agentleFS
bradautomatesbradautomates/second-brain/.claude/skills/new/SKILL.md

new

Skill217 starsChanged 8 months agoMITView on GitHub

Quick capture - classify and file natural language input into the vault. Part of chief-of-staff system. Use for capturing tasks, ideas, project notes, or people notes.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use upgrade, gate and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • agenticnotetakingSkill

    upgrade

    Apply plugin knowledge base updates to an existing generated system. Consults the Ars Contexta research graph for methodology improvements, proposes skill upgrades with research justification. Never auto-implements. Triggers on "/upgrade", "upgrade skills", "check for improvements", "update methodology".

    Also in 4 projects that use this

  • synaptiaiSkill

    gate

    Create a BDSK review_gate artifact. Defines a checkpoint that controls whether generated output may proceed toward acceptance. Use when defining quality, security, or scope gates for execution plans.

    Also in 3 projects that use this

  • kt057Skill

    check

    lint, typecheck, test を一括実行して結果をサマリーする

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 5 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create items from natural language: /new <input>

    line 10
  2. Distinctive:

    When creating a task without a due date, use AskUserQuestion:

    line 51
  3. Very specific:

    Use Obsidian wiki-style links [[slug]] in the markdown body to connect entities.

    line 67
  4. Very specific:

    When creating a task linked to a project, update the project file to include [[task-slug]].

    line 69
  5. Distinctive:

    Check if person/project already exists before creating (use Glob).

    line 71

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/new - Quick Capture

Create items from natural language: /new <input>

Input is in $ARGUMENTS.

Do NOT commit manually unless explicitly asked. A PostToolUse hook auto-commits after Write operations.

Steps

  1. Decompose - Extract ALL entities from input (may be multiple)
  2. Classify each entity: task | project | person | idea
  3. Extract structured data (due dates, tags, names)
  4. Link entities via frontmatter fields
  5. Write files for each entity (hook handles git commit)
  6. Respond with summary of what was created

Decomposition

Parse input for multiple entities. Example:

"new project with John Smith for marketing outbound, need landing page and brainstorm names"

Entities:

  • Person: John Smith
  • Project: marketing-outbound (linked to John Smith)
  • Task: create landing page (linked to project)
  • Task: brainstorm names for workshop (linked to project)

Classification

  • Named person with context → person
  • Ongoing work, multiple steps → project
  • Specific actionable item → task
  • Speculative, "what if" → idea
  • Confidence < 0.5 → Ask for clarification

Edge case: "start/begin/create X" → task (the action of initiating), not project.

  • "I need to start a content plan" → task: start content plan
  • "Working on the content plan" → project: content plan (if ongoing)

Missing Information

When creating a task without a due date, use AskUserQuestion:

Question: "When is this due?"
Header: "Due date"
Options:
  - "Today" → use today's date
  - "End of week" → use Friday of current week
  - "Next week" → use Monday of next week
  - (Other allows custom entry)

Apply similar pattern for other ambiguous fields when classification confidence is high but key data is missing.

Linking

Use Obsidian wiki-style links [[slug]] in the markdown body to connect entities.

When creating a task linked to a project, update the project file to include [[task-slug]]. Same for project → person links.

Check if person/project already exists before creating (use Glob). Use Read before editing existing files.

File Formats

Task:

---
type: task
status: pending
due: YYYY-MM-DD  # optional
tags: []
---
Description here.

Project:

---
type: project
status: active
tags: []
---
## Next Action
- First task to do
[[linked-task-slug]]

## Notes

Person:

---
type: person
last-contact: YYYY-MM-DD
tags: []
---
## Context
Who they are, relationship.

## Follow-ups
- [ ] Pending items

Idea:

---
type: idea
tags: []
---
Description of the idea.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.