openspec-new-change
Skill85 starsChanged 6 months agoApache-2.0View on GitHub
Use this skill at Step 3 of the v2 SOP to create the OpenSpec change scaffold (proposal.md / design.md / specs/ / tasks.md) for a stage of the PRD. Initializes the change directory under openspec/changes/<slug>/, fills the proposal with PRD references, and emits a design.md skeleton including a Compliance Design section that links to COMPLIANCE_TAG.md. After this skill, use openspec-continue-change for full content expansion. Chinese trigger examples: "新建 OpenSpec change", "Step 3", "OpenSpec 初始化", "建 change", "新建变更". Do NOT use without a signed COMPLIANCE_TAG (Step 0) and a clean PRD (Step 1) and aligned TDD (Step 2). Success = change directory exists with valid skeleton, all references resolve, no orphan spec ids.
70 other projects use a version of this.
Adopted by
Most recently taken up by
- cylingo-group/claw-installertheir own version, first seen Nov 15, 2026
- haskelium/openpreztheir own version, first seen Nov 15, 2026
- trivoallan/ontracktheir own version, first seen Nov 15, 2026
- rulemason/rulemasontheir own version, first seen Nov 15, 2026
- ValorVie/custom-skillstheir own version, first seen Nov 8, 2026
- FuDesign2008/open-skillstheir own version, first seen Nov 6, 2026
Used with
Projects with it also use openspec-ff-change, openspec-bulk-archive-change and 7 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.
MicrosoftSkillopenspec-ff-change
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.
Also in 61 projects that use this
MicrosoftSkillopenspec-bulk-archive-change
Archive multiple completed changes at once. Use when archiving several parallel changes.
Also in 56 projects that use this
goernSkilldraft-openspec-docs
Collaborative page-drafting mode for the OpenSpec docs. Builds a scratch plan inside the target page (purpose, structure, numbered draft steps), iterates on it with the user, then drafts one section per approved step and cleans up after itself. Use when a page needs a from-scratch rewrite or a new page is being shaped with the user in the loop.
Also in 3 projects that use this
goernSkillrelease-openspec
Use this skill when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut a beta or stable release, verify publishing, and polish GitHub release notes. Also use when asked whether an open release PR is complete, what the next release step is, or to continue a release paused for human approval.
Also in 3 projects that use this
Microsoft AzureSkillopenspec-update-change
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.
Also in 14 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
- +1 more from microsoft
- +2 more from goern
Other versions70 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 70
- Fission-AI/OpenSpec★ 75ksame name
- alibaba/druid★ 28ksame name
- studyzy/imewlconverter★ 10ksame name
- PBH-BTN/PeerBanHelper★ 6.4ksame name
- fengshao1227/ccg-workflow★ 6ksame name
- Soju06/codex-lb★ 3.3ksame name
- Draculabo/AntigravityManager★ 2.5ksame name
- studyzy/OpenSpec-cn★ 1.3ksame name
- microsoft/rayfin★ 646same name
- mckinsey/agents-at-scale-ark★ 439same name
60 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 repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ask-questions-if-underspecifiedSkill
- audit-snapshot-microSkill
- audit-snapshotSkill
- compliance-precheckSkill
- compliance-reviewSkill
- memory-curateSkill
- mocking-stubbingSkill
- openspec-apply-changeSkill
- openspec-continue-changeSkill
- openspec-verify-changeSkill
- phi-desensitizeSkill
- prd-authorSkill
- prd-implementation-precheckSkill
- prd-precheckSkill
- prdSkill
- prompt-injection-scanSkill
- quick-fixSkill
- requesting-code-reviewSkill
- systematic-debuggingSkill
- task-decompositionSkill
- tdd-alignmentSkill
- test-data-generationSkill
The file
Files
OpenSpec New Change
The bootstrap step of an OpenSpec change. Sets up structure; content fills in the next step (openspec-continue-change).
Scaffolded structure
openspec/changes/<slug>/
├── proposal.md # 30-second readout: why + scope + stage + DoD
├── design.md # technical approach + 合规设计说明
├── specs/
│ └── index.md # spec id table; one row per shippable behavior
├── tasks.md # task list (filled by task-decomposition next)
├── COMPLIANCE_TAG.md # signed at Step 0 (link or copy)
└── MODEL_ALLOWLIST.json # active at Step 0Workflow
- Derive slug — from the PRD stage name (中文允许,URL-safe optional).
- Initialize — create directory + 4 skeleton files.
- Fill proposal — pull from PRD §1, §3, §5 (for the relevant stage).
- Fill design — leave technical body for
openspec-continue-change; must include## 合规设计说明section now (data tier, PHI flow, model allowlist summary). - Init specs — table with at least 1 placeholder row; spec ids of form
S<n>-<short>. - Init tasks — empty list;
task-decompositionfills it. - Sanity — all references resolve (PRD path, COMPLIANCE_TAG path).
Compliance Design section template
## 合规设计说明
- 数据等级: <L1/L2/L3/L4>(引用 COMPLIANCE_TAG.md §2)
- PHI 流向: <从哪到哪到哪>(如适用)
- 模型 allowlist: <coder/reviewer/architect 选型摘要,详见 MODEL_ALLOWLIST.json>
- 跨境数据: 是 / 否(如是,必须额外说明绕开方式)
- 新增 prompt 注入面: 是 / 否(如是,列出 RAG/工具/外部输入路径)Common failure modes
- Missing COMPLIANCE_TAG link — design.md 写出来后才发现忘了合规章节。修:本 skill 强制建出该 section。
- Slug over-engineering —
omni-agent-os-stage-3-orchestrator-minimal-execution-v2-redux太长。修:保持简短可识别。 - Specs without rows — index.md 留空。修:至少给 1 个占位 spec id。
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.

