agentleFS
Sign inStart free
thoitiettxl-cyberthoitiettxl-cyber/Claw-II/skills/feature-dev/SKILL.md

feature-dev

Skill2 starsChanged 7 months agoMITView on GitHub

Feature development workflow for OpenClaw Android follows a phase-gated flow: discovery → clarification → design → implementation → review.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use code-review.

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.
  • GoogleSkill

    code-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 6 projects that use this

The file

Create a free account to mount
Files
SKILL.md

feature-dev

Indexed Reference Map

  • @[SKILL.md#L1-L63] Frontmatter + phase workflow
  • @[references/INDEX.md#L1-L12] Reading order
  • @[references/QUICK_REFERENCE.md#L1-L13] Phase gate quick map
  • @[references/CORE_API.md#L1-L27] Input/output and decision checkpoints
  • @[references/PATTERNS.md#L1-L14] Patterns implements feature
  • @[references/EXAMPLES.md#L1-L7] Example flows
  • @[references/AI_WORKFLOW.md#L1-L7] End-to-end AI execution

Scope

  • In-scope:
    • Feature development has many unknowns/edge cases.
    • Need design options + decision checkpoint before implementation.
    • Need quality gate before reporting done.
  • Out-of-scope:
    • Simple one-liner fix without the need for a full workflow.
    • Deploy/cutover external without approval.

Reading Order

  1. references/QUICK_REFERENCE.md
  2. references/CORE_API.md
  3. references/PATTERNS.md
  4. references/EXAMPLES.md
  5. references/AI_WORKFLOW.md

Coverage Matrix

  • Discovery/spec clarification: yes
  • Architecture options + trade-off: yes
  • Implementation execution: yes
  • QA review + summary: yes
  • External rollout: gated by approval

Trigger Rules

  • Positive: Used when the user requests a new feature or a refactor with a large scope.
  • Negative: Not used for very small patches, read-only operations.
  • Escalation: Any external write/deploy action requires checkpoint approval.

SOP

  1. Discovery: determine goals, constraints, acceptance criteria.
  2. Clarify: lists ambiguity/edge-cases and closes assumptions.
  3. Design: create 2-3 options + recommendation.
  4. Implement: execute the approved option.
  5. Review: run quality gate + next steps.

Error Handling

  • Requirement is vague: stop implementation, ask for clarification.
  • Scope explodes: dividing into phases, prioritizing MVP.
  • Missing dependency/tool: report blocker + workaround.

Output Contract

  • Artifact: implementation log theo phase + file touch list.
  • Validation: each phase has done-when measurable.
  • Compliance Verdict: PASS when phase gates and quality gates are both met.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free