create-spec
Skill170 starsChanged 52 days agoMITView on GitHub
Turn the design into a build-ready spec a fresh context can implement and verify. Use when the user asks to create a spec.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- holgerleichsenring/specification-first-agentic-developmenttheir own version, first seen Oct 13, 2026
- sanzhardanybayev/synergytheir own version, first seen Oct 13, 2026
- gittower/git-flow-nexttheir own version, first seen Oct 8, 2026
- leonvanzyl/agentic-coding-starter-kittheir own version, first seen Oct 8, 2026
- braincandy-parallel/tamarindos-workflow-kittheir own version, first seen Sep 18, 2026
- madalinpopa/skillstheir own version, first seen Sep 14, 2026
Used with
Projects with it also use review-spec, create-plan and 5 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.
dekozaSkillreview-spec
Use when a diff must be reviewed against the spec, ticket, or issue that originated it — missing requirements, scope creep, and requirements implemented wrongly — producing cited findings and nothing else. One axis of a two-axis review, independently invocable. Triggers on: "spec review", "does this match the ticket", "review the PR against the spec", "did we build what was asked", "spec axis". Does not judge code style — that is review-standards.
Also in 3 projects that use this
JetBrainsSkillcreate-plan
Research the codebase and create an implementation plan with architecture notes, design document, and track decomposition. Use when starting a new feature or large change.
Also in 3 projects that use this
MicrosoftSkillpr-review
Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode. Use when reviewing a docs PR for factual correctness: setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.
Also in 3 projects that use this
VercelSkillvercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Also in 3 projects that use this
BlockSkillfrontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Also in 4 projects that use this
- MicrosoftSkill
handoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- gittower/git-flow-next★ 458same name
- leonvanzyl/agentic-coding-starter-kit★ 447same name
- holgerleichsenring/specification-first-agentic-development★ 41same name
- dominicletz/elixir-skills★ 34same name
- leonvanzyl/claude-code-pro-workflow-demo★ 4same name
- NitinJ/specforge★ 4same name
- ReStartAllKill/skills★ 2same name
- sanzhardanybayev/synergy★ 2same name
- sikbrad/spark-harness-template★ 2same name
- araujoleonardo/skills★ 1same name
7 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 repository3 other files it gives its agents.
- implementSkill
- kick-offSkill
- setup-kikoSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
3
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 11
Run scripts/check-kiko with the opened project root's absolute path as its only argument, and use the returned path as KIKO_ROOT.
- Very specific: line 18
Do not initialize or repair .kiko.
- Very specific: line 53
Run the self-review and fix every failure.
- Distinctive: line 64
Treat a revision like the first draft: classify, gate, and self-review what changed, then ask again.
- Distinctive: line 69
Do not commit until the user explicitly confirms the current file.
- Distinctive: line 72
If the spec directory is in a Git working tree, commit it and report the commit SHA.
“Common” is measured: kept by at least 6 in 10 of the 14 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
create-spec turns the design into a build-ready spec — the delivery
contract a fresh context can implement and verify.
1. Locate the spec directory
Run scripts/check-kiko with the opened project root's absolute path as its
only argument, and use the returned path as KIKO_ROOT.
- Exit 3: ask the user to run the
setup-kikoskill at the project root, then retry. - Any other nonzero exit: report the error and stop.
Do not initialize or repair .kiko.
SPEC_DIR is the spec directory named when this skill was invoked, directly
under $KIKO_ROOT/docs; ask for it when none was named. It holds
decisions.md, the decisions made so far toward the outcome, and facts.md,
per the facts file. The spec goes to
$SPEC_DIR/spec.md; if it already exists, report that and stop.
2. Classify the design
decisions.md holds one entry per decision:
- DECISION<n> [user] <question, with the options as put>
<what the user chose or said>DECISION1 is the outcome and becomes the Goal. [user] marks the user as
the decider. IDs increase and are never reused; a changed decision is a new
entry that says which ID it supersedes. An entry holds what was put to the
user and what they chose or said, nothing written for them. A decision the
user makes while create-spec runs, whether answering a returned issue or
revising the draft, is appended the same way before it is used, worded so
that question and answer have one reading without the conversation.
Apply the spec rules to each entry. Run each empirical premise through the evidence gate in the spec rules before using it.
3. Draft and preflight
Assemble, without writing either file, the complete draft per the template and the facts to append per the facts file.
Run the self-review and fix every failure. Write
the draft to $SPEC_DIR/spec.md and append the facts to $SPEC_DIR/facts.md
only after this preflight passes.
4. Review with the user
Present the written file as the exact review target, list every D or state that there are none, show the decisions entries appended since this skill started, name the entries the delivery boundary left to the user's release, and ask the user to confirm or revise the document.
Treat a revision like the first draft: classify, gate, and self-review what changed, then ask again.
5. Commit the confirmed version
Do not commit until the user explicitly confirms the current file. Any later semantic change requires another confirmation.
If the spec directory is in a Git working tree, commit it and report the commit SHA; otherwise warn the user that nothing marks the spec as confirmed.
Recommend starting /implement $SPEC_DIR in a new window or after
/compact, so that implement starts from the files rather than this
conversation.
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.