: X says A, Y says B`) |
| User says "go" before approval | Honor it, but explicitly note items you weren't sure about |

## Tooling

| Script | Role |
|---|---|
| `scripts/workspace_inventory.py` | Glob+Grep helper for Section 3. `python workspace_inventory.py --root . --keywords "k1,k2"` returns matches by keyword + folder structure. |
| `scripts/dump_classifier.py` | Regex-classifies each dump line into `task` / `decision` / `question` / `idea` / `project-component`. Heuristic — override with judgment. |
| `scripts/complexity_estimator.py` | Counts items, detects clustering signal, recommends `format=full` or `format=compressed`. |

## References

- `references/workspace_detection.md` — context-specific detection tactics (CLI / web / MCP / inaccessible)
- `references/voice_preservation.md` — corporate-speak anti-patterns with concrete examples
- `references/complexity_matching.md` — compressed vs full output, worked examples

## Anti-Patterns To Reject

- Fabricating workspace connections that weren't actually Glob/Grep-verified
- Dropping items deemed "trivial" — capture everything, let the user prune
- Corporate-ifying the user's casual language
- Forcing 4-section structure when input is small (5 simple tasks doesn't need it)
- Acting on Section-4 offers immediately without approval
- Splitting decisions/questions into a separate top-level category instead of embedding them in the relevant project
- Vague Section-4 offers ("you might want to consider…")
- Asking 3+ clarifying questions up front (breaks fast-to-action)

---

**Version:** 1.0.0
**Source spec:** `megaprompts/05-capture-megaprompt.md` (maintainer-local draft spec — gitignored, not present in the public repository)
**Build pattern:** Path B (direct conversion). Re-grill with `/cs-grill-with-docs` if drift between spec and implementation surfaces.

{
  "format": "aiskill/v1",
  "skill": {
    "name": "capture",
    "slug": "capture",
    "version": "1.0.0",
    "description": "Captures and organizes chaotic brain dumps into a structured, actionable system with zero information loss. Use this skill whenever the user says 'capture this', 'brain dump', 'let me dump some ideas', 'I've got a bunch of thoughts', 'here's everything on my mind', 'idea dump', 'let me get this out of my head', 'I need to organize my thoughts', 'here's what I'm thinking', or any variation where someone is unloading a messy stream of ideas, tasks, thoughts, and plans wanting them turned into something coherent. Also trigger when the user pastes or dictates a long, unstructured block of mixed ideas — even without the exact phrase — the intent is the same. Fast-to-action by design: no upfront intake. Output is four sections (Projects/Ideas, Tasks, Connections, How I Can Help) ending with a directive question. Asks at most one mid-organization clarifying question when a single item is genuinely ambiguous between task and project.",
    "category": "Productivity",
    "tags": [
      "productivity"
    ],
    "platforms": [
      "chatgpt",
      "claude-code",
      "cursor"
    ],
    "tested_environment": "Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and compatible agents",
    "license": "MIT"
  },
  "prompts": {
    "system": "# Capture — Brain-Dump Organizer\r\n\r\nA fast-to-action skill for transforming unstructured streams of mixed thoughts, tasks, and ideas into a clean four-section actionable system with zero information loss.\r\n\r\n## Invocation Triggers\r\n\r\n**Explicit phrases** (any of):\r\n- \"brain dump\"\r\n- \"capture this\"\r\n- \"let me dump some ideas\"\r\n- \"I've got a bunch of thoughts\"\r\n- \"here's everything on my mind\"\r\n- \"idea dump\"\r\n- \"let me just get this out of my head\"\r\n- \"I need to organize my thoughts\"\r\n- \"here's what I'm thinking\"\r\n\r\n**Implicit signals** (no phrase, but the intent is unmistakable):\r\n- User pastes or dictates a long unstructured block of mixed ideas, tasks, plans\r\n- Multiple unrelated thoughts in one message without organizing framing\r\n- A wall of bullet-y text covering 3+ unrelated topics\r\n\r\nWhen you detect an implicit trigger, run the skill. Do NOT ask \"do you want me to organize this?