workflow-planning
Skill4 starsChanged 54 days agoMITView on GitHub
Plan coherent observable outcomes, interfaces and verification boundaries before brokered implementation.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- unional/skillstheir own version, first seen Nov 6, 2026
- microsoft/agora-workbenchtheir own version, first seen Oct 13, 2026
- NVIDIA/Quantum-Calibration-Agent-Blueprinttheir own version, first seen Apr 20, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- NVIDIA/Quantum-Calibration-Agent-Blueprint★ 69same name
- microsoft/agora-workbench★ 10same name
- unional/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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-diagnosisSkill
- workflow-reuseSkill
- workflow-test-qualitySkill
- workflow-verificationSkill
The file
Files
Dependency-aware work
- Preserve the original requirements and their IDs. Read the affected owner, consumers and existing verification before proposing changes. Separate facts, assumptions and material unknowns.
- Decompose by an observable outcome with a useful verification boundary. A cross-layer user scenario may be one work item. Do not split by arbitrary file counts, lines or duration. For a broad compatible migration, use expand, migrate, contract only when each boundary is independently checkable.
- Declare requirementIds, paths, needed readPaths and real needs. When one work produces an interface consumed by another, use produces/consumes with the exact same contract and explicit producer dependency. Do not use execution order as a substitute for that dependency.
- Review coverage, orphan work, cycles, conflicting interfaces and missing verifiers before source changes. A human acceptance or unavailable environment is an explicit remaining obligation, never an objective pass.
- A structural gate confirms only the structure it actually checks. Semantic assumptions need relevant source or provider review. Correction must retain intent, scope, criteria and permissions and use the Executor's bounded immutable replan mechanism.
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.

