agentleFS
gabrieldabbahgabrieldabbah/genesis/skills/todo/SKILL.md

todo

Skill4 starsChanged 4 months agoMITView on GitHub

Maintain the project's master TODO — the internal backlog in docs/TODO.md and its dated archive docs/TODO-done.md. Use when adding/updating/sorting TODO items, marking something in-progress/implemented/verified/done, asking \"what should I do next\", or mentioning \"/todo\". Uses explicit status markers ([ ] not started, [~] in progress, [?] implemented-but-unverified, [x] done), a separate [P] priority marker, verification type (🤖 auto vs 🙋 needs-human), and exposure tags. Orders by priority → ease → dependency count. Archives a whole completed section into docs/TODO-done.md under today's real date — an [x] inside a section still in progress stays. Never invents a date.

37 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use standup, update-docs and 10 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.
  • AnthropicSkill

    standup

    Generate a standup update from recent activity. Use when preparing for daily standup, summarizing yesterday's commits and PRs and ticket moves, formatting work into yesterday/today/blockers, or structuring a few rough notes into a shareable update.

    Also in 3 projects that use this

  • Hugging FaceSkill

    update-docs

    Update documentation across the repo after API changes. Finds stale references in docs, examples, docstrings, and fixes them.

    Also in 3 projects that use this

  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 3 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 5 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 4 projects that use this

  • photon-groveSkill

    unslop

    Detects and rewrites generic, overly polished, or AI-sounding prose while preserving meaning. Use when the user asks to "unslop", humanize, de-AI, tighten, or review whether writing sounds generated.

    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, 0 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 34 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Keep the project's docs/TODO.md (the live backlog) and docs/TODO-done.md (the dated archive) accurate, honest, and well-ordered.

    line 10
  2. Very specific:

    Move on done — a whole section, not an item: When a heading section holds no open items at all, move the section into docs/TODO-done.md …

    line 30
  3. Very specific:

    Do not move an item to done without its verification having actually been observed.

    line 39
  4. Very specific:

    Keep it truthful: stalled work is [~] with a note, not a silent [ ].

    line 47
  5. Very specific:

    Never invent a date; never delete history from TODO-done.md.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 34 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

Maintain the master TODO

Keep the project's docs/TODO.md (the live backlog) and docs/TODO-done.md (the dated archive) accurate, honest, and well-ordered. Template + full legend live in those files' headers.

Status markers (status first, then optional priority)

  • [ ] not started · [~] in progress / partial · [?] implemented but unverified (code looks done, not yet proven) · [x] done and verified.
  • [P] is a separate priority marker, prepended: [ ] [P] ….
  • Verification type on every item: 🤖 = an agent can prove it with a test/command · 🙋 = needs a human (manual test, judgment, real-world check). Every item carries a → verify: line stating exactly how.
  • Exposure tags (optional): 🌍 public-eligible · 🔒 internal-only · ⚖ needs ToS/Privacy review.

What this skill does

  • Add an item to the right section with a status marker, verification type + → verify:, deps:, and any tags. New work without a clear verify is incomplete — ask or infer one.
  • Advance status: [ ]→[~]→[?]→[x]. Set [?] when code is written but the verify has not passed yet; do not jump to [x] on assumption.
  • Sort open items by priority → ease → dependency count (quick unblocked wins first, then foundational, then dependent systems). Keep ## 0. In-flight to what's actively in progress.
  • Move on done — a whole section, not an item. When a heading section holds no open items at all, move the section into docs/TODO-done.md under today's real date (read it from the system, never invent it), preserving the descriptions and the evidence (the command that passed, the PR, who verified). An [x] inside a section still in progress stays: it records that one part is built while the unit is not, and moving a finished part out of an unfinished whole strips the whole of the context needed to finish it.
  • After a move, grep the moved titles — index lines elsewhere that pointed into that section now dangle.

Hard rules

  • Do not move an item to done without its verification having actually been observed. [?] is the honest holding state for "implemented, not proven."
  • Default every item to 🤖. Make items auto-verifiable: write the e2e, visual, contract or injected-error test that proves it. A 🤖 item is not something to ask the user to check.
  • Reserve 🙋 for genuine human-acceptance only: a subjective look-and-feel call, or a check needing the human's credentials / a live deploy (account/login/live-key/deploy work). The autonomous loop does not stop to ask about 🙋 items: it builds everything around them, defers them to docs/DEPLOYMENT.md, and keeps going; they are handed off and run together at the end. A 🙋 item is never auto-closed.
  • Keep it truthful: stalled work is [~] with a note, not a silent [ ].
  • Never invent a date; never delete history from TODO-done.md.

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.