workflow-diagnosis
Skill4 starsChanged 54 days agoMITView on GitHub
Diagnose a bounded bugfix or verified scenario failure before proposing a source correction.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- clean-implementationSkill
- code-reviewSkill
- core-analysisSkill
- core-debuggingSkill
- core-documentationSkill
- core-planningSkill
- core-securitySkill
- delivery-pipelineSkill
- domain-backendSkill
- domain-engineeringSkill
- domain-frontendSkill
- domain-mobileSkill
- flowcairn-controlSkill
- implementation-lessonSkill
- project-contextSkill
- testingSkill
- workflow-planningSkill
- workflow-reuseSkill
- workflow-test-qualitySkill
- workflow-verificationSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read the original criterion, current source owner, consumers, immutable test oracle and actual failed receipt/report.
≈ “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
Evidence before correction
- Read the original criterion, current source owner, consumers, immutable test oracle and actual failed receipt/report. A failed scenario confirms an observation; it does not automatically identify the cause.
- Distinguish a source defect, inconsistent plan, environment failure, wrong verifier and uncertain process. Name a falsifiable cause hypothesis and connect it to the relevant source and scenario. Use existing read-only evidence; the Executor runs checks after a brokered proposal.
- Correct source only when the hypothesis explains the original expected behavior. Keep the approved scope, interfaces, criteria and tests unchanged. Do not make a timeout disappear by disabling an assertion, weakening an expected result, adding an unapproved dependency or replacing a real integration with a mock.
- For missing capability, bad oracle, contradictory requirements or unresolved uncertainty, report the specific blocker and propose no speculative edits. No report, zero tests, unknown termination and stale inputs cannot authorize a repair.
- The existing repair budget is finite. A repair closes only with fresh required checks against the final source/artifact/environment; a self-reported diagnosis or successful edit is not proof.
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.

