to-spec
Converts a feature PRD, plan, BMad architecture/epics/stories output, or conversation context into `docs/features/<feature>/SPEC.md` with functional behavior…
Skill by pop1414
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/pop1414-to-spec
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, backend, data, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/to-spec
What's inside
- Skill name
to-spec- Description
- Converts a feature PRD, plan, BMad architecture/epics/stories output, or conversation context into `docs/features/<feature>/SPEC.md` with functional behavior, technical contracts, edge cases, and executable verification commands. Use when user wants to write a spec, turn PRD into implementation-ready requirements, promote BMad technical findings into the formal AI-native document system, define API/data/state behavior, or prepare input for `to-issues`.
- License
- MIT
- Instructions
- 95 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# To Spec 把 PRD、Plan 或 conversation context 转成 AI 可执行的功能和技术规格。输出默认写入 `docs/features/<feature>/SPEC.md`。 ## Workflow 1. **Load repo workflow** - Read the repo's actual agent adapter if present, such as `AGENTS.md`, `CLAUDE.md`, `.cursor/rules/`, or `.github/copilot-instructions.md` - Read `docs/agents/document-system.md` and `docs/agents/domain.md` if they exist - Read `CONTEXT.md` and relevant `docs/adr/` - If source material comes from BMad or `_bmad-output/`, read `docs/BMAD_INTEGRATION.md` and `docs/LEVEL3_BMAD_WORKFLOW.md` 2. **Find source material** - Prefer `docs/features/<feature>/PRD.md` - Also read `docs/features/<feature>/PLAN.md` if present - If BMad was used, read relevant BMad PRD, architecture, epics/stories, readiness, review, or story files as source material - If no PRD exists, use conversation context and mark assumptions explicitly 3. **Explore code only as needed** - Inspect existing API, models, tests, and module boundaries related to the feature - Use project vocabulary from `CONTEXT.md` - Respect ADR constraints; flag conflicts instead of silently overriding them 4. **Draft the Spec** - Describe external behavior, not internal implementation steps - Include functional scenarios, state transitions, business rules, error scenarios, data model, API contract, validation rules, and verification commands - Do not invent product scope that is absent from the PRD; put uncertain scope under `Open Questions` - Promote only stable BMad conclusions into `SPEC.md`; BMad task ordering, story execution notes, and transient review notes stay in `_bmad-output/` or control issues - If BMad output conflicts with existing `docs/`, stop and surface the conflict; update `docs/` only after the chosen conclusion is clear 5. **Write or update** - Create `docs/features/<feature>/SPEC.md` - If updating an existing Spec, preserve still-valid content and change only affected sections - Ensure `Parent PRD` points to `docs/features/<feature>/PRD.md` 6. **Finish with next step** - If sequencing is still unclear or the work spans phases/features, suggest `/to-plan` - If the Spec is implementation-ready and AI-native issues own execution, suggest `/to-issues` - If BMad story cycle owns execution, suggest `bmad-sprint-planning`; use `/to-issues` only for blocker, HITL, risk, debt, review follow-up, or documentation-fix control issues - If terminology is unresolved, suggest `/grill-with-docs` - If a durable technical trade-off appears, suggest an ADR ## Required Spec Shape ```markdown # Spec: <Feature Name> > Parent PRD: docs/features/<feature>/PRD.md > Related ADR: <links or None> ## Overview ## Functional Specification ### User Scenarios ### State Transitions ### Business Rules ### Error Scenarios ## Technical Specification ### Data Model ### API Contract ### Validation Rules ## Verification ### Automated Verification Commands | Command | Expected Result | Failure Handling | | ------- | --------------- | ---------------- | | `<build>` | <expected> | <what to fix> | | `<test>` | <expected> | <what to fix> | ### Manual QA Steps ### Known Non-Testable Acceptance Criteria ## Open Questions ``` ## Quality Bar - Every user-visible behavior in the PRD has a corresponding Spec rule or scenario. - Every API/data/state rule has an observable reason from PRD, Context, or ADR. - Verification commands are concrete commands an agent can run. - Spec does not mention exact source file paths unless they are part of a public contract. - Ambiguity is explicit; do not hide unknowns in vague wording.
From pop1414/ai-native-doc-system, MIT.
