compound-knowledge-summary
Skill0 starsChanged 8 months agoMITView on GitHub
Use when API delivery work is verified and the agent should turn validated lessons into reusable knowledge for future tasks
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- backend-contract-exit-gateSkill
- brainstormingSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- frontend-contract-entry-gateSkill
- recall-contract-contextSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- writing-plansSkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 14
Use this skill when:
- Distinctive: line 36
Do not promote unverified guesses into patterns.
- Distinctive: line 37
Keep one summary per task or change set.
≈ “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
Compound Knowledge Summary
Overview
Successful work should compound. After verification, convert durable lessons into repository knowledge so future agents can recall them instead of improvising again.
When to Use
Use this skill when:
- backend and frontend contract work is verified
- a gate failure exposed a repeatable pattern
- a delivery changed DTO, envelope, naming, or OpenAPI conventions
Process
- Summarize what worked, what failed, and what contract assumptions were validated.
- Record the summary using
templates/compound-summary.md. - Promote stable lessons into
knowledge/patternswhen they are reusable. - Record breakages or cautionary cases in
knowledge/incidents.
Required Content
- contract surface touched
- which recall items helped
- new knowledge worth preserving
- whether the lesson belongs in
summary,pattern, orincident
Guardrails
- Do not promote unverified guesses into patterns.
- Keep one summary per task or change set.
- Tie new knowledge back to concrete contract behavior.
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.