skill-forge
starsforks
How to install skill-forge?
dnyoussef/context-cascade/skill-forge
$npx -y skills add DNYoussef/context-cascade --skill skill-forge/*============================================================================*/ /* SKILL-FORGE SKILL :: VERILINGUA x VERIX EDITION */ /*============================================================================*/
SKILL.md
| 1 | /*============================================================================*/ |
| 2 | /* SKILL-FORGE SKILL :: VERILINGUA x VERIX EDITION */ |
| 3 | /*============================================================================*/ |
| 4 | |
| 5 | --- |
| 6 | name: skill-forge |
| 7 | version: 3.0.1 |
| 8 | description: | |
| 9 | [assert|neutral] Advanced skill creation system for Claude Code that combines deep intent analysis, evidence-based prompting principles, and systematic skill engineering. Use when creating new skills or refining exist [ground:given] [conf:0.95] [state:confirmed] |
| 10 | category: foundry |
| 11 | tags: |
| 12 | - foundry |
| 13 | - creation |
| 14 | - meta-tools |
| 15 | author: ruv |
| 16 | cognitive_frame: |
| 17 | primary: evidential |
| 18 | goal_analysis: |
| 19 | first_order: "Execute skill-forge workflow" |
| 20 | second_order: "Ensure quality and consistency" |
| 21 | third_order: "Enable systematic foundry processes" |
| 22 | --- |
| 23 | |
| 24 | /*----------------------------------------------------------------------------*/ |
| 25 | /* S0 META-IDENTITY */ |
| 26 | /*----------------------------------------------------------------------------*/ |
| 27 | |
| 28 | [define|neutral] SKILL := { |
| 29 | name: "skill-forge", |
| 30 | category: "foundry", |
| 31 | version: "3.0.1", |
| 32 | layer: L1 |
| 33 | } [ground:given] [conf:1.0] [state:confirmed] |
| 34 | |
| 35 | /*----------------------------------------------------------------------------*/ |
| 36 | /* S1 COGNITIVE FRAME */ |
| 37 | /*----------------------------------------------------------------------------*/ |
| 38 | |
| 39 | [define|neutral] COGNITIVE_FRAME := { |
| 40 | frame: "Evidential", |
| 41 | source: "Turkish", |
| 42 | force: "How do you know?" |
| 43 | } [ground:cognitive-science] [conf:0.92] [state:confirmed] |
| 44 | |
| 45 | ## Kanitsal Cerceve (Evidential Frame Activation) |
| 46 | Kaynak dogrulama modu etkin. |
| 47 | |
| 48 | /*----------------------------------------------------------------------------*/ |
| 49 | /* S2 TRIGGER CONDITIONS */ |
| 50 | /*----------------------------------------------------------------------------*/ |
| 51 | |
| 52 | [define|neutral] TRIGGER_POSITIVE := { |
| 53 | keywords: ["skill-forge", "foundry", "workflow"], |
| 54 | context: "user needs skill-forge capability" |
| 55 | } [ground:given] [conf:1.0] [state:confirmed] |
| 56 | |
| 57 | /*----------------------------------------------------------------------------*/ |
| 58 | /* S3 CORE CONTENT */ |
| 59 | /*----------------------------------------------------------------------------*/ |
| 60 | |
| 61 | <!-- SKILL SOP IMPROVEMENT v1.0 --> |
| 62 | ## Skill Execution Criteria |
| 63 | |
| 64 | ### When to Use This Skill |
| 65 | - Creating new skills with comprehensive structure and validation |
| 66 | - Building agent-powered workflows with multi-agent orchestration |
| 67 | - Developing production-grade skills with proper documentation |
| 68 | - Need adversarial testing and COV protocol validation |
| 69 | - Creating skills that integrate with MCP servers and Claude Flow |
| 70 | |
| 71 | ### When NOT to Use This Skill |
| 72 | - For quick atomic micro-skills (use micro-skill-creator instead) |
| 73 | - For agent creation without skill wrapper (use agent-creator) |
| 74 | - For prompt optimization only (use prompt-architect) |
| 75 | - When simple script suffices without skill abstraction |
| 76 | |
| 77 | ### Success Criteria |
| 78 | - [assert|neutral] primary_outcome: "Production-grade skill with comprehensive structure, agent coordination, adversarial testing, and integration documentation" [ground:acceptance-criteria] [conf:0.90] [state:provisional] |
| 79 | - [assert|neutral] quality_threshold: 0.91 [ground:acceptance-criteria] [conf:0.90] [state:provisional] |
| 80 | - [assert|neutral] verification_method: "Skill passes adversarial testing protocol, survives COV validation, integrates with Claude Flow, includes examples and tests" [ground:acceptance-criteria] [conf:0.90] [state:provisional] |
| 81 | |
| 82 | ### Edge Cases |
| 83 | - case: "Skill requires complex multi-agent coordination" |
| 84 | handling: "Use agent orchestration patterns, define clear coordination protocol, test with ruv-swarm" |
| 85 | - case: "Skill needs MCP server integration" |
| 86 | handling: "Declare MCP dependencies in frontmatter, add auto-enable logic, document requirements" |
| 87 | - case: "Skill has performance constraints" |
| 88 | handling: "Add performance benchmarks, optimize agent selection, implement caching strategies" |
| 89 | |
| 90 | ### Skill Guardrails |
| 91 | NEVER: |
| 92 | - "Skip adversarial testing (validation protocol required for production)" |
| 93 | - "Create skills without proper file structure (examples, tests, resources mandatory)" |
| 94 | - "Omit MCP integration points (skills should leverage available tools)" |
| 95 | - "Use generic coordination (leverage specialized orchestration agents)" |
| 96 | ALWAYS: |
| 97 | - "Follow file structure standards (examples/, tests/, resources/, references/)" |
| 98 | - "Include adversarial testing protocol and COV validation" |
| 99 | - "Declare MCP server dependencies in YAML frontmatter" |
| 100 | - "Provide comprehensive examples with expected inputs/outputs" |
| 101 | - "Document integration with Claude Flow and agent coordination" |
| 102 | |
| 103 | ### Evidence-Based Execution |
| 104 | self_consistency: "After skill creation, run multiple execution rounds with diverse inputs to verify consistent behavior and agent coordination quality" |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