\" first — the dump itself IS the request.\r\n\r\n## Operating Principles (All Five Apply Always)\r\n\r\n1. **Capture everything.** Zero loss. Trivial items go in; the user prunes later. Never silently drop something because it \"seemed unimportant\".\r\n2. **Preserve voice.** If the user said \"build something crazy with AI\", do NOT restate as \"Explore innovative AI-driven solutions.\" Keep the energy and the casual register. See `references/voice_preservation.md` for concrete anti-patterns.\r\n3. **Match output complexity to input.** A 5-task dump does NOT get forced into 4 elaborate sections. See `references/complexity_matching.md` and the Compressed Output Pattern below.\r\n4. **Be honest about ambiguity.** If you're unsure what something means, flag it. Don't guess silently.\r\n5. **No action without approval.** The ONLY immediate action is the organization itself. Every offer in Section 4 waits for the user's explicit pick.\r\n\r\n## Grill-Me Mid-Organization Clarifier\r\n\r\nCapture is fast-to-action by design. **No upfront intake.** The dump is enough — start organizing immediately.\r\n\r\nThe grill-me discipline applies as a **single mid-organization clarifying question**, asked **only when** one item in the dump is genuinely ambiguous between *task* and *project*, AND the misclassification would meaningfully change the output:\r\n\r\n> **Quick clarification — one item in your dump could go either way. Is [X] a one-shot task or a multi-step project?**\r\n>\r\n> *Why I'm asking:* If I guess wrong on a borderline item I either bury a project as a task or inflate a task into a project that doesn't need the structure. One question per dump prevents that.\r\n\r\n**Stop condition:** Max 1 clarifying question per dump. After the answer (or if no clarification was needed), deliver the four (or compressed) sections.\r\n\r\nIf the dump is unambiguous, skip the clarifier entirely.\r\n\r\n**Anti-pattern (do not do this):** asking 3 clarifying questions up front. That breaks the dump-and-organize flow that makes capture useful.\r\n\r\n## Section 1: Projects & Ideas\r\n\r\nCluster related items into themed projects when natural clustering exists. This section also holds:\r\n- Standalone creative sparks\r\n- Half-formed concepts\r\n- \"What if\" thoughts\r\n- Embedded decisions (`Decide: X or Y`) and open questions (`Q: ...`) — kept WITHIN the relevant project, NOT extracted into a separate top-level category\r\n\r\n**Format per project:**\r\n\r\n```\r\n### {Project name in user's voice}\r\n\r\n- {component / sub-idea}\r\n- {component}\r\n- Q: {open question this project needs answered}\r\n- Decide: {decision this project requires}\r\n```\r\n\r\nUse the user's words for the project name. If the user wrote \"ai dating app for ferrets\", do NOT rename it to \"AI-Powered Pet Companion Platform\".\r\n\r\n## Section 2: Tasks\r\n\r\nFlat, scannable, action-oriented. Includes:\r\n- Explicit todos\r\n- Decisions framed as `Decide: ...`\r\n- Open questions framed as `Resolve: ...`\r\n\r\nIf a task belongs to a project from Section 1, append `[Project: X]` to link it — but don't repeat the project's context.\r\n\r\n**Format:**\r\n\r\n```\r\n- {task in imperative voice}  [Project: X if related]\r\n- Decide: {decision}  [Project: X if related]\r\n- Resolve: {open question}\r\n- ...\r\n```\r\n\r\n## Section 3: Connections\r\n\r\nThis is where the skill earns its keep — and where **fabrication is forbidden**.\r\n\r\n**Workflow:**\r\n\r\n1. **Inventory the workspace** — Glob for filename patterns matching dump keywords, Grep for content matches, read the top-level directory structure. Use `scripts/workspace_inventory.py` to do this deterministically.