{"id":35893248,"url":"https://github.com/tripleyak/SkillForge","last_synced_at":"2026-01-15T19:00:47.546Z","repository":{"id":331054076,"uuid":"1124990304","full_name":"tripleyak/SkillForge","owner":"tripleyak","description":"The ultimate meta-skill for generating best-in-class Claude Code skills.","archived":false,"fork":false,"pushed_at":"2025-12-31T03:29:26.000Z","size":70132,"stargazers_count":203,"open_issues_count":0,"forks_count":23,"subscribers_count":4,"default_branch":"main","last_synced_at":"2026-01-03T22:03:16.025Z","etag":null,"topics":["claude-ai","claude-code","claude-skills"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tripleyak.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-30T01:02:27.000Z","updated_at":"2026-01-03T09:50:47.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/tripleyak/SkillForge","commit_stats":null,"previous_names":["tripleyak/skillcreator","tripleyak/skill-creator-and-improver"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/tripleyak/SkillForge","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tripleyak%2FSkillForge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tripleyak%2FSkillForge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tripleyak%2FSkillForge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tripleyak%2FSkillForge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tripleyak","download_url":"https://codeload.github.com/tripleyak/SkillForge/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tripleyak%2FSkillForge/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28465782,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-15T18:56:24.589Z","status":"ssl_error","status_checked_at":"2026-01-15T18:56:23.992Z","response_time":62,"last_error":"SSL_read: (null) (tls_retry_write_records failure)","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["claude-ai","claude-code","claude-skills"],"created_at":"2026-01-09T11:00:36.028Z","updated_at":"2026-01-15T19:00:47.043Z","avatar_url":"https://github.com/tripleyak.png","language":"Python","readme":"# SkillForge v4.0\n\n**From Art to Engineering: A Manifesto for AI Skill Creation.**\n\n![SkillForge](assets/images/01-title.png)\n\n---\n\n## The Problem\n\nThe central challenge in AI development isn't a lack of ideas, but the inconsistent process of turning them into robust, reliable skills. Current methods are often ad-hoc, brittle, and difficult to scale—resembling more of an art form than a predictable engineering discipline.\n\n![The Quality Gap](assets/images/02-quality-gap.png)\n\n---\n\n## The Solution\n\n**Quality is built in, not bolted on.**\n\nSkillForge is a methodology where rigor is integrated into every step of the creation process, from initial conception to final validation. It's a fundamental shift from reactive testing to proactive engineering.\n\n![Quality Built In](assets/images/03-quality-built-in.png)\n\n---\n\n## What's New in v4.0\n\n### Phase 0: Universal Skill Triage\n\nSkillForge now analyzes **any input**—prompts, errors, code, URLs—and automatically routes to the right action:\n\n- **USE_EXISTING** - Existing skill handles this perfectly\n- **IMPROVE_EXISTING** - Existing skill is close but needs enhancement\n- **CREATE_NEW** - No good match, create new skill\n- **COMPOSE** - Multiple skills needed, suggest chain\n\n```bash\n# These all work - SkillForge routes automatically:\n\nSkillForge: create a skill for automated code review\n→ Creates new skill (Phase 1-4)\n\nhelp me debug this TypeError\n→ Recommends debugging skills\n\ndo I have a skill for Excel?\n→ Searches and recommends matching skills\n```\n\n### Universal Domain Matching\n\n- Matches by **concept** (debugging, testing, spreadsheets) not hardcoded skill names\n- Works for **everyone** regardless of what skills you have installed\n- 20+ domain categories with intelligent synonym matching\n- Graceful degradation - returns `CREATE_NEW` when no skills match\n\n---\n\n## The 4-Phase Architecture\n\nSkillForge implements its philosophy through a rigorous, autonomous 4-phase architecture. This structure ensures that every skill undergoes comprehensive analysis, thorough specification, clean generation, and objective approval before it is complete.\n\n![4-Phase Architecture](assets/images/04-four-phase-architecture.png)\n\n---\n\n## Phase 1: Deep Analysis\n\n**Maximum depth before a single line is generated.**\n\nEvery problem is systematically deconstructed through **11 distinct thinking lenses**. This framework forces a holistic and unbiased evaluation, moving beyond surface-level requirements to uncover hidden constraints, edge cases, and long-term implications.\n\n![Phase 1: Thinking Lenses](assets/images/05-phase1-thinking-lenses.png)\n\nThe 11 lenses include: Systems Thinking, First Principles, User-Centric Thinking, Edge Cases, Temporal Analysis, Security Implications, Ethical Considerations, Regression Analysis, Scalability, Performance, and Long-Term Viability.\n\n---\n\n## Phases 2 \u0026 3: Specification \u0026 Generation\n\n**Translating deep analysis into a flawless build.**\n\nThe insights from the 11 lenses are codified into a structured, machine-readable specification using a standardized XML template. This spec then guides an autonomous generation phase, ensuring the final skill is a perfect implementation of the exhaustive analysis.\n\n![Phases 2 \u0026 3](assets/images/06-phases-2-3.png)\n\n---\n\n## Phase 4: Multi-Agent Synthesis\n\n**A panel of experts demands unanimous approval.**\n\nA generated skill is not considered complete until it passes a rigorous synthesis protocol. It is submitted to a panel of specialized Opus 4.5 agents, each evaluating the skill against distinct, specialized criteria. **Approval must be unanimous.