completeness-qa
Skill0 starsChanged 11 days agoMITView on GitHub
Inventory public functions, flag stubs and untested symbols, and name the next skills that raise SWE quality for this change. Use after implement, before claiming done, or when asked to QA, find missing tests, or catch half-done functions.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- api-and-interface-designSkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- context-engineeringSkill
- debugging-and-error-recoverySkill
- deprecation-and-migrationSkill
- documentation-and-adrsSkill
- doubt-driven-developmentSkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- idea-refineSkill
- incremental-implementationSkill
- interview-meSkill
- observability-and-instrumentationSkill
- performance-optimizationSkill
- planning-and-task-breakdownSkill
- security-and-hardeningSkill
- shipping-and-launchSkill
- source-driven-developmentSkill
- spec-driven-developmentSkill
- test-driven-developmentSkill
- using-agent-skillsSkill
- kit-ci-triageSkill
- kit-evalsSkill
- kit-provider-adaptersSkill
- kit-releaseSkill
- kit-tuiSkill
- a11y-passSkill
- add-readmeSkill
- api-docsSkill
- changelogSkill
- cli-helpSkill
- code-reviewSkill
- data-checkSkill
- deps-hygieneSkill
- fix-bugSkill
- project-setupSkill
- pr-readySkill
- ship-checklistSkill
- workspace-setupSkill
- write-testsSkill
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
- Very specific: line 13
Prefer the git diff. If there is no diff, scan src/, lib/, crates/, app/.
- Very specific: line 14
Run node scripts/inventory.mjs from this skill folder (--root = project).
- Distinctive: line 15
Do not invent symbols the script did not list.
- Very specific: line 19
Do not write production code or tests unless the user asked.
≈ “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
Instructions
- Prefer the git diff. If there is no diff, scan
src/,lib/,crates/,app/. - Run
node scripts/inventory.mjsfrom this skill folder (--root= project). If Node is missing, followreferences/scan-rules.mdby hand. - Do not invent symbols the script did not list.
- Rank “test next” using
references/swe-quality-ladder.md. Print at most five rows. Never drop astub. - Name at most three follow-on catalog skills, each with a reason from the findings. Do not recommend skills outside the ladder file.
- Print the script report. Keep
.kit/completeness.jsonwhen the project is writable. - Do not write production code or tests unless the user asked. Point at
write-testsorfix-bug.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.