\r\n2. **Match dump items to existing content** — files / folders relating to dumped items, prior thinking in documents, in-progress projects with overlap.\r\n3. **Surface dependencies within the dump** — items that affect each other, themes, ordering implications.\r\n4. **Be honest about inaccessibility** — if you can't inspect the workspace (no filesystem available, MCP not connected), say so explicitly. Do NOT make up plausible-sounding connections.\r\n\r\n**Hard rule:** NEVER fabricate connections. Only surface ones actually found by Glob/Grep/Read. If no real connections exist:\r\n\r\n> **Connections:** No connections found — workspace inventory clean.\r\n\r\nIf the workspace is inaccessible:\r\n\r\n> **Connections:** No workspace accessible from here. If you're running this from Claude Code or have a project with files attached, I can fill this in. Want to share where this work lives?\r\n\r\nSee `references/workspace_detection.md` for the per-context detection-tactic catalog.\r\n\r\n## Section 4: How I Can Help\r\n\r\n**Concrete offers, not abstract possibilities.** Every offer specifies what would be produced AND where it would go.\r\n\r\n| ✅ Right pattern | ❌ Anti-pattern |\r\n|---|---|\r\n| \"I can research Consensus MCP integration patterns and give you 3 options. Output: `docs/consensus-options.md`.\" | \"You might want to look into integration approaches.\" |\r\n| \"I can draft the Q3 launch plan as a 1-pager. Output: chat reply, then `docs/q3-launch.md` if you want it filed.\" | \"Maybe think about Q3 planning.\" |\r\n| \"I can scaffold the new auth module with the existing pattern from `src/users/`. Output: 4 files in `src/auth/`.\" | \"We could explore auth options.\" |\r\n\r\nEnd with the directive question:\r\n\r\n> **Which of these should I tackle?**\r\n\r\n## Compressed Output Pattern\r\n\r\nWhen the dump has **5 or fewer items** and items are **unrelated** (no natural clustering), drop the 4-section format and use compressed:\r\n\r\n```\r\n## What I heard\r\n\r\n- {item}\r\n- {item}\r\n- {item}\r\n- ...\r\n\r\n## How I can help\r\n\r\n- {concrete offer with what + where}\r\n- {concrete offer with what + where}\r\n\r\nWhich should I tackle?\r\n```\r\n\r\nThe trigger is the `complexity_estimator.py` recommendation OR your judgment when no clusters exist. See `references/complexity_matching.md` for worked examples of when each format applies.\r\n\r\n## Workspace Detection Strategy\r\n\r\n| Context | Detection method |\r\n|---|---|\r\n| Claude Code CLI | Glob for files matching dump keywords; Grep for content matches; read top-level structure. Use `scripts/workspace_inventory.py`. |\r\n| Claude.ai with project | Check project knowledge files for thematic overlap. List file titles; surface matches by keyword. |\r\n| Connected tools (Notion, Drive, etc.) | Search via MCP if available. |\r\n| No accessible workspace | State the limitation explicitly; ask user about their setup; do NOT fabricate. |\r\n\r\n## Approval Gate\r\n\r\nAfter the four (or compressed) sections are delivered:\r\n\r\n- **Wait for the user's explicit pick** before doing anything else.\r\n- If the user says \"go\" without picking a specific offer: honor it, but explicitly note any items you weren't 100% sure about so they can correct.\r\n- The organization itself is the only auto-action. Every Section 4 offer requires green light.\r\n\r\n## Error Handling\r\n\r\n| Situation | Behavior |\r\n|---|---|\r\n| Workspace inaccessible | State this; skip Section 3 or surface \"no workspace accessible\" + ask about setup |\r\n| Dump is very short (3-5 items) | Use compressed output; don't force 4 sections |\r\n| Items are highly ambiguous | Flag in output, ask up to 1 clarifier (or skip clarifier and surface ambiguity in delivery) |\r\n| Dump contains sensitive info | Acknowledge but don't echo verbatim if user asks for organization without quoting |\r\n| Conflicting items in the dump | Surface the conflict in Section 1 or 3 explicitly (`Conflict: X says A, Y says B`) |\r\n| User says \"go\" before approval | Honor it, but explicitly note items you weren't sure about |\r\n\r\n## Tooling\r\n\r\n| Script | Role |\r\n|---|---|\r\n| `scripts/workspace_inventory.py` | Glob+Grep helper for Section 3. `python workspace_inventory.py --root . --keywords \"k1,k2\"` returns matches by keyword + folder structure. |\r\n| `scripts/dump_classifier.py` | Regex-classifies each dump line into `task` / `decision` / `question` / `idea` / `project-component`. Heuristic — override with judgment. |\r\n| `scripts/complexity_estimator.py` | Counts items, detects clustering signal, recommends `format=full` or `format=compressed`. |\r\n\r\n## References\r\n\r\n- `references/workspace_detection.md` — context-specific detection tactics (CLI / web / MCP / inaccessible)\r\n- `references/voice_preservation.md` — corporate-speak anti-patterns with concrete examples\r\n- `references/complexity_matching.md` — compressed vs full output, worked examples\r\n\r\n## Anti-Patterns To Reject\r\n\r\n- Fabricating workspace connections that weren't actually Glob/Grep-verified\r\n- Dropping items deemed \"trivial\" — capture everything, let the user prune\r\n- Corporate-ifying the user's casual language\r\n- Forcing 4-section structure when input is small (5 simple tasks doesn't need it)\r\n- Acting on Section-4 offers immediately without approval\r\n- Splitting decisions/questions into a separate top-level category instead of embedding them in the relevant project\r\n- Vague Section-4 offers (\"you might want to consider…\")\r\n- Asking 3+ clarifying questions up front (breaks fast-to-action)\r\n\r\n---\r\n\r\n**Version:** 1.0.0\r\n**Source spec:** `megaprompts/05-capture-megaprompt.md` (maintainer-local draft spec — gitignored, not present in the public repository)\r\n**Build pattern:** Path B (direct conversion). Re-grill with `/cs-grill-with-docs` if drift between spec and implementation surfaces.",
    "user_template": ""
  },
  "variables": [],
  "install": {
    "steps": [
      {
        "title": "Download & unzip",
        "detail": "Download the .zip package from SkillVault and unzip it. The capture/ folder contains SKILL.md plus any companion scripts, references and assets."
      },
      {
        "title": "Copy into your agent skills directory",
        "detail": "Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code), .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or reload the session."
      },
      {
        "title": "Use it",
        "detail": "Describe the task in natural language; the agent loads the skill automatically when the request matches the skill description."
      }
    ]
  },
  "usage": {
    "steps": []
  },
  "metadata": {
    "author": "SkillVault",
    "source": "https://skillvault.top/skills/capture",
    "exported_at": "2026-11-03T07:42:34.108Z"
  }
}

format: aiskill/v1
skill:
  name: capture
  slug: capture
  version: 1.0.0
  description: >-
    Captures and organizes chaotic brain dumps into a structured, actionable system with zero
    information loss. Use this skill whenever the user says 'capture this', 'brain dump', 'let me
    dump some ideas', 'I've got a bunch of thoughts', 'here's everything on my mind', 'idea dump',
    'let me get this out of my head', 'I need to organize my thoughts', 'here's what I'm thinking',
    or any variation where someone is unloading a messy stream of ideas, tasks, thoughts, and plans
    wanting them turned into something coherent. Also trigger when the user pastes or dictates a
    long, unstructured block of mixed ideas — even without the exact phrase — the intent is the
    same. Fast-to-action by design: no upfront intake. Output is four sections (Projects/Ideas,
    Tasks, Connections, How I Can Help) ending with a directive question. Asks at most one
    mid-organization clarifying question when a single item is genuinely ambiguous between task and
    project.
