audit-task
Skill486 starsChanged 15 days agoApache-2.0View on GitHub
Launch a subagent to critically and exhaustively audit a task plan markdown file. Looks for bugs, inconsistencies, missing features, and inaccurate, wrong, or dangerous steps.
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
- Very specific: line 12
Read the provided <file> (which is typically a Markdown file in the task/ folder).
- Very specific: line 15
Read the plan in the provided <file>.
- Distinctive: line 17
Look for bugs, inconsistencies, and missing features.
- Distinctive: line 20
Wait for the subagent to complete its analysis.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Audit Task
This skill is invoked when the user runs the /audit-task <file> slash command.
Procedure
- Read the provided
<file>(which is typically a Markdown file in thetask/folder). - Launch a subagent using the
invoke_subagenttool withModel: "inherit". You can use an existing subagent likeresearch, or define a new one for this specific purpose. - The prompt for the subagent MUST instruct it to:
- Read the plan in the provided
<file>. - Audit the plan critically and exhaustively.
- Look for bugs, inconsistencies, and missing features.
- Identify any inaccurate, wrong, or dangerous steps/instructions.
- Report its findings clearly and systematically.
- Read the plan in the provided
- Wait for the subagent to complete its analysis.
- Present the subagent's findings to the user in a clear, structured report.
In this repository30 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- build-infra/AGENTS.mdAGENTS.md
- rust-analyzer-mcp-server/AGENTS.mdAGENTS.md
- task/AGENTS.mdAGENTS.md
- llms.txtllms.txt
- analyze-log-filesSkill
- analyze-performanceSkill
- batch-refactor-with-sub-agentsSkill
- check-bounds-safetySkill
- check-code-qualitySkill
- check-test-coverageSkill
- code-reviewSkill
- concurrency-safetySkill
- create-commit-messageSkill
- create-prSkill
- design-philosophySkill
- fast-string-allocationsSkill
- fix-issueSkill
- merge-prSkill
- organize-modulesSkill
- organize-testsSkill
- release-crateSkill
- remove-crate-prefixSkill
- review-prSkill
- run-clippySkill
- safe-renamingSkill
- test-cross-platformSkill
- write-documentationSkill
- write-structured-tracingSkill
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.