**\n\n![Phase 4: Multi-Agent Synthesis](assets/images/07-phase4-synthesis.png)\n\nThe panel includes:\n- **Code Quality Agent** - Architecture, patterns, correctness\n- **Evolution Agent** - Timelessness, extensibility, future-readiness\n- **Security Agent** - Vulnerability assessment, safe patterns\n- **Script Agent** (conditional) - Validates code quality when scripts are present\n\n---\n\n## The Evolution Mandate\n\n**Designing for a multi-year lifespan.**\n\nSkills built with SkillForge are not ephemeral. A dedicated **Evolution \u0026 Timelessness Agent** scores every skill on its potential for longevity, extensibility, and future-readiness.\n\n**The skill must achieve a score of ≥7/10 to pass. This is a non-negotiable quality gate.**\n\n---\n\n## Three Core Principles\n\n![Core Principles](assets/images/09-core-principles.png)\n\n| Principle | Implementation |\n|-----------|----------------|\n| **Engineer for Agents** | Standardized directory structure, XML-based templates, automated validation |\n| **Systematize Rigor** | 4-phase architecture, regression questioning, 11 thinking lenses, multi-agent synthesis |\n| **Design for Evolution** | Dedicated Evolution agent, mandatory ≥7/10 timelessness score, required extension points |\n\n---\n\n## Agentic Capabilities\n\nSkillForge includes a comprehensive script integration framework, enabling skills to possess fully agentic capabilities like self-verification, error recovery, and state persistence.\n\n![Agentic Capabilities](assets/images/10-agentic-capabilities.png)\n\n**Key Features:**\n- **Phase 1D: Automation Analysis** - Proactively identifies opportunities for Python scripts\n- **Conditional 4th Agent** - Script Agent validates code quality when scripts are present\n- **Self-verification** - Scripts can verify their own outputs\n- **State persistence** - Track progress across sessions\n\n### New Scripts in v4.0\n\n| Script | Purpose |\n|--------|---------|\n| `triage_skill_request.py` | Intelligent input classification and skill matching |\n| `discover_skills.py` | Scans all skill sources and builds searchable index |\n| `match_skills.py` | Multi-factor confidence scoring |\n| `verify_recommendation.py` | Self-verification of recommendation quality |\n\n---\n\n## Directory Structure\n\nThe methodology is reflected in a clean, predictable, and standardized directory structure. Every component has its place, from templates and references to validation scripts.\n\n![Directory Structure](assets/images/11-directory-structure.png)\n\n```\nskillforge/\n├── SKILL.md                    # Main skill definition\n├── README.md                   # This file\n├── LICENSE                     # MIT License\n├── references/                 # The \"brain\" of the system\n│   ├── regression-questions.md\n│   ├── multi-lens-framework.md\n│   ├── specification-template.md\n│   ├── evolution-scoring.md\n│   ├── synthesis-protocol.md\n│   └── script-integration-framework.md\n├── assets/\n│   └── templates/              # Reusable blueprints\n│       ├── skill-spec-template.xml\n│       ├── skill-md-template.md\n│       └── script-template.py\n└── scripts/                    # Automated quality gates\n    ├── triage_skill_request.py\n    ├── discover_skills.py\n    ├── match_skills.py\n    ├── verify_recommendation.py\n    ├── validate-skill.py\n    └── package_skill.py\n```\n\n---\n\n## Installation \u0026 Usage\n\n![Installation](assets/images/12-installation.png)\n\n```bash\n# Installation\ncp -r skillforge ~/.claude/skills/\n\n# Full autonomous execution\nSkillForge: {goal}\n\n# Natural language activation\ncreate skill for {purpose}\n\n# Generate specification only\nskillforge --plan-only\n```\n\n### Triggers\n\n**Creation:**\n- `SkillForge: {goal}` - Full autonomous skill creation\n- `create skill` - Natural language activation\n- `design skill for {purpose}` - Purpose-first creation\n\n**Routing (v4.0):**\n- `{any input}` - Analyzes and routes automatically\n- `do I have a skill for` - Searches existing skills\n- `which skill` / `what skill` - Recommends matching skills\n- `improve {skill-name} skill` - Enters improvement mode\n\n---\n\n## Requirements\n\n- Claude Code CLI\n- Claude Opus 4.5 model access\n- Python 3.8+ (for validation scripts)\n\n---\n\n## Conclusion\n\n![Closing](assets/images/13-closing.png)\n\n**SkillForge is a systematic methodology for quality.**\n\nBy codifying expert analysis, rigorous specification, and multi-agent peer review into a fully autonomous system, SkillForge provides a blueprint for building the next generation of robust, reliable, and evolution-aware AI skills.\n\n**It transforms skill creation from an art into an engineering discipline.**\n\n---\n\n## License\n\nMIT License - see [LICENSE](LICENSE)\n\n---\n\n## Changelog\n\n### v4.0.0 (Current)\n- Renamed from SkillCreator to SkillForge\n- Added Phase 0: Universal Skill Triage\n- Added universal domain-based matching (works for everyone)\n- Added triage, discovery, matching, and verification scripts\n- Intelligent routing: USE → IMPROVE → CREATE → COMPOSE\n\n### v3.2.0\n- Added Script Integration Framework for agentic skills\n- Added 4th Script Agent to synthesis panel (conditional)\n- Added Phase 1D: Automation Analysis\n\n### v3.1.0\n- Added progressive disclosure structure\n- Fixed frontmatter for packaging compatibility\n\n### v3.0.0\n- Complete redesign as ultimate meta-skill\n- Added regression questioning loop\n- Added multi-lens analysis framework (11 models)\n- Added evolution/timelessness core lens\n- Added multi-agent synthesis panel\n","funding_links":[],"categories":["Claude Skills","Python"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftripleyak%2FSkillForge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftripleyak%2FSkillForge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftripleyak%2FSkillForge/lists"}