ccl-skills / scripts
AGENTS.md6 starsChanged 3 months agoApache-2.0View on GitHub
Scripts here validate shared CCL skills, routing surfaces, extraction discipline, and structural invariants. - Keep validators deterministic and explicit about warning versus blocking status. - Do not broaden allowlists or downgrade failures without a recorded rationale and regression evidence. - Route/frontmatter checks must fail closed on malformed YAML or stale route references that affect behavior. - Script changes need self-tests or fixture coverage where feasible.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- eval/AGENTS.mdAGENTS.md
- hooks/AGENTS.mdAGENTS.md
- packages/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- skills/code-review/scripts/AGENTS.mdAGENTS.md
- skills/multi-perspective-research/scripts/AGENTS.mdAGENTS.md
- skills/product-rd-workflow/scripts/AGENTS.mdAGENTS.md
- skills/test-artifact-management/references/AGENTS.mdAGENTS.md
- skills/testing-strategy/scripts/AGENTS.mdAGENTS.md
- skills/tighten-doc/scripts/AGENTS.mdAGENTS.md
- skills/worktree-isolation/scripts/AGENTS.mdAGENTS.md
- agents-file-coverage-gateSkill
- app-cross-platform-devSkill
- code-reviewSkill
- defect-diagnosisSkill
- feature-risk-routerSkill
- go-microservice-architectureSkill
- go-microservice-devSkill
- grill-meSkill
- llm-inference-integrationSkill
- miniapp-product-devSkill
- multi-agent-delegationSkill
- multi-perspective-researchSkill
- nodejs-service-devSkill
- platform-observabilitySkill
- platform-release-engineeringSkill
- platform-service-connectivitySkill
- product-rd-workflowSkill
- product-ui-ux-designSkill
- python-service-architectureSkill
- python-service-devSkill
- release-coordinationSkill
- release-doc-writerSkill
- requirement-baselineSkill
- requirement-doc-writerSkill
- requirement-intentSkill
- requirement-scopeSkill
- skill-extraction-workflowSkill
- terminal-cli-devSkill
- test-artifact-managementSkill
- testing-strategySkill
- tighten-docSkill
- web-react-devSkill
- worktree-isolationSkill
The file
We split this AGENTS.md 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 8
Keep validators deterministic and explicit about warning versus blocking status.
- Distinctive: line 10
Do not broaden allowlists or downgrade failures without a recorded rationale and regression evidence.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
skills/skill-extraction-workflow/scripts Agent Contract
Scripts here validate shared CCL skills, routing surfaces, extraction discipline, and structural invariants.
Rules:
- Keep validators deterministic and explicit about warning versus blocking status.
- Do not broaden allowlists or downgrade failures without a recorded rationale and regression evidence.
- Route/frontmatter checks must fail closed on malformed YAML or stale route references that affect behavior.
- Script changes need self-tests or fixture coverage where feasible.
Validation:
bash skills/skill-extraction-workflow/scripts/check-ccl-skills.sh .
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.