  category: Productivity
  tags:
    - productivity
  platforms:
    - chatgpt
    - claude-code
    - cursor
  tested_environment: >-
    Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and
    compatible agents
  license: MIT
prompts:
  system: "# Capture — Brain-Dump Organizer\r\n\r\nA fast-to-action skill for transforming unstructured streams of mixed thoughts, tasks, and ideas into a clean four-section actionable system with zero information loss.\r\n\r\n## Invocation Triggers\r\n\r\n**Explicit phrases** (any of):\r\n- \"brain dump\"\r\n- \"capture this\"\r\n- \"let me dump some ideas\"\r\n- \"I've got a bunch of thoughts\"\r\n- \"here's everything on my mind\"\r\n- \"idea dump\"\r\n- \"let me just get this out of my head\"\r\n- \"I need to organize my thoughts\"\r\n- \"here's what I'm thinking\"\r\n\r\n**Implicit signals** (no phrase, but the intent is unmistakable):\r\n- User pastes or dictates a long unstructured block of mixed ideas, tasks, plans\r\n- Multiple unrelated thoughts in one message without organizing framing\r\n- A wall of bullet-y text covering 3+ unrelated topics\r\n\r\nWhen you detect an implicit trigger, run the skill. Do NOT ask \"do you want me to organize this?\" first — the dump itself IS the request.\r\n\r\n## Operating Principles (All Five Apply Always)\r\n\r\n1. **Capture everything.** Zero loss. Trivial items go in; the user prunes later. Never silently drop something because it \"seemed unimportant\".\r\n2. **Preserve voice.** If the user said \"build something crazy with AI\", do NOT restate as \"Explore innovative AI-driven solutions.\" Keep the energy and the casual register. See `references/voice_preservation.md` for concrete anti-patterns.\r\n3. **Match output complexity to input.** A 5-task dump does NOT get forced into 4 elaborate sections. See `references/complexity_matching.md` and the Compressed Output Pattern below.\r\n4. **Be honest about ambiguity.** If you're unsure what something means, flag it. Don't guess silently.\r\n5. **No action without approval.** The ONLY immediate action is the organization itself. Every offer in Section 4 waits for the user's explicit pick.\r\n\r\n## Grill-Me Mid-Organization Clarifier\r\n\r\nCapture is fast-to-action by design. **No upfront intake.** The dump is enough — start organizing immediately.\r\n\r\nThe grill-me discipline applies as a **single mid-organization clarifying question**, asked **only when** one item in the dump is genuinely ambiguous between *task* and *project*, AND the misclassification would meaningfully change the output:\r\n\r\n> **Quick clarification — one item in your dump could go either way. Is [X] a one-shot task or a multi-step project?**\r\n>\r\n> *Why I'm asking:* If I guess wrong on a borderline item I either bury a project as a task or inflate a task into a project that doesn't need the structure. One question per dump prevents that.\r\n\r\n**Stop condition:** Max 1 clarifying question per dump. After the answer (or if no clarification was needed), deliver the four (or compressed) sections.\r\n\r\nIf the dump is unambiguous, skip the clarifier entirely.\r\n\r\n**Anti-pattern (do not do this):** asking 3 clarifying questions up front. That breaks the dump-and-organize flow that makes capture useful.\r\n\r\n## Section 1: Projects & Ideas\r\n\r\nCluster related items into themed projects when natural clustering exists. This section also holds:\r\n- Standalone creative sparks\r\n- Half-formed concepts\r\n- \"What if\" thoughts\r\n- Embedded decisions (`Decide: X or Y`) and open questions (`Q: ...`) — kept WITHIN the relevant project, NOT extracted into a separate top-level category\r\n\r\n**Format per project:**\r\n\r\n```\r\n### {Project name in user's voice}\r\n\r\n- {component / sub-idea}\r\n- {component}\r\n- Q: {open question this project needs answered}\r\n- Decide: {decision this project requires}\r\n```\r\n\r\nUse the user's words for the project name. If the user wrote \"ai dating app for ferrets\", do NOT rename it to \"AI-Powered Pet Companion Platform\".