agentleFS
quietdaemonquietdaemon/starter-skills/skills/idea-inbox/SKILL.md

idea-inbox

Skill1 starsChanged 5 months agoMITView on GitHub

Instantly capture an idea, task, or note into a backlog file and commit it — capture-first, zero friction. Use when the user says /idea ..., add idea: ..., capture this, log this, or tosses out a concept they don't want to lose.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. jqaisystems/jqai-ai-skills★ 3same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Idempotent-ish: if a commit fails (e.g. dirty tree mid-edit), report it rather than silently dropping the idea — the one thing this skill …

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Idea Inbox

A friction-free capture chute. The user throws an idea at the assistant; it lands in a backlog file with a timestamp and is committed — in seconds, no questions asked. The whole value is speed and zero-loss: never make the user stop to categorize, confirm, or format. Capture first; organize later.

When to activate

The user:

  • Uses /idea ..., add idea: ..., capture this: ..., or log this: ...
  • Describes a concept they clearly want kept ("I was thinking we could…")

What you do

  1. Extract the core idea from the message.
  2. Format one line: YYYY-MM-DD — <concise idea> (optionally — <tag> if a category is obvious — best guess only, never ask).
  3. Append + commit via the helper:
    python3 <AGENT_HOME>/scripts/idea_inbox.py "<formatted line>"
    (Give it ~30s; it does a git commit.)
  4. On success (OK — captured): reply with just a short confirmation ("Captured."). Nothing more.
  5. On failure: surface the error and offer to retry.

The capture-first rule (the point of this skill)

  • Do not ask for clarification — not the category, not the format, nothing. A 60-second capture that's slightly mis-tagged beats a perfect one the user abandoned mid-thought.
  • Do not add commentary, critique, or suggestions alongside the capture. This is an inbox, not a conversation.
  • Commit to a best guess on any optional field and move on.

Where it goes

A single Markdown backlog, e.g. <BACKLOG_FILE> (an ## Inbox section the user triages later). Keep one predictable home so nothing scatters.

Pitfalls

  • Don't let it become a chat. The failure mode is the assistant "helpfully" asking which project this belongs to — that defeats the entire purpose.
  • Idempotent-ish: if a commit fails (e.g. dirty tree mid-edit), report it rather than silently dropping the idea — the one thing this skill must never do is lose a capture.
  • Keep it scoped: capture ideas, not arbitrary long documents. Big writeups belong in their own file, not the inbox line.

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.