FE

feature-workflow

Forces a discovery-first workflow for feature development to maintain system consistency.

Install

mkdir -p .claude/skills/feature-workflow && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14536" && unzip -o skill.zip -d .claude/skills/feature-workflow && rm skill.zip

Installs to .claude/skills/feature-workflow

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use PROACTIVELY for non-trivial features, bug fixes, behavior changes, or refactors so work starts with discovery, readiness refactoring, approved-pattern selection, and verification planning before implementation.
214 charsno explicit “when” trigger
Intermediate

Key capabilities

  • →Read core rules and path-specific rules
  • →Inspect current implementation details
  • →Identify approved local patterns
  • →Perform readiness refactoring
  • →Plan verification for behavior changes
  • →Plan build verification for toolchain confidence

How it works

The skill guides the user through reading relevant documentation, inspecting existing code, identifying approved patterns, and planning necessary refactoring and verification steps before implementing changes.

Inputs & outputs

You give it
A non-trivial product or code change task
You get back
A plan for implementation including pattern identification and verification

When to use feature-workflow

  • →Implementing non-trivial features
  • →Planning refactors to avoid drift
  • →Setting up verification for behavior changes

About this skill

Feature Workflow

Goal

Deliver non-trivial product or code changes without introducing pattern drift, duplicated behavior, or local patches that make the surrounding system worse.

Required flow

  1. Load applicable path rules and pattern-governance-reference before writing.
  2. Use task-files:task-files to create or update the task file required for planned or complex work.
  3. Define the observable outcome and the checks that will prove it.
  4. Inspect the current implementation before planning edits:
    • upstream callers and entry points
    • downstream implementations and consumers
    • lateral files that solve the same concern
    • nearest tests or task files
  5. Identify the approved local pattern for the touched concern.
  6. Assume the area may not be ready for the requested change. If readiness refactoring is needed, do that first and keep it tied to the requested outcome.
  7. If no approved pattern exists, stop and propose the new standard before implementing it broadly.
  8. If the task is Apple-platform implementation work, use implement-apple-change.
  9. If the task changes behavior, use test-changes to add or update coverage and run the smallest meaningful verification before handoff.
  10. If the task needs compile or toolchain confidence, plan the smallest meaningful build-verify check before handoff.
  11. Delegate broad discovery to codebase-explorer; use pattern-compliance-reviewer for a second read-only pass when the change is architectural or cross-cutting.
  12. Record the approved pattern in the task file alongside the plan and verification.

Stop and ask before

  • introducing a new dependency
  • introducing a new architectural pattern, service layer, helper family, file layout, or naming convention
  • preserving accidental compatibility that conflicts with a cleaner current design
  • deleting or rewriting broad areas where user intent is ambiguous
  • using external systems when code, tests, configuration, and local evidence can answer the question

Do not

  • Do not patch the nearest file before checking for the established pattern.
  • Do not keep duplicate old and new implementations unless the task explicitly requires a temporary migration.
  • Do not add hidden fallbacks, default values, or sentinel behavior for data that should be present.
  • Do not claim completion without exact command evidence.

When not to use it

  • →When introducing a new dependency without prior approval
  • →When introducing a new architectural pattern without prior approval
  • →When deleting or rewriting broad areas with ambiguous user intent

Limitations

  • →Requires reading existing documentation and code
  • →Does not permit introducing new patterns without prior approval
  • →Does not allow claiming completion without exact command evidence

How it compares

This skill enforces a structured, discovery-first approach to code changes, preventing pattern drift and unverified implementations, unlike directly implementing changes.

Compared to similar skills

feature-workflow side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
feature-workflow (this skill)05moNo flagsIntermediate
agent-sparc-coordinator07moNo flagsIntermediate
confidence-check136moReviewBeginner
specification-architect1310moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

agent-sparc-coordinator

ruvnet

Agent skill for sparc-coordinator - invoke with $agent-sparc-coordinator

00

confidence-check

SuperClaude-Org

Pre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification.

13114

specification-architect

adrianpuiu

A rigorous, traceability-first system that generates five interconnected architectural documents (blueprint.md, requirements.md, design.md, tasks.md, and validation.md) with complete requirements-to-implementation traceability. Use this skill when users need to architect systems, create technical specifications, or develop structured project documentation with guaranteed traceability.

1388

chief-architect

ananddtyagi

PERSONAL APP ARCHITECT - Strategic development orchestrator for personal productivity applications. Analyzes project context, makes architectural decisions for single-developer projects, delegates to specialized skills, and ensures alignment between user experience goals and technical implementation. Optimized for personal apps targeting 10-100 users.

617

drift-analysis

avifenesh

This skill should be used when the user asks about "plan drift", "reality check", "comparing docs to code", "project state analysis", "roadmap alignment", "implementation gaps", or needs guidance on identifying discrepancies between documented plans and actual implementation state.

213

ralplan

Yeachan-Heo

Iterative planning with Planner, Architect, and Critic until consensus

110

Search skills

Search the agent skills registry