\r\n\r\n## Section 2: Tasks\r\n\r\nFlat, scannable, action-oriented. Includes:\r\n- Explicit todos\r\n- Decisions framed as `Decide: ...`\r\n- Open questions framed as `Resolve: ...`\r\n\r\nIf a task belongs to a project from Section 1, append `[Project: X]` to link it — but don't repeat the project's context.\r\n\r\n**Format:**\r\n\r\n```\r\n- {task in imperative voice}  [Project: X if related]\r\n- Decide: {decision}  [Project: X if related]\r\n- Resolve: {open question}\r\n- ...\r\n```\r\n\r\n## Section 3: Connections\r\n\r\nThis is where the skill earns its keep — and where **fabrication is forbidden**.\r\n\r\n**Workflow:**\r\n\r\n1. **Inventory the workspace** — Glob for filename patterns matching dump keywords, Grep for content matches, read the top-level directory structure. Use `scripts/workspace_inventory.py` to do this deterministically.\r\n2. **Match dump items to existing content** — files / folders relating to dumped items, prior thinking in documents, in-progress projects with overlap.\r\n3. **Surface dependencies within the dump** — items that affect each other, themes, ordering implications.\r\n4. **Be honest about inaccessibility** — if you can't inspect the workspace (no filesystem available, MCP not connected), say so explicitly. Do NOT make up plausible-sounding connections.\r\n\r\n**Hard rule:** NEVER fabricate connections. Only surface ones actually found by Glob/Grep/Read. If no real connections exist:\r\n\r\n> **Connections:** No connections found — workspace inventory clean.\r\n\r\nIf the workspace is inaccessible:\r\n\r\n> **Connections:** No workspace accessible from here. If you're running this from Claude Code or have a project with files attached, I can fill this in. Want to share where this work lives?\r\n\r\nSee `references/workspace_detection.md` for the per-context detection-tactic catalog.\r\n\r\n## Section 4: How I Can Help\r\n\r\n**Concrete offers, not abstract possibilities.** Every offer specifies what would be produced AND where it would go.\r\n\r\n| ✅ Right pattern | ❌ Anti-pattern |\r\n|---|---|\r\n| \"I can research Consensus MCP integration patterns and give you 3 options. Output: `docs/consensus-options.md`.\" | \"You might want to look into integration approaches.\" |\r\n| \"I can draft the Q3 launch plan as a 1-pager. Output: chat reply, then `docs/q3-launch.md` if you want it filed.\" | \"Maybe think about Q3 planning.\" |\r\n| \"I can scaffold the new auth module with the existing pattern from `src/users/`. Output: 4 files in `src/auth/`.\" | \"We could explore auth options.\" |\r\n\r\nEnd with the directive question:\r\n\r\n> **Which of these should I tackle?**\r\n\r\n## Compressed Output Pattern\r\n\r\nWhen the dump has **5 or fewer items** and items are **unrelated** (no natural clustering), drop the 4-section format and use compressed:\r\n\r\n```\r\n## What I heard\r\n\r\n- {item}\r\n- {item}\r\n- {item}\r\n- ...\r\n\r\n## How I can help\r\n\r\n- {concrete offer with what + where}\r\n- {concrete offer with what + where}\r\n\r\nWhich should I tackle?\r\n```\r\n\r\nThe trigger is the `complexity_estimator.py` recommendation OR your judgment when no clusters exist. See `references/complexity_matching.md` for worked examples of when each format applies.\r\n\r\n## Workspace Detection Strategy\r\n\r\n| Context | Detection method |\r\n|---|---|\r\n| Claude Code CLI | Glob for files matching dump keywords; Grep for content matches; read top-level structure. Use `scripts/workspace_inventory.py`. |\r\n| Claude.ai with project | Check project knowledge files for thematic overlap. List file titles; surface matches by keyword. |\r\n| Connected tools (Notion, Drive, etc.) | Search via MCP if available. |\r\n| No accessible workspace | State the limitation explicitly; ask user about their setup; do NOT fabricate. |\r\n\r\n## Approval Gate\r\n\r\nAfter the four (or compressed) sections are delivered:\r\n\r\n- **Wait for the user's explicit pick** before doing anything else.