Claude Skill

toolkit

Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.

LLM Mart · 0 points · 1 views 0 listing impressions 0 install-command copies
Download notque-vexjoy-agent-skills_meta_toolkit-1f3eabd.zip · 273 KB

Install

skills CLI npx skills add https://github.com/notque/vexjoy-agent/tree/main/skills/meta/toolkit
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install notque-vexjoy-agent@llmmart
Git git clone https://github.com/notque/vexjoy-agent.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole notque/vexjoy-agent collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Toolkit

Nine modes covering the full toolkit lifecycle: creating and improving skills and agents; evaluating agents; maintaining routing tables; generating CLAUDE.md; composing multi-skill DAGs; and running the evolution loop. Classify the request and follow the matching section.

Mode Selection

Mode Signals Section
Skill Creator create skill, scaffold skill, new skill, build a skill Create Skill
Agent Creator create agent, scaffold agent, new agent Create Agent
Weak-Model Uplift weaker model, uplift skill, make a skill work for Opus 4.6, improve guidance from generated output Uplift for Weaker Models
Agent Comparison compare agents, A/B test agents, benchmark agents, benchmark skill, bake-off Compare Agents
Agent Evaluation evaluate agent quality, audit agent, grade agent, eval skill Evaluate Agent
Skill Composer compose skills, DAG orchestration, skill pipeline Compose Skills
Routing Tables update routing tables, sync routing, routing drift Update Routing
Toolkit Evolution evolve toolkit, self-improve, discover gaps Evolve Toolkit
Generate CLAUDE.md generate claude.md, create claude.md, init Generate CLAUDE.md

Create Skill

Phases: INTENT -> DRAFT -> TEST -> REGISTER

  1. Capture intent. What should the skill do? When should it trigger? What output? Are outputs objectively verifiable (code, data) or subjective (writing, design)?
  2. Duplicate check. Run grep -i "<domain>" skills/*/SKILL.md to check existing coverage. If an umbrella skill covers the domain, add a reference file instead.
  3. Write SKILL.md. Follow references/skill-creator/skill-template.md for frontmatter structure. Apply Dense-Complete Writing standard. Frontmatter must include: name, description, routing (triggers, not_for, category, pairs_with), allowed-tools.
  4. Test. Try 3 should-trigger, 2 should-not-trigger, and 2 near-miss prompts with the skill loaded. Revise the SKILL.md until routing and output are right.
  5. Register. Run python3 scripts/generate-skill-index.py to update routing.

Load references/skill-creator.md for the full workflow. Deep references in references/skill-creator/ cover progressive disclosure, artifact schemas, complexity tiers, error catalog, enrichment workflow, and more.

Scripts: scripts/skill-creator/


Create Agent

Phases: DISCOVER -> DESIGN -> SCAFFOLD -> REGISTER -> VALIDATE

  1. Discover. Check for domain overlap: grep -i "<domain>" agents/*.md. If an existing agent covers the domain, add a references/ file instead.
  2. Design. Decide role type (reviewer/engineer/orchestrator), allowed tools, complexity, triggers (3-6 specific phrases), pairs_with (verify each exists), reference files, description (intent verb + domain + boundary clause), activation cases.
  3. Scaffold. Write the agent file using references/agent-creator/agent-frontmatter-template.md. Follow docs/PHILOSOPHY.md for operator context structure.
  4. Register. Run python3 scripts/generate-agent-index.py.
  5. Validate. Run python3 scripts/validate-references.py to check reference file integrity. Test activation with the 3+2+2 prompt set.

Load references/agent-creator.md for full phases. Deep references in references/agent-creator/ cover design patterns, frontmatter template, eval design.


