plan
Skill2 starsChanged 6 months agoMITView on GitHub
Plan feature implementation across services and roles — parse requirements, understand project architecture (`ARCHITECTURE.md`, `AGENTS.md`), decompose into work packages per service/role, estimate complexity, produce an actionable implementation plan. Part of the umbrella feature workflow. Includes mandatory multi-reviewer feedback loop with product-manager, solution-architect, and system-architect.
184 other projects use a version of this.
Adopted by
Most recently taken up by
- event-driven-io/emmetttheir own version, first seen Nov 16, 2026
- champ18ion/claud18codetheir own version, first seen Nov 16, 2026
- FAHTHIZ/oasistheir own version, first seen Nov 16, 2026
- chuckplayer/claude-agent-packtheir own version, first seen Nov 16, 2026
- ansvisor/ansvisortheir own version, first seen Nov 15, 2026
- timmo001/skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use context-optimize, heartmula and 10 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.
SireJeffSkillcontext-optimize
Context Optimization - Orchestrate RPI workflow TODO generation with interactive scoping
Also in 4 projects that use this
math-incSkillheartmula
Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.
Also in 9 projects that use this
Tommy-ywSkillwebhook-subscriptions
Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.
Also in 5 projects that use this
math-incSkillminecraft-modpack-server
Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.
Also in 5 projects that use this
john-data-chenSkilltouchdesigner-mcp
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
Also in 6 projects that use this
gaebalaiSkillcodex-system
PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".
Also in 3 projects that use this
- +3 more from math-inc
Other versions184 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 184
- Yeachan-Heo/oh-my-codex★ 34ksame name
- crbnos/carbon★ 2.8ksame name
- graphistry/pygraphistry★ 2.6ksame name
- zereight/gitlab-mcp★ 2.1ksame name
- math-inc/OpenGauss★ 1.3ksame name
- kdlbs/kandev★ 1.1ksame name
- suboss87/FDEOps★ 940same name
- codewithmukesh/dotnet-claude-kit★ 808same name
- witnesstodark/mr-mak-workspace★ 800same name
- loongclaw-ai/loongclaw★ 640same name
174 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 repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-skillsSkill
- analyze-localSkill
- analyze-prodSkill
- analyzeSkill
- architectureSkill
- asset-validationSkill
- blog-postSkill
- bugfixSkill
- cloud-platformsSkill
- code-reviewSkill
- content-creationSkill
- context-engineeringSkill
- create-prSkill
- deployment-proceduresSkill
- deploy-productionSkill
- deploy-stagingSkill
- docsSkill
- feature-devSkill
- geo-writerSkill
- humanizerSkill
- infra-changeSkill
- marketing-operationsSkill
- marketingSkill
- ml-pipelineSkill
- pre-commitSkill
- productSkill
- project-initSkill
- prompt-engineeringSkill
- qaSkill
- releaseSkill
- run-testsSkill
- security-scanSkill
- seo-reviewSkill
- social-media-managerSkill
- test-localSkill
- test-strategySkill
- ui-ux-designSkill
- worktree-isolationSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 10 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 168 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Read every provided document thoroughly
- Distinctive: line 41
If the specification is ambiguous or incomplete — ask before proceeding.
- Distinctive: line 45
Read and internalize the project's structure to plan correctly:
- Distinctive: line 49
Read the following files (if they exist):
- Distinctive: line 64
If documentation is incomplete or absent, scan the filesystem:
- Distinctive: line 79
Create a map of services/modules the feature touches:
- Distinctive: line 114
Only include work streams that the feature actually requires.
- Distinctive: line 223
Wait for user approval. The user may reorder, split, merge, or remove work packages.
- Very specific: line 251
After the plan is approved, apply product-manager role and update FEATURES.md:
- Very specific: line 253
If FEATURES.md does not exist — create it at the project root
- Very specific: line 254
Add or update the feature entry with status planned
- Very specific: line 255
If the feature has a PRD or spec — save it in features/ directory and link from FEATURES.md
- Distinctive: line 259
After approval, guide execution:
- Distinctive: line 264
Update the plan if scope changes during implementation
“Common” is measured: kept by at least 6 in 10 of the 168 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
Feature Plan
Plan a feature implementation by understanding the project architecture, decomposing work into service-level and role-level packages, and producing an actionable plan. This is the planning phase — no code is written here. Output feeds into feature-dev skill for execution.