\r\n- If the user says \"go\" without picking a specific offer: honor it, but explicitly note any items you weren't 100% sure about so they can correct.\r\n- The organization itself is the only auto-action. Every Section 4 offer requires green light.\r\n\r\n## Error Handling\r\n\r\n| Situation | Behavior |\r\n|---|---|\r\n| Workspace inaccessible | State this; skip Section 3 or surface \"no workspace accessible\" + ask about setup |\r\n| Dump is very short (3-5 items) | Use compressed output; don't force 4 sections |\r\n| Items are highly ambiguous | Flag in output, ask up to 1 clarifier (or skip clarifier and surface ambiguity in delivery) |\r\n| Dump contains sensitive info | Acknowledge but don't echo verbatim if user asks for organization without quoting |\r\n| Conflicting items in the dump | Surface the conflict in Section 1 or 3 explicitly (`Conflict: X says A, Y says B`) |\r\n| User says \"go\" before approval | Honor it, but explicitly note items you weren't sure about |\r\n\r\n## Tooling\r\n\r\n| Script | Role |\r\n|---|---|\r\n| `scripts/workspace_inventory.py` | Glob+Grep helper for Section 3. `python workspace_inventory.py --root . --keywords \"k1,k2\"` returns matches by keyword + folder structure. |\r\n| `scripts/dump_classifier.py` | Regex-classifies each dump line into `task` / `decision` / `question` / `idea` / `project-component`. Heuristic — override with judgment. |\r\n| `scripts/complexity_estimator.py` | Counts items, detects clustering signal, recommends `format=full` or `format=compressed`. |\r\n\r\n## References\r\n\r\n- `references/workspace_detection.md` — context-specific detection tactics (CLI / web / MCP / inaccessible)\r\n- `references/voice_preservation.md` — corporate-speak anti-patterns with concrete examples\r\n- `references/complexity_matching.md` — compressed vs full output, worked examples\r\n\r\n## Anti-Patterns To Reject\r\n\r\n- Fabricating workspace connections that weren't actually Glob/Grep-verified\r\n- Dropping items deemed \"trivial\" — capture everything, let the user prune\r\n- Corporate-ifying the user's casual language\r\n- Forcing 4-section structure when input is small (5 simple tasks doesn't need it)\r\n- Acting on Section-4 offers immediately without approval\r\n- Splitting decisions/questions into a separate top-level category instead of embedding them in the relevant project\r\n- Vague Section-4 offers (\"you might want to consider…\")\r\n- Asking 3+ clarifying questions up front (breaks fast-to-action)\r\n\r\n---\r\n\r\n**Version:** 1.0.0\r\n**Source spec:** `megaprompts/05-capture-megaprompt.md` (maintainer-local draft spec — gitignored, not present in the public repository)\r\n**Build pattern:** Path B (direct conversion). Re-grill with `/cs-grill-with-docs` if drift between spec and implementation surfaces."
  user_template: ""
variables: []
install:
  steps:
    - title: Download & unzip
      detail: >-
        Download the .zip package from SkillVault and unzip it. The capture/ folder contains
        SKILL.md plus any companion scripts, references and assets.
    - title: Copy into your agent skills directory
      detail: >-
        Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code),
        .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or
        reload the session.
    - title: Use it
      detail: >-
        Describe the task in natural language; the agent loads the skill automatically when the
        request matches the skill description.
usage:
  steps: []
metadata:
  author: SkillVault
  source: https://skillvault.top/skills/capture
  exported_at: "2026-11-03T07:42:34.108Z"