spec
Skill1 starsChanged 53 days agoMITView on GitHub
Use when a request leaves done, data, architecture or a trade-off open. When a new visual surface does not name its data or behavior, spec decides those first; design-ui follows for presentation. Not for a clear goal, a failure, or visual-only work.
168 other projects use a version of this.
Adopted by
Most recently taken up by
- thistleknot/skillstheir own version, first seen Nov 8, 2026
- varelaia/claude-skills-publictheir own version, first seen Nov 8, 2026
- mrlemoos/galiciatheir own version, first seen Nov 8, 2026
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
- standardagents/skillstheir own version, first seen Nov 8, 2026
- Surething-io/cockpittheir own version, first seen Nov 8, 2026
Used with
Projects with it also use backprop, ios-clean and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JuliusBrusseeSkillbackprop
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
Also in 4 projects that use this
Saqlain-811Skillios-clean
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
Also in 5 projects that use this
- Saqlain-811Skill
ios-fix
Autonomous iOS bug fixer. (gstack)
Also in 5 projects that use this
bastosSkillios-design-review
Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".
Also in 5 projects that use this
ShreyRaviSkillplan-tune
Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.
Also in 7 projects that use this
timurgaleevSkilldocument-generate
Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.
Also in 6 projects that use this
- +2 more from Saqlain-811
Other versions168 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 168
- garrytan/gstack★ 141ksame name
- getsentry/sentry-react-native★ 1.8ksame name
- JuliusBrussee/cavekit★ 1.1ksame name
- kdlbs/kandev★ 1.1ksame name
- getsentry/sentry-dart★ 878same name
- poshan0126/dotclaude★ 871same name
- codewithmukesh/dotnet-claude-kit★ 808same name
- SparkDevNetwork/Rock★ 701same name
- hyperlink-academy/leaflet★ 527same name
- strands-agents/box★ 503same name
158 more not listed
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 repository10 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- buildSkill
- configureSkill
- edit-skillsSkill
- find-causeSkill
- gateSkill
- save-sessionSkill
- shipSkill
- watchSkill
- write-docsSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 145 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Read references/verdict.md for the no-question case.
- Very specific: line 19
Ask only per ../../lib/references/question.md ## When to ask.
- Very specific: line 20
When the user asked for options, follow references/architecture-sketch.md and write no file.
- Distinctive: line 22
When running or reading code answers a point, record it.
- Very specific: line 27
Ask per ../../lib/references/question.md, and record each choice exo decides in Decisions.
- Very specific: line 28
Read references/step-rules.md for recommendations and the Land: question.
- Distinctive: line 29
After the last answer, write the brief with no recap and no yes question.
“Common” is measured: kept by at least 6 in 10 of the 145 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Shaping
Shaping turns a request into a brief that settles what done means, so the build starts with no open decision.
Steps
- Gate.
- First invoke every installed non-
exo:skill matching the request. - Spec always ends on a brief; with no open decision the brief still gets written.
- Open with the verdict.
- An open decision is one the user would notice that neither request nor code settles.
- Read
references/verdict.mdfor the no-question case. - Ask only per
../../lib/references/question.md## When to ask. - When the user asked for options, follow
references/architecture-sketch.mdand write no file.
- First invoke every installed non-
- Sort each point.
- When running or reading code answers a point, record it; ask nothing.
- Each open decision passes
## When to ask. A plain product choice only the user can make becomes a question, root first; exo decides any other. - A decision the user left open stays open whatever the code does.
- Name the owning layer and a smaller option.
- Ask one at a time.
- Ask per
../../lib/references/question.md, and record each choice exo decides in Decisions. - Read
references/step-rules.mdfor recommendations and theLand:question. - After the last answer, write the brief with no recap and no yes question.
- Ask per
- Dispatch steps 4 to 8 as one
exo:orchestratorpart withWorkers: 1,Reads: noneand a Result file under.exo/. It runs:node "${CLAUDE_SKILL_DIR}/scripts/repo-map.mjs",, thenreferences/step-rules.md.- List tasks per
references/task-list.md,references/brief.mdandreferences/templates.md; store perreferences/brief.md. node "${CLAUDE_SKILL_DIR}/scripts/plan-check.mjs" --plan <brief file> --root <checkout root> --loop; fix flagged lines and any missing heading,Data:, Success criterion or## Manual checks.- Open points per
references/brief.md## Open points step, then rerun plan-check; leave flagged## Open pointsunfixed.
- Hand off per
references/hand-off.md.
References
| File | Read it when |
references/stored-brief.md | Request names or extends a brief, issue or plan. |
../../lib/references/question.md | Each question and reply. |
references/brief.md | Before writing the brief; step 4. |
references/task-list.md | Before writing the task list. |
references/example-plan.md | Before the first task. |
references/templates.md | Step 4. |
../build/references/data-migration.md | When its first line applies. |
../build/references/test-design.md | When its first line applies. |
../build/references/security.md | When its first line applies. |
references/brief-in-an-issue.md | specs is issues or both. |
../ship/references/fields.md | Before creating that issue. |
references/architecture-sketch.md | Two or more structural shapes compete. |
../../docs/principles/README.md | Request adds or changes an LLM agent, its prompt, tools or loop. |
references/verdict.md | Step 1. |
references/step-rules.md | Steps 1, 3, 4, mode research. |
references/hand-off.md | Step 5. |
references/watching.md | Step 5, run started. |
references/measured-goal.md | Goal is a measured score, cost or time. |
references/research.md | Mode research. |
references/sources.md | Mode research. |
references/verification.md | Mode research. |
references/worker-modes.md | Mode research. |
references/ideate.md | Mode ideate. |
Report: brief location, next stage or question.
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.