iic2143/setup-guides/speckit-plan
Claude Code and agent skill by iic2143/setup-guides
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Create a concise implementation plan from the current feature spec.
Install
npx vskill@latest install iic2143/setup-guides/speckit-planSKILL.md
User Input
Goal
Create one plan.md with the technical approach, files, tasks, validation, risks, and out-of-scope. Do not create research.md, data-model.md, quickstart.md, contracts/, or tasks.md.
Workflow
- Read
.specify/feature.jsonto find the active feature directory. - Read
spec.mdfrom that directory. - If
spec.mdhas unresolved[NEEDS CLARIFICATION: ...]markers, ask the user to resolve them before planning. - Read
AGENTS.md,README.md, and only the repo files needed to understand the change. - Identify implementation gaps after reading the repo.
- If a gap changes architecture, data model, security, validation, or file scope, ask the user up to 3 concise questions before writing the plan.
- If a gap has a safe default, document it under
RiesgosorFuera de alcanceinstead of asking. - Copy the active Spec Kit template resolved from
.specify/templates/overrides/plan-template.mdintoplan.md. - Fill the plan with:
- Summary
- Repo reading notes
- Exact files likely to change
- Small implementation steps
- Embedded task checklist
- Validation commands or manual checks
- Risks and out-of-scope
- Keep implementation tasks small enough to review in one PR.
Quality Bar
- The plan is implementation-oriented and grounded in current repo files.
- Every task mentions a concrete file or behavior.
- Validation is runnable or manually checkable.
- Critical implementation gaps were asked or documented.
- No extra Spec Kit artifacts are generated.
Done When
specs/YYYYMMDD-HHMMSS-short-name/plan.mdexists.- The plan has a task checklist and validation section.
- Report the plan path and recommended next action.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingresources/speckit/skills/speckit-plan/SKILL.md
Popularity
- Repository stars
- 56
- Repository forks
- 14
- 7-day trend score
- 20
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/iic2143/setup-guides/speckit-plan)