plan-feature
Skill1 starsChanged 13 days agoMITView on GitHub
Run the three-phase Feature Planner validation before implementing a feature. Use when the user says plan feature, plan a new feature, I want to add, or any request for structured feature planning with edge case and risk analysis.
30 other projects use a version of this.
Adopted by
Most recently taken up by
- NemesLaszlo/claude-code-harnessword for word, first seen Nov 8, 2026
- olimstv/claude-skillstheir own version, first seen Nov 1, 2026
- aberson/skill-meshtheir own version, first seen Oct 24, 2026
- alexisselorm/claude-skillstheir own version, first seen Oct 17, 2026
- nowsprinting/unity-coding-skillstheir own version, first seen Oct 16, 2026
- asta-nguyen/kamehadbtheir own version, first seen Oct 16, 2026
Used with
Projects with it also use review-pr, systematic-debugging and 1 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.
DockerSkillreview-pr
Review one or more incoming Docker documentation pull requests as a maintainer. Independently validate technical claims, assess editorial fit and information architecture, choose a verdict, and draft exact inline or PR-wide feedback behind a confirmation gate. Use for requests such as "review PR 123", "is this PR correct?", "does this information belong here?", "validate this PR", or "help review backlog PRs". Do not use to maintain or fix a PR you own; use maintain-pr for that.
Also in 3 projects that use this
OpenAISkillsystematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Also in 3 projects that use this
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions30 projects use a version of this.
Word for word · 1
- NemesLaszlo/claude-code-harness★ 1100% same
Edited · 0
None found.
Wrote their own version · 29
- Aurealibe/claude-config★ 68same name
- smartwhale8/claude-playbook★ 40same name
- uniffy-io/uniffy★ 26same name
- nowsprinting/unity-coding-skills★ 20same name
- asta-nguyen/kamehadb★ 14same name
- Karthick-Ramachandran/persist-os★ 9same name
- MooseDesign1/DDD-DesignDrivenDevelopment★ 9same name
- mnzralee/claude-multi-agent-architecture★ 8same name
- iopsystems/skills-mcp★ 6same name
- lautioliver/barrilete-kit★ 6same name
19 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 repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- before-and-afterSkill
- code-structureSkill
- cross-reviewSkill
- evidence-driven-testingSkill
- exploreSkill
- fix-issuesSkill
- greploopSkill
- implementSkill
- investigateSkill
- new-featureSkill
- reviewSkill
- security-scanSkill
- shipSkill
- unslopSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 28 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Before planning, validate the project's documentation and specs:
- Distinctive: line 27
Completeness: All key features specced? Features in README but missing from specs?
- Distinctive: line 29
Consistency: Do specs, README, AGENTS.md and tasks tell the same story?
- Distinctive: line 63
File coverage: All files that need changes identified?
“Common” is measured: kept by at least 6 in 10 of the 28 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
Context
- Current branch: !
git branch --show-current || true - Recent changes: !
git log --oneline -5 || true - Top-level layout: !
git ls-tree --name-only HEAD || true
Your Task
You are the Feature Planner agent. Run all three validation phases for the following feature and return the consolidated plan to the caller:
Feature: $ARGUMENTS
Phase 1: Domain & Spec Validation
Before planning, validate the project's documentation and specs:
- Completeness: All key features specced? Features in README but missing from specs?
- Gaps: Missing specs, undocumented decisions, features without tasks
- Consistency: Do specs, README, AGENTS.md and tasks tell the same story? Contradictions?
- Staleness: Specs outdated relative to completed work? CHANGELOG accurate?
- Coverage: Tasks cover all specced features? Orphaned tasks?
- Clarity: Requirements precise enough to implement? Vague language?
- Data model: Entities, relationships, invariants defined? Missing fields or constraints?
- API contracts: Endpoints, payloads, error responses, status codes documented?
- Non-functional requirements: Performance targets, scalability, availability, rate limits?
Report each item as PASS / WARN / BLOCK. Stop if any BLOCK items exist.
Phase 2: Task Validation
For each task derived from the feature:
- Requirements clarity: Specific and testable? Flag vague language
- Acceptance criteria: Concrete, verifiable, can each become a test?
- Scope: Too big? Too small? Clear boundaries?
- Edge cases: Error states, empty states, concurrent access, boundary conditions, null inputs, permission denied, timeout/retry, race conditions
- Dependencies: Other tasks, services, APIs, feature flags?
- Security implications: Auth, user data, financial transactions?
- Data implications: Schema changes? Migration? Breaking changes?
- Observability: Logging, metrics, alerting needs?
- Rollback strategy: Safely revertible? Feature flag needed?
- Domain consistency: Aligns with specs and architecture?
Output a refined task definition for each task with all gaps filled.
Phase 3: Implementation Plan Validation
Build and validate the implementation plan:
- Spec-plan alignment: Addresses all requirements and acceptance criteria?
- Technical approach: Simplest that meets requirements?
- Pattern consistency: Follows existing codebase patterns? Actions orchestrate, a service layer owns reusable mechanics (
/code-structure) - File coverage: All files that need changes identified?
- Implementation order: Right order? Hidden dependencies?
- Testing strategy: Unit, integration, e2e coverage for critical paths?
- Evidence plan: What before/after proof will show it works (
/evidence-driven-testing): screenshots or recording for UI, measured numbers or output pairs otherwise - Migration strategy: DB migrations? Feature flags? Backwards compatibility?
- Risk areas: Complex integrations, performance, third-party limits?
- Verification plan: How to prove it works?
Final Output
Produce a consolidated Validated Feature Plan with:
- Validation summary (all 3 phases)
- Warnings and accepted risks
- Refined tasks in implementation order
- Full implementation plan with file changes
- Evidence plan per task
- Recommended agent assignments
- Open questions needing human decision
Refer to the Feature Planner agent for detailed output formats. End with: "Next: /new-feature if not yet isolated, then /implement."
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.

