spec
Skill2 starsChanged 11 days agoMITView on GitHub
Turn an idea into a spec with an interview, and cut it into tickets that each build in one session. Works in any repo.
171 other projects use a version of this.
Adopted by
Most recently taken up by
- timursafiullin/aodtheir own version, first seen Nov 15, 2026
- RohiRIK/skillstheir own version, first seen Nov 15, 2026
- Soe-Reh/soes-skillstheir own version, first seen Nov 15, 2026
- NomadicDaddy/aiddtheir own version, first seen Nov 15, 2026
- felipefontoura/claude-sdd-kittheir own version, first seen Nov 15, 2026
- thistleknot/skillstheir 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-811Skillios-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 versions171 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 171
- garrytan/gstack★ 142ksame name
- getsentry/sentry-react-native★ 1.8ksame name
- JuliusBrussee/cavekit★ 1.1ksame name
- kdlbs/kandev★ 1.1ksame name
- getsentry/sentry-dart★ 877same name
- poshan0126/dotclaude★ 871same name
- codewithmukesh/dotnet-claude-kit★ 808same name
- SparkDevNetwork/Rock★ 701same name
- strands-agents/box★ 547same name
- hyperlink-academy/leaflet★ 527same name
161 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 repository22 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 148 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read the ## Agent skills block in AGENTS.md, then docs/agents/tracker.md and docs/agents/domain.md.
- Distinctive: line 16
Read the idea from the argument, or from the issue that it names.
- Very specific: line 22
Call the Skill tool with interview.
- Very specific: line 37
Write the spec from the log with SPEC-TEMPLATE.md.
- Distinctive: line 57
Ask with the question tool: "Approve" or "Change".
“Common” is measured: kept by at least 6 in 10 of the 148 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
Spec
/spec is the start of a feature. It ends with a spec that a team can read, cut into tickets that /build takes one at a time. It makes no branch, no worktree and no commit.
1. Load
Read the ## Agent skills block in AGENTS.md, then docs/agents/tracker.md and docs/agents/domain.md. When the block is missing, read NO-SETUP.md in the folder of the setup-skills skill, and go on with its sources.
Read the idea from the argument, or from the issue that it names. Then read the area of the code that the idea touches, the glossary and the ADRs for that area.
Completion: you can describe in a few lines how the area works today.
2. Interview
Call the Skill tool with interview. The design tree for a spec always contains these decisions:
- The problem, and the user who has it.
- What each user can do and check. You write the user stories from these answers.
- What is out of scope.
- The test seams. Propose the highest existing seam.
- The schema changes: each migration, or none.
- The look of each new or changed screen, when the spec touches a screen: "prototype it, or keep it plain?" On prototype, call the Skill tool with
prototype, and record the chosen variant with its link.
During the interview, say at once when a word conflicts with the glossary, propose one exact term for a vague word, and show each place where the user's account differs from the code.
Completion: the interview returned the decisions log, with each decision above settled.
3. Draft
Write the spec from the log with SPEC-TEMPLATE.md. Its Domain changes section takes the terms and ADR candidates of the log, and nothing else.
Cut the spec into tickets with TICKETS.md. Estimate the lines for each story, with its tests and fixtures, then multiply the sum by 1.5, because a 1900 line estimate shipped 3024 lines.
This is the one approval. Write this list in your message, before the question, because the question tool does not show it:
You approve:
- Problem: <who has it, and what it costs them>
- Scope: <what the feature does>
- Out of scope: <each item>
- Seams: <each seam>
- Schema: <each migration, or none>
- Look: <the chosen variant with its link, or plain>
- Domain: <each new term and ADR, or none>
- Size: about <lines> changed lines
- Tickets:
1. <title> · <what it delivers> · blocked by: <refs, or none>Ask with the question tool: "Approve" or "Change". On Change, apply the edits, show the list again and ask again. A term or a decision that is not in the log goes to the user before you publish.
Completion: the list is in the chat above the question, and the user approved.
4. Publish
With a tracker, call the Skill tool with issue, with one list: the spec with the spec label, then each ticket with the spec as its parent, and its blockers by ref.
With no tracker, write the spec and its ## Tickets section to .scratch/spec/<slug>.md, and add .scratch/ to .git/info/exclude when git does not already ignore it. Outside a git repo, print them in the chat.
Then delete the decisions log file. The spec is now the record.
Completion: the spec and each ticket exist, and the log file is gone.
Report
Spec URL or file path · each ticket with its number and blockers · next step: /build <n> for each ticket with no blocker.
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.