More from pop1414/ai-native-doc-system
- 0.479score
git-guardrails-claude-code
pop1414
设置 Claude Code hooks,在危险 git commands(push, reset --hard, clean, branch -D 等)执行前阻止它们。Use when user wants to prevent destructive git operations, add git safety…
SkillCFreshness: CClaude Code +9 - 0.479score
diagnose
pop1414
面向棘手 bug、性能回退和 BMad story execution failures 的纪律化 diagnosis loop。Reproduce → minimise → hypothesise → instrument → fix → regression-test.
SkillCFreshness: CClaude Code +9 - 0.474score
caveman
pop1414
超压缩 communication mode。Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.
SkillCFreshness: CClaude Code +9 - 0.474score
to-issues
pop1414
将正式文档或 BMad 执行发现转成本地 issues。Use when user wants to convert a spec or plan into implementation issues, or create BMad control-panel issues for blockers, HITL…
SkillCFreshness: CClaude Code +9 - 0.474score
to-plan
pop1414
Converts a feature PRD, spec, BMad epics/stories, release goal, or conversation context into an execution plan at `docs/plans/<plan>.md` or…
SkillCFreshness: CClaude Code +9 - 0.474score
to-prd
pop1414
将当前 conversation context 或 BMad PRD 输出转成 `docs/features/<feature>/PRD.md`,并接入 AI-native 文档链。Use when user wants to create a PRD, write product requirements…
SkillCFreshness: CClaude Code +9 - 0.474score
write-a-skill
pop1414
创建结构正确、支持 progressive disclosure 并带 bundled resources 的新 agent skills。Use when user wants to create, write, or build a new skill.
SkillCFreshness: CClaude Code +9 - 0.474score
grill-with-docs
pop1414
Grilling session that challenges a plan against the existing domain model, feature docs, and documented decisions, then updates CONTEXT.md and ADRs as…
SkillCFreshness: CClaude Code +9 - 0.474score
improve-codebase-architecture
pop1414
根据 CONTEXT.md 中的 domain language 和 docs/adr/ 中的 decisions,寻找 codebase 的 deepening opportunities。Use when the user wants to improve architecture, find…
SkillCFreshness: CClaude Code +9 - 0.474score
migrate-to-shoehorn
pop1414
将 test files 从 `as` type assertions 迁移到 @total-typescript/shoehorn。Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
SkillCFreshness: CClaude Code +9 - 0.474score
scaffold-exercises
pop1414
创建包含 sections、problems、solutions 和 explainers 的 exercise directory structures,并确保通过 linting。Use when user wants to scaffold exercises, create exercise stubs…
SkillCFreshness: CClaude Code +9 - 0.474score
setup-ai-document-system
pop1414
Sets up repo-local adapters and `docs/agents/` configuration so engineering skills share one issue tracker, triage vocabulary, domain layout, AI-native…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 3, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/pop1414/ai-native-doc-system
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from pop1414
- 0.479score
git-guardrails-claude-code
pop1414
设置 Claude Code hooks,在危险 git commands(push, reset --hard, clean, branch -D 等)执行前阻止它们。Use when user wants to prevent destructive git operations, add git safety…
SkillCFreshness: CClaude Code +9 - 0.479score
diagnose
pop1414
面向棘手 bug、性能回退和 BMad story execution failures 的纪律化 diagnosis loop。Reproduce → minimise → hypothesise → instrument → fix → regression-test.
SkillCFreshness: CClaude Code +9 - 0.474score
improve-codebase-architecture
pop1414
根据 CONTEXT.md 中的 domain language 和 docs/adr/ 中的 decisions,寻找 codebase 的 deepening opportunities。Use when the user wants to improve architecture, find…
SkillCFreshness: CClaude Code +9 - 0.474score
grill-with-docs
pop1414
Grilling session that challenges a plan against the existing domain model, feature docs, and documented decisions, then updates CONTEXT.md and ADRs as…
SkillCFreshness: CClaude Code +9 - 0.474score
caveman
pop1414
超压缩 communication mode。Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.
SkillCFreshness: CClaude Code +9 - 0.474score
migrate-to-shoehorn
pop1414
将 test files 从 `as` type assertions 迁移到 @total-typescript/shoehorn。Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
SkillCFreshness: CClaude Code +9
Cite this page
to-spec skill. Agent Mart. https://agentmart.dev/skills/pop1414-to-spec (last updated 2026-10-24)