skill-builder
Create new Claude Code skills from procedural knowledge. Invoke PROACTIVELY when:- Discovering a reusable workflow pattern worth preserving- User asks to "capture this as a skill" or "make this reusable"- Recognizing institutional knowledge that should persist- After solving a problem in a novel way worth repeating- Noticing repeated patterns across sessionsAUTONOMOUS: Create skills proactively, then inform user what was created.
When & Why to Use This Skill
The Skill Builder is a powerful meta-skill for Claude Code designed to autonomously capture, package, and persist procedural knowledge. By identifying successful novel solutions and repeated workflow patterns, it transforms transient interactions into reusable, structured skills. This ensures that institutional knowledge and optimized coding practices are preserved and easily accessible for future tasks, significantly enhancing the autonomy and efficiency of the AI agent.
Use Cases
- Workflow Automation: Automatically detecting a complex, multi-step debugging or deployment sequence and packaging it into a reusable skill for one-click execution in the future.
- Institutional Knowledge Retention: Capturing project-specific architectural constraints and internal coding standards to ensure they are consistently applied across all development sessions.
- Proactive Pattern Recognition: Identifying repetitive manual tasks performed by the user and autonomously creating a skill to automate those processes without requiring manual configuration.
- Best Practice Codification: Researching the latest industry standards for a specific technology and integrating those findings into a structured skill that guides future code generation.
| name | skill-builder |
|---|---|
| description | | |
| AUTONOMOUS | Create skills proactively, then inform user what was created. |
Skill Builder
Build new Claude Code skills that capture procedural knowledge.
Autonomy Model
Create then inform: When recognizing skill-worthy knowledge, create the skill proactively, then inform the user what was created and why. Don't ask permission first.
When to Invoke (Proactively)
- Successful novel solution - Just solved something in a way worth repeating
- Repeated pattern - Noticed doing the same thing multiple times
- Institutional knowledge - Learning domain-specific rules that should persist
- User workflow - User demonstrates a process they want automated
- Research findings - Discovered best practices worth preserving
Quality Gates (Pre-Extraction)
Before creating a skill, verify ALL gates pass:
| Gate | Question | Fail Criteria |
|---|---|---|
| REUSABLE | Applies beyond this instance? | One-off solution |
| NON-TRIVIAL | Required discovery, not docs lookup? | Just followed documentation |
| SPECIFIC | Clear trigger conditions defined? | Vague "sometimes useful" |
| VERIFIED | Solution confirmed working? | Theoretical, untested |
If ANY gate fails → Stop. Not skill-worthy.
Skill Creation Workflow
0. Research Best Practices
Before extracting, search for current patterns:
# Use Gemini CLI for web-grounded research
gemini "[technology] [feature] best practices 2026"
gemini "[technology] [problem type] official recommendations"
Why: Don't just codify what you did. Incorporate current best practices. Skip if: Pattern is project-specific internal convention.
1. Identify the Knowledge
- What problem does this solve?
- What trigger terms would activate it?
- Is it cross-project or project-specific?
2. Draft Structure
Reference references/structure-guide.md for ideal anatomy.
3. Write Description
Reference references/description-patterns.md for trigger-rich descriptions (~100 words, explicit trigger terms).
4. Validate
Run scripts/validate_skill.py <skill-path> to check structure and frontmatter.
5. Inform User
After creating, tell user:
- What skill was created and why
- What triggers will activate it
- How to test it works
Progressive Disclosure
Keep SKILL.md lean (<100 lines). Put detailed specs in references/:
- Detailed examples →
references/examples.md - Edge cases →
references/edge-cases.md - Anti-patterns →
references/anti-patterns.md
Code Opportunities
If skill involves deterministic operations (validation, parsing, extraction), create scripts/ with executable code rather than prose instructions. Scripts:
- Run without loading into context
- Must be executable (
chmod +x) - Should handle errors gracefully
Skill Locations
- Personal:
~/.claude/skills/- Available across all projects - Project:
.claude/skills/- Shared with team via git
Template
Use templates/SKILL-TEMPLATE.md as starting point for new skills.