small-task
Skill0 starsChanged 45 days agoMITView on GitHub
Always-on task framing, injected every prompt: say what DONE proves, name blockers, micro-steps with checks, riskiest first, scope lock. Over one sitting or ~7 steps: long-task.
In this repository34 other files it gives its agents.
- audit-codeSkill
- audit-docsSkill
- auditSkill
- bisect-driverSkill
- coding-conventionsSkill
- commit-gateSkill
- compact-ioSkill
- cron-task-manageSkill
- cve-auditSkill
- data-integrity-auditSkill
- decision-logSkill
- deck-builderSkill
- determinism-guardSkill
- etl-validateSkill
- experiment-logSkill
- fetch-firstSkill
- flaky-test-detectorSkill
- github-repo-polishSkill
- golden-lockSkill
- history-leak-scanSkill
- landing-checkSkill
- llm-eval-harnessSkill
- local-secrets-manageSkill
- long-taskSkill
- milestone-trackSkill
- opus-workersSkill
- path-quirk-auditSkill
- reorg-proposalSkill
- research-briefSkill
- seed-controlSkill
- shell-portabilitySkill
- skill-vetSkill
- token-squeezeSkill
- venue-fitSkill
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
- Distinctive: line 10
Before the first edit or command of a task:
≈ “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.
Files
Before the first edit or command of a task:
- DONE — one testable sentence: the output, state, or exit code that proves it. Say it before starting.
- BLOCKERS — anything not on disk yet (a key, an account, someone else's change, the owner's decision)? Name it first; a reported block beats a guessed workaround.
- MICRO-STEPS — list them, each ending in "→ verify:
<check>". - RISKIEST FIRST — the step most likely to fail or to change the plan runs first.
- SCOPE LOCK — this task only. Unrelated bugs get named, not fixed.
A chat question needs none of this — answer it. More than one sitting or ~7 steps → long-task.
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
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.