agentleFS
maribolmaribol/overvibe/skills/tasks/SKILL.md

tasks

Skill2 starsChanged 3 days agoMITView on GitHub

Keep every request in the project's TASKS.md so none gets lost: add each one before starting it, tick only what is verified, list what waits on the owner. Use whenever you take on, finish or hand over a request.

51 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use send-user-message, tinyagi-admin 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.
  • Maliot100XSkill

    send-user-message

    Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp). Use when the agent needs to notify, alert, or send an unsolicited message to a user — especially during heartbeat invocations, scheduled tasks, or when the agent wants to reach out without a prior user message in the current conversation. Triggers: 'send message to user', 'notify user', 'alert user', 'message the user on discord/telegram/whatsapp', or any need to proactively communicate with a paired sender.

    Also in 4 projects that use this

  • jlia0Skill

    tinyagi-admin

    Manage and operate the TinyAGI system itself — agents, teams, settings, queue, tasks, daemon lifecycle, and source code. Use when the agent needs to: list/add/remove/update agents or teams, check queue status, view logs, start/stop/restart TinyAGI, change settings (provider, model, channels), send messages to the queue, manage tasks, retry dead-letter messages, view recent responses, modify TinyAGI source code or configuration, or perform any administrative operation on the TinyAGI platform. Triggers: 'manage tinyagi', 'add an agent', 'remove a team', 'check queue', 'view logs', 'restart tinyagi', 'change provider', 'update settings', 'create a task', 'modify tinyagi code'.

    Also in 3 projects that use this

  • ArvorCoSkill

    constitution

    Create or update the project constitution - personalized governance and coding principles. Use when starting a project or updating project standards. Triggers on: create constitution, update principles, set project rules.

    Also in 4 projects that use this

  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 6 projects that use this

  • GoogleSkill

    quality

    Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.

    Also in 3 projects that use this

  • anyprotoSkill

    skills-manager

    Context-aware routing to skills and hooks management. Use when troubleshooting skill activation, fine-tuning keywords, or managing the automated documentation system.

    Also in 3 projects that use this

  • +1 more from ArvorCo

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 44 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Run them in the project folder or pass --dir <folder>.

    line 27
  2. Distinctive:

    Put under Waiting on the owner only what the owner alone can do: a decision, a login, a payment, approving a deploy.

    line 40
  3. Distinctive:

    Never delete an open line you did not finish.

    line 47
  4. Distinctive:

    Commit the tick with the work when it is already verified, otherwise in one follow-up commit after the check.

    line 62
  5. Very specific:

    Run overvibe tasks check. It lists ticked lines outside Done, lines without an id, an id used twice, ticks that do not say how they were …

    line 66

“Common” is measured: kept by at least 6 in 10 of the 44 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

Tasks (TASKS.md)

Why: when requests pile up, or the context is compacted, agents forget some of them. One line per request in the project's TASKS.md is the record that survives.

The rule

  • Every request gets its own line before you start it. That includes requests sent mid-turn and each one in a message that asks for several things. Add them all first, then work.
  • Before you end a turn, read back the open lines you added. Say which are still open and why. Never end a turn as if everything is done while one of your lines is open.
  • After a compaction or a resume, read TASKS.md first, before anything else.

Adding a line

overvibe tasks add "<what, in one sentence>"            # under To do; prints the id, e.g. T1112-15
overvibe tasks add --waiting "<what the owner must do>"  # under Waiting on the owner
overvibe tasks id                                        # only an id, if you write the line yourself

Run them in the project folder or pass --dir <folder>. The file is TASKS.md at the git repo's top; add makes it with its three sections when it is missing. The line it writes:

- [ ] T1112-15 2026-11-12 <what> · session e411f976

The id is T<MMDD>-<n> (the next free one for today, never reused). The session tag is the first 8 characters of your session id, so the owner can open your session from the Tasks view in Overvibe. add finds it for you: Claude Code's $CLAUDE_CODE_SESSION_ID, Codex's $CODEX_THREAD_ID, or Overvibe's record for $OVERVIBE_SESSION. Outside those, pass --session <id8> or leave the tag off. Working on a line someone else added? Add your own tag after theirs (· session <theirs> · session <yours>).

Put under Waiting on the owner only what the owner alone can do: a decision, a login, a payment, approving a deploy. Everything you can do yourself goes under To do.

While you work

  • The id goes in branch names and commit subjects: feat/T1112-15-tasks-skill, Tasks skill and CLI [T1112-15].
  • A follow-up you promise, or a bug you find and will not fix now, is a request too: give it a line.
  • Never delete an open line you did not finish. Say on it what is left instead.

Ticking

Tick a line only when the result is verified: a test that passes, a page that answers, a screenshot. Written code is not done. A ticked line says the commit and how it was checked, and moves under ## Done, below a heading for the day (add the heading if today has none):

## Done

### 2026-11-12
- [x] T1112-15 2026-11-12 <what> · <commit> · checked: bun test, live run on a scratch repo · session e411f976

Commit the tick with the work when it is already verified, otherwise in one follow-up commit after the check.

Before you end the turn

Run overvibe tasks check. It lists ticked lines outside Done, lines without an id, an id used twice, ticks that do not say how they were checked, and ids already in commits on main whose line is still open. Fix what it lists for your lines.

The file

# TASKS

## Waiting on the owner
- [ ] T1112-3 2026-11-12 Approve the price change on the pricing page · session 1a2b3c4d

## To do
- [ ] T1112-2 2026-11-12 Fix the login button on mobile · session 1a2b3c4d

## Done

### 2026-11-12
- [x] T1112-1 2026-11-12 Add the export button · 9f8e7d6 · checked: bun test, clicked it on the local page · session 1a2b3c4d

New lines go first in their section. A repo's deck.json can name another file ("tasks": "docs/TASKS.md"); the CLI and the Tasks view both follow it.

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.