task-prompts
Skill13 starsChanged yesterdayMITView on GitHub
Write agent task, delegation, and handoff prompts; resume or compact agy and Claude Code sessions.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- fmind/dotword for word, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 1
- fmind/dot★ 13100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository62 other files it gives its agents.
- AGENTS.mdAGENTS.md
- dot_agents/AGENTS.mdAGENTS.md
- skills/repository-docs/references/agents.mdAGENTS.md
- claudeCLAUDE.md
- chezmoiSkill
- dot-developmentSkill
- dot-releaseSkill
- dot-skillsSkill
- acliSkill
- agent-frameworksSkill
- agent-harnessesSkill
- agent-projectSkill
- agent-protocolsSkill
- agySkill
- airflowSkill
- auth-statusSkill
- awsSkill
- bfSkill
- cfSkill
- chrome-devtoolsSkill
- clipboardSkill
- cloud-runSkill
- code-securitySkill
- colabSkill
- databricksSkill
- diagrams-as-codeSkill
- dockerSkill
- documentation-siteSkill
- dot-cliSkill
- draft-docSkill
- draft-mailSkill
- draft-typst-deckSkill
- duckdbSkill
- fmindSkill
- full-reviewSkill
- gcloudSkill
- ghSkill
- git-deliverySkill
- github-actionsSkill
- gwsSkill
- hfSkill
- humanizeSkill
- infra-as-codeSkill
- kaggleSkill
- kubernetesSkill
- miseSkill
- model-providersSkill
- playwrightSkill
- project-scaffoldingSkill
- pupSkill
- python-mlopsSkill
- python-stackSkill
- python-webSkill
- repository-docsSkill
- scheduled-jobsSkill
- skillifySkill
- <name>Skill
- terms-reviewSkill
- trimSkill
- upgrade-toolsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Write self-contained prompts for an agent without this conversation.
- Very specific: line 20
Capture state: check git status --short --branch, completed proof, exact stopping point, remaining work, failed approaches, and key …
- Very specific: line 22
Save and verify: write .agents/prompts/<YYYY-MM-DD>-<slug>.md under git rev-parse --show-toplevel (or ~/.agents/prompts/ outside Git), …
- Very specific: line 35
Cite, never paste: keep failures and proof gaps.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Task and Continuation Prompts
Write self-contained prompts for an agent without this conversation. agent-frameworks owns embedded application prompts; prefer native resume or compaction via continuation when session state carries over.
Workflow
- Choose the mode: fresh task or continuation; lock down outcome, latest corrections, scope, and acceptance criteria.
- Capture state: check
git status --short --branch, completed proof, exact stopping point, remaining work, failed approaches, and key decision rationales. Before/clear, follow continuation to save and copy the handoff. - Draft non-empty sections: objective, authority, constraints and rejected approaches, verified facts, current state, next step, verification, and return (plus ordered slices only when needed).
- Save and verify: write
.agents/prompts/<YYYY-MM-DD>-<slug>.mdundergit rev-parse --show-toplevel(or~/.agents/prompts/outside Git), confirm zero hidden-context assumptions, and report the path.
Task guides
<!-- guides:start -->- continuation: Resume, compact, or fork agy and Claude Code sessions, or copy a handoff prompt before /clear.
<!-- guides:end -->Gotchas
- Authority travels with the task: separate approved actions from proposals; writing a prompt grants no new permission.
- Cite, never paste: keep failures and proof gaps; reference
path:lineinstead of copying code orAGENTS.md. - Keep
.agents/prompts/untracked: global Git ignore covers it (git check-ignore -v .agents/prompts/x.md); add no repo ignore rule, and commit prompts only on request.
Documentation
- Companions: clipboard, git-worktree.
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.

