aio-compound
Skill0 starsChanged 31 days agoMITView on GitHub
Capture a verified backend investigation as a searchable original lesson when its causal reasoning is absent from code, tests and existing docs; update stale lessons instead of creating duplicates. Use after non-obvious agent, pipeline, data or recovery work is solved.
In this repository54 other files it gives its agents.
- agent-workflowsSkill
- aio-agentsSkill
- aio-algorithmsSkill
- aio-apiSkill
- aio-architectureSkill
- aio-autoplanSkill
- aio-benchmarkSkill
- aio-brainstormSkill
- aio-canarySkill
- aio-checkpointSkill
- aio-ciSkill
- aio-commitSkill
- aio-dataSkill
- aio-debugSkill
- aio-devex-reviewSkill
- aio-doc-reviewSkill
- aio-explainSkill
- aio-feedbackSkill
- aio-handoffSkill
- aio-ideateSkill
- aio-observeSkill
- aio-optimizeSkill
- aio-pipelinesSkill
- aio-plan-reviewSkill
- aio-planSkill
- aio-proofSkill
- aio-prototypeSkill
- aio-qa-onlySkill
- aio-qaSkill
- aio-releaseSkill
- aio-resumeSkill
- aio-reviewSkill
- aio-securitySkill
- aio-shipSkill
- aio-simplifySkill
- aio-specSkill
- aio-tddSkill
- aio-test-auditSkill
- aio-testSkill
- aio-verifySkill
- aio-workSkill
- aio-worktreeSkill
- all-in-oneSkill
- apple-appstore-reviewerSkill
- backend-algorithmsSkill
- backend-debugSkill
- backend-pipelinesSkill
- backend-planSkill
- backend-reviewSkill
- backend-verifySkill
- complete-destructionSkill
- launch-readinessSkill
- play-policy-insightsSkill
- reverse-engineer-anythingSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Search existing project lessons and relevant backend knowledge.
- Distinctive: line 12
Update the matching lesson when it is stale or incomplete.
≈ “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
AIO Compound
Retain knowledge that prevents recurrence or substantial rediscovery. Completion, effort and a large diff are not reasons to add documentation. Read lesson procedure and use lesson only when the lesson earns a durable record.
- Confirm the problem is solved and the causal claim verified against the current tree and observed evidence. Unconfirmed hypotheses stay in the diagnostic log, not the knowledge base.
- Search existing project lessons and relevant backend knowledge. Decide whether the reasoning would be lost without a lesson. Code/tests that already explain it usually need no duplicate document.
- Update the matching lesson when it is stale or incomplete. Otherwise write one focused original lesson with context, trigger, invariant, root cause, failed hypotheses, evidence, verified remedy, limits, retrieval terms and refresh conditions.
- Validate cited artifacts, path containment and claims; check search terms retrieve the lesson and distinguish it from similar problems. Update the project's existing index or a contained lesson index for new durable records.
- Return the lesson path, what is now retrievable and any remaining limits, or report that no qualifying lesson was written. Do not change instruction files or publish knowledge externally merely to make it discoverable.
This skill captures actual learning and returns to its caller. It does not start a new build, duplicate upstream manuals or add speculative global rules to every future 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.