1. Receive Feature Requirements
Gather the feature specification from the user:
- Accepted formats: PRD, ARD, design doc, implementation plan, ticket/issue, verbal description
- Read every provided document thoroughly
- Extract and organize:
- Goal: What the feature does (1–2 sentences)
- Requirements: Functional (what it does) and non-functional (performance, security, compliance)
- Acceptance criteria: How to verify the feature works
- Constraints: Deadlines, compatibility, dependencies on other teams/services
- Out of scope: What this feature explicitly does NOT cover
If the specification is ambiguous or incomplete — ask before proceeding. Do not assume missing requirements.
2. Understand Project Architecture
Read and internalize the project's structure to plan correctly:
2a. Read Architecture Documentation
Read the following files (if they exist):
ARCHITECTURE.md— system overview, component boundaries, data flow, service mapAGENTS.md(root) — tech stack declaration, project structure, conventions- Subdirectory
AGENTS.mdfiles — per-service/module context and stack info
Extract:
- Service/module boundaries (monolith modules, microservices, frontend/backend split)
- Tech stack per service (language, framework, database, messaging)
- Communication patterns (REST, gRPC, events, shared DB)
- Data flow relevant to the feature
- Deployment topology (monorepo vs polyrepo, shared vs independent deploys)
2b. Scan Project Structure
If documentation is incomplete or absent, scan the filesystem:
// turbo
ls -la (or dir for Windows)Look for:
- Monorepo signals:
packages/,services/,apps/, rootpackage.jsonwith workspaces, Nx/Turborepo config - Polyrepo signals: Single service, one
AGENTS.md, one tech stack - Infrastructure:
terraform/,infra/,k8s/,helm/,docker-compose.yml - Dependency files:
package.json,pom.xml,requirements.txt,go.mod,*.csprojper service
2c. Build Service Map
Create a map of services/modules the feature touches:
## Service Map
| Service/Module | Tech Stack | Role | Affected by Feature |
|---|---|---|---|
| [name] | [lang + framework] | `role-id` | [yes/no — how] |
| [name] | [lang + framework] | `role-id` | [yes/no — how] |
| infrastructure | Terraform / K8s | `devops-engineer` role | [yes/no — how] |3. Decompose into Work Packages
Break the feature into work packages — each package is a self-contained unit of work scoped to one service/module and one role.
3a. Identify Work Streams
Group changes by responsibility:
| Work Stream | Role | Scope |
| Frontend | frontend-engineer role | UI components, pages, client-side logic, API integration |
| Backend API | java-engineer role / python-engineer role | Endpoints, business logic, data access, validation |
| Data Layer | db-engineer role | Database schema, migrations, queries, indexing, optimization |
| Infrastructure | devops-engineer role | Terraform, Docker, K8s, config, secrets |
| Cloud Architecture | cloud-architect role | Cloud platform design, landing zones, networking, cost optimization |
| CI/CD Architecture | devops-architect role | Pipeline design, deployment strategy, GitHub org governance, platform engineering |
| ML / Data | ml-engineer role | Models, pipelines, feature engineering. For LLM/RAG/agent features also consult context-engineering skill |
| Data Pipelines | data-engineer role | ETL/ELT, data warehousing, Spark, dbt, Airflow |
| Mobile | mobile-engineer role | React Native, Flutter, iOS, Android apps |
| Marketing Content | marketing-strategist role | Positioning, messaging, GTM, landing pages |
| Architecture | system-architect role | System design, ARCHITECTURE.md, component boundaries, tech selection |
| Cross-cutting | software-engineer role | Shared libraries, contracts, API specs |
Only include work streams that the feature actually requires. Do not add empty streams.
