targeted-validation
Skill4 starsChanged 52 days agoMITView on GitHub
Choose and run proportionate validation after a coherent code change. Use near completion of implementation, fixes, refactors, or dependency changes; not after every edit.
In this repository37 other files it gives its agents.
- global-instructions/AGENTS.mdAGENTS.md
- api-contract-safetySkill
- api-endpoint-deprecationSkill
- aspnet-core-api-developmentSkill
- background-services-dotnetSkill
- bug-investigationSkill
- code-qualitySkill
- code-reviewSkill
- context-resetSkill
- dependency-managementSkill
- deployment-readiness-dotnetSkill
- diff-reviewSkill
- distributed-workflowsSkill
- dotnet-architectureSkill
- dotnet-implementationSkill
- dotnet-securitySkill
- ef-core-safetySkill
- exception-handlingSkill
- git-workflowSkill
- google-bigquery-dotnetSkill
- google-cloud-pubsub-dotnetSkill
- google-firestore-dotnetSkill
- http-client-integrationsSkill
- integration-testing-dotnetSkill
- observability-dotnetSkill
- performance-diagnostics-dotnetSkill
- poc-developmentSkill
- production-debuggingSkill
- production-hotfixSkill
- production-loggingSkill
- redis-dotnetSkill
- relational-database-dotnetSkill
- retry-resilienceSkill
- safe-terminalSkill
- shared-code-impactSkill
- task-routerSkill
- unit-testingSkill
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 14
Use repository-provided scripts and CI-equivalent options when available.
- Distinctive: line 16
Do not repeatedly run an unchanged expensive suite.
≈ “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
Targeted validation
Validate after a coherent implementation and diff inspection. Choose the lowest-cost command that provides relevant confidence, then broaden only for risk, dependency reach, or failures:
affected test(s) -> affected test project -> affected project build -> solution build/testUse repository-provided scripts and CI-equivalent options when available. Include analyzers, formatting, contract/integration tests, coverage, or packaging only when the change or project workflow calls for them. A targeted compile during implementation is reasonable when it resolves real uncertainty.
Do not repeatedly run an unchanged expensive suite. Do not fix unrelated failures. Re-run only validation invalidated by subsequent edits.
Report exact commands and outcomes. For failures, distinguish caused-by-change, pre-existing/unrelated, and inconclusive/environmental results, with concise evidence. Never claim success for a check that was not run.
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.