plan-vs-built
Skill1 starsChanged 3 months agoCC-BY-4.0View on GitHub
Compare what repos have ACTUALLY built -- binaries, tests that run, container tags, deployed manifests, live endpoints -- against what their plan.md says should exist, then create beads for the gap. Sweeps EVERY repo with a plan by default; narrows to one only when given a path. Classifies every plan deliverable as BUILT / UNPROVEN / PARTIAL / STUB / ABSENT / DIVERGENT / PLAN-STALE from observed artifacts rather than from prose, docs, commit messages, or closed beads; separately flags falsely-closed beads whose deliverable does not exist. Use when asked what's left to build, whether a project is really done, how far the code has drifted from the plan, or to turn that gap into tracked work.
In this repository18 other files it gives its agents.
- adrSkill
- api-design-reviewSkill
- diff-reviewSkill
- find-stubsSkill
- migration-runbookSkill
- plan-authorSkill
- plan-gap-reviewSkill
- plan-idea-genSkill
- plan-reviewSkill
- plan-to-beadSkill
- postmortemSkill
- readme-reviewSkill
- release-readinessSkill
- repo-hygieneSkill
- spec-reviewSkill
- test-plan-reviewSkill
- threat-modelSkill
- usage-statuslineSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 5 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.