3b. Define Work Packages
For each work stream, create ordered work packages:
### [Work Stream]: [Service Name] — `role-id`
#### WP-[N]: [Title]
- **Description**: What to implement
- **Files**: Expected files to create/modify
- **Dependencies**: Which WPs must complete first
- **Acceptance criteria**: How to verify this WP is done
- **Complexity**: S (hours) / M (day) / L (days) / XL (week+)Rules for decomposition:
- Each WP is independently testable
- WPs within a stream are ordered by dependency (foundations first)
- Cross-service dependencies are explicitly marked
- Database migrations always come before code that uses them
- API contracts defined before consumer implementation
3c. Define Integration Points
For features spanning multiple services, explicitly document:
<integration_points>
- API contracts: Request/response schemas for new or modified endpoints
- Events/messages: New event types, payload schemas, producers, consumers
- Shared types: DTOs, enums, or constants shared across services
- Database changes: Schema migrations, new tables/columns, index requirements
- Configuration: New env vars, feature flags, secrets needed </integration_points>
4. Dependency Graph
Visualize the execution order:
## Dependency Graph
WP-1: [DB migration]
└─► WP-2: [Backend API]
├─► WP-3: [Frontend integration]
└─► WP-4: [Infrastructure/config]
WP-5: [Tests] ← depends on WP-2, WP-3Identify:
- Critical path: Longest chain of dependent WPs — determines minimum timeline
- Parallelizable: WPs that can be worked on simultaneously by different roles
- Blockers: External dependencies (other teams, third-party APIs, approvals)
5. Risk Assessment
Evaluate risks for each work stream:
| Risk | Impact | Likelihood | Mitigation |
| [risk description] | High/Med/Low | High/Med/Low | [mitigation strategy] |
Common risks to evaluate:
- Breaking changes to existing APIs (backward compatibility)
- Database migration on large tables (performance, downtime)
- Cross-service coordination (deployment order matters)
- New dependencies or services (operational complexity)
- Security implications (new auth flows, data exposure)
6. Present the Plan
Compile the full plan and present to the user:
# Feature Plan: [Feature Name]
## Goal
[1–2 sentences]
## Architecture Impact
- Services affected: [list]
- New services: [if any]
- Database changes: [yes/no — summary]
- Infrastructure changes: [yes/no — summary]
## Work Packages
### Stream 1: [name] — `role-id`
| WP | Title | Complexity | Dependencies | Status |
|----|-------|------------|--------------|--------|
| WP-1 | [title] | M | — | planned |
| WP-2 | [title] | S | WP-1 | planned |
### Stream 2: [name] — `role-id`
| WP | Title | Complexity | Dependencies | Status |
|----|-------|------------|--------------|--------|
| WP-3 | [title] | L | WP-1 | planned |
## Critical Path
WP-1 → WP-2 → WP-5 (estimated: [timeframe])
## Risks
[table from Step 5]
## Next Step
Run `feature-dev` skill per work package, applying the designated role.Wait for user approval. The user may reorder, split, merge, or remove work packages.
7. Multi-Reviewer Feedback Loop
The Feature Plan MUST pass a mandatory multi-reviewer cycle before handoff. Do not update FEATURES.md or hand off to the feature-dev skill until every reviewer returns approved.
Reviewer Panel
Apply each role below in sequence, treating each as an independent reviewer with its own pass over the plan:
product-managerrole — scope alignment with the PRD, WP coverage of acceptance criteria, risk coverage, correct prioritization, missing requirementssolution-architectrole — end-to-end design coherence, integration points, API contracts, cross-service coordination, tech stack fit per WP, non-functional requirements coveragesystem-architectrole — system boundaries, component topology, data flow,ARCHITECTURE.mdconsistency, scalability and deployment implications of the WP decomposition
Cycle
- For each role, produce a findings report: Critical (must fix), Major (should fix, justify if waived), Minor (optional), plus an explicit verdict:
approved/approved-with-changes/rejected. Keep reports separate per role - Collect all three reports before editing
- Apply all actionable findings to the plan (re-scope WPs, adjust dependencies, add missing streams, revise complexity). Resolve conflicts with priority Critical > Major > Minor; on ties, system-architect > solution-architect > product-manager. Record waivers with a one-line rationale
- Re-run the same three reviewer passes against the updated plan
- Loop until every reviewer returns
approvedwith zero remaining critical/major findings
Termination: pass when all three are approved. On divergence (findings not shrinking, mutually exclusive asks) — pause and ask the user to arbitrate. Max 5 cycles before escalation.
Record the review history at the bottom of the plan as a ## Review History section listing each cycle's reviewer verdicts and open issue counts.
8. Update FEATURES.md
After the plan is approved, apply product-manager role and update FEATURES.md:
- If
FEATURES.mddoes not exist — create it at the project root - Add or update the feature entry with status
planned - If the feature has a PRD or spec — save it in
features/directory and link fromFEATURES.md
9. Handoff to Implementation
After approval, guide execution:
- Sequential (single developer): Execute WPs in dependency order using
feature-devskill for each - Parallel (multiple developers/sessions): Assign independent WPs to separate sessions, each applying the appropriate role
- Track WP status:
planned→in_progress→done - Update the plan if scope changes during implementation
Integration
- Input: PRD, ARD, design doc, or user request
- Preceded by:
productskill (produces PRD),architectureskill (produces ARD, design docs, API contracts, engineering estimates) - Followed by:
feature-devskill (implementation per work package) - Roles:
product-managerrole (requirements; Step 7 reviewer),solution-architectrole +system-architectrole (architecture; Step 7 reviewers),cloud-architectrole (cloud platform),devops-architectrole (CI/CD architecture), stack-specific roles (work packages) - Skills:
context-engineeringskill (context pipeline design, RAG, memory, agent harness — for AI/LLM feature work packages)
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.

