continual-improvement-check
Skill1 starsChanged 14 days agoMITView on GitHub
Use when planning or developing an AI or agent workflow that will handle repeated real tasks. Ask whether its outcomes could improve later versions.
In this repository43 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/adopt-skill-stack.mdcCursor rule
- adopt-skill-stackSkill
- api-and-interface-designSkill
- astrobyte-architectSkill
- astrobyte-git-identitySkill
- astrobyte-modeSkill
- astrobyte-project-startupSkill
- astrobyte-pr-workflowsSkill
- astrobyte-recallSkill
- astrobyte-reviewSkill
- astrobyte-show-workSkill
- astrobyte-tddSkill
- astrobyte-verify-projectSkill
- blast-radiusSkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- codebase-designSkill
- deprecation-and-migrationSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- frontend-designSkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- grillingSkill
- handoffSkill
- hermetic-test-suitesSkill
- observability-and-instrumentationSkill
- performance-optimizationSkill
- pr-feedback-loopSkill
- prototypeSkill
- researchSkill
- security-and-hardeningSkill
- setup-astrobyte-skillsSkill
- shipping-and-launchSkill
- source-driven-developmentSkill
- technical-writingSkill
- to-questionnaireSkill
- typescript-best-practicesSkill
- unslopSkill
- update-skill-stackSkill
- writing-for-agentsSkill
The file
Files
Continual improvement check
For an AI or agent workflow that will handle repeated real tasks, ask:
Could representative real outcomes from this system become evaluated improvements to later versions?
Record a one-sentence answer in the plan. If yes, name one outcome signal worth keeping and one quality check that could judge it. Stop there unless the user asks to design the improvement loop.
Done when the plan contains a direct answer.
Inspired by Shopify Engineering's Sidekick continual-learning loop: https://shopify.engineering/sidekicks-continual-learning-loop
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.