feature-dev
Automate 7-phase feature development with specialized agents (code-explorer, code-architect, code-reviewer). Use for multi-file features, architectural decisions, or encountering ambiguous requirements, integration patterns, design approach errors.
Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security
Installation for Agentic Skill
View all platforms →skilz install secondsky/claude-skills/feature-dev skilz install secondsky/claude-skills/feature-dev --agent opencode skilz install secondsky/claude-skills/feature-dev --agent codex skilz install secondsky/claude-skills/feature-dev --agent gemini
First time? Install Skilz: pip install skilz
Works with 22+ AI coding agents
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/secondsky/claude-skills cp -r claude-skills/plugins/feature-dev/skills/feature-dev ~/.claude/skills/ Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
pytest-config
by atholaStandardized pytest configuration patterns for plugin development. Reducesduplication across parseltongue, pensive, sanctum, and other plugins.Trigger...
shell-testing-framework
by manutejShell script testing expertise using bash test framework patterns from unix-goto, covering test structure (arrange-act-assert), 4 test categories, ass...
markdownlint-custom-rules
by TheBushidoCollectiveCreate custom linting rules for markdownlint including rule structure, parser integration, error reporting, and automatic fixing.
agentdb-advanced-features
by ruvnet"Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed s...
Agentic Skill Details
- Repository
- claude-skills
- Type
- Technical
- Meta-Domain
- development
- Primary Domain
- testing
- Market Score
- 62.0
Agent Skill Grade
D
Score: 62/100
Click to see breakdown
Score Breakdown
Areas to Improve
- Invalid YAML syntax - parsing failed
- References README.md, agents/*.md, commands/*.md but files don't exist
- No frontmatter to check name
Recommendations
- Focus on improving Spec Compliance (currently 0/15)
- Focus on improving Pda (currently 12/30)
- Address 4 high-severity issues first
Graded: 1/19/2026
Developer Feedback
I took a look at your feature-dev skill and wanted to share some thoughts.
Links:
TL;DR
You're at 62/100, which puts you in D territory. This skill has solid bones—your Utility pillar scored 18/20, which is really strong, and your workflow thinking is clear. But you're getting hammered on Spec Compliance (0/15) and Progressive Disclosure Architecture (12/30). The good news? These are fixable issues, not conceptual ones.
What's Working Well
- Utility is legit (18/20) — Your 7-phase workflow actually addresses real gaps in feature development, and the agent specialization (code-explorer, code-architect, code-reviewer) is practical
- Good trigger phrases — Your activation keywords are specific and discoverable; someone will actually find this when they need it
- Solid examples — You've included concrete output examples that show how the agents work together, which is helpful for understanding the workflow
- Clear instructions — The step-by-step breakdown is easy to follow; this isn't a vague skill
The Big One: Frontmatter is Broken
Your SKILL.md has invalid YAML frontmatter. The grader literally can't parse it, which automatically tanks you 15 points on Spec Compliance. Here's the fix:
Current (broken):
---
name: feature-dev
description: Automate 7-phase feature development with specialized agents (code-explorer, code-architect, code-reviewer). Use for multi-file features, architectural decisions, or
Should be:
---
name: feature-dev
description: Automate feature development across 7 phases using specialized agents. Use when asked to "build a feature", "architect a complex feature", "design multi-file features", or "review feature implementations".
keywords: ["feature development", "architecture", "code review", "multi-agent workflow"]
required-context: true
---
Close that YAML block properly, complete the description with clear trigger phrases, and add keywords. This alone gets you +5 points.
Other Things Worth Fixing
Missing referenced files — You mention
README.md,agents/*.md, andcommands/*.mdthroughout, but these don't exist in the repo. Either create them (which adds nice layered structure) or remove the references. This is costing you points on Progressive Disclosure Architecture.No table of contents — Your SKILL.md is 325 lines without a TOC. For something this long, readers need navigation signals. Add a quick markdown TOC at the top so people can jump to phases, workflow steps, or examples.
Incomplete reference depth — The PDA pillar expects supporting documentation files. Create a simple
README.mdthat explains the overall approach, or break the SKILL.md into sections with clear "learn more here" pointers. Right now it reads like a wall of text.Workflow checklist needs completion — You've numbered 7 phases but the verification section feels rushed. Flesh out what "success" looks like for each phase with concrete acceptance criteria.
Quick Wins
- Fix the YAML frontmatter (+5 points immediately)
- Add a TOC and reference files (+5 points)
- Flesh out the description with trigger phrases (+4 points)
- Complete the verification checklist (+3 points)
These four moves should push you into B territory pretty easily. Your core idea is solid—it's just the packaging that needs work.
Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.
Browse Category
More development Agentic SkillsReport Security Issue
Found a security vulnerability in this agent skill?