Uplift for Weaker Models

Improve a skill, agent, or shared guide until a weaker model produces strong output with it. Load references/weak-model-uplift.md and follow its steps:

  1. Pick the target from data. Query ~/.claude/learning/usage.db and learning.db for heavily used or failing skills.
  2. Build tasks and checks first. 4–8 tasks plus 1–2 held-out tasks; deterministic checks and a yes/no rubric written before any run.
  3. Run the arms. No guidance and current guidance, two samples per task minimum, with python3 scripts/weak_model_run.py.
  4. Score and look. Checks, rubric, your own review of every artifact, optional Jev questions on extracted facts.
  5. Turn failures into rules. Concrete values, before/after examples, runnable checks; delete stale instructions; examples from unrelated products.
  6. Rerun the guided arm and held-out tasks; stop when gains flatten or after three rounds.
  7. Report and ship a per-round table with held-out results, cost, and caveats in the PR body.

Compare Agents

Controlled benchmarks comparing agent variants on identical tasks.

  1. Select variants. Identify the agents to compare (2-4 variants).
  2. Design benchmark. Load references/agent-comparison/benchmark-tasks.md. Select 5-10 representative tasks covering the agent's domain. When the result decides a ship, also load references/blind-ab-tests.md and pass its difficulty pilot before the main run.
  3. Execute. Run each task with each variant. Collect: output quality, token usage, tool calls, time.
  4. Grade. Apply rubric from references/agent-comparison/grading-rubric.md. Score each dimension.
  5. Report. Use references/agent-comparison/report-template.md. Include: methodology, per-task scores, aggregate rankings, cost analysis, recommendation.
  6. Optimize. Load references/agent-comparison/optimize-phase.md to improve the winning variant further.

Load references/agent-comparison.md for the full methodology.


Evaluate Agent

Static structural and standards-compliance grading with a 90-point deterministic scorer.

  1. Read the agent file. Extract frontmatter, body sections, reference files.
  2. Score. Apply rubric from references/agent-evaluation/scoring-rubric.md. Categories: identity (15 pts), expertise (20 pts), routing (15 pts), references (15 pts), workflow (15 pts), standards (10 pts).
  3. Report. Use references/agent-evaluation/report-templates.md. Include: per-category scores, specific findings, improvement recommendations.
  4. Batch mode. For multiple agents: references/agent-evaluation/batch-evaluation.md.

Load references/agent-evaluation.md for the full methodology.


Compose Skills

DAG-based multi-skill orchestration with dependency resolution.

  1. Define the DAG. List skills in execution order. Identify dependencies (skill B needs output from skill A).
  2. Check compatibility. Load references/skill-composer/compatibility-matrix.md. Verify input/output contracts between skills.
  3. Build the pipeline. Load references/skill-composer/composition-patterns.md for orchestration patterns (serial, parallel, fan-out, conditional).
  4. Execute. Run skills in DAG order. Pass outputs between skills via the defined contracts.
  5. Validate. Check all skills completed. Verify final output meets the composite goal.

Load references/skill-composer.md for the full methodology. See references/skill-composer/examples.md for worked examples.

Scripts: scripts/skill-composer/


Update Routing

5-phase pipeline: SCAN -> EXTRACT -> GENERATE -> UPDATE -> VERIFY.

  1. SCAN. Run python3 scripts/generate-skill-index.py to discover all skills and agents.
  2. EXTRACT. Parse frontmatter from each SKILL.md and agent file. Extract triggers, description, category, complexity.
  3. GENERATE. Build skills/INDEX.json and agents/INDEX.json.
  4. UPDATE. Write index files. PostToolUse hooks auto-regenerate on individual edits; this covers bulk changes and drift.
  5. VERIFY. Compare generated index against discovered files. Report missing entries, conflicts, or stale entries.

Load references/routing-table-updater.md for full phases. Deep references in references/routing-table-updater/ cover routing format, extraction patterns, conflict resolution, batch mode.


Evolve Toolkit

7-phase pipeline: DISCOVER -> DIAGNOSE -> PROPOSE -> CRITIQUE -> BUILD -> VALIDATE -> EVOLVE.

  1. DISCOVER. Audit recent sessions for routing failures, skill gaps, agent weaknesses, user friction.
  2. DIAGNOSE. Load references/toolkit-evolution/diagnose-scripts.md. Run gap analysis scripts. Identify patterns.
  3. PROPOSE. Generate 3-5 improvement proposals with expected impact, effort, risk.
  4. CRITIQUE. Apply multi-perspective review to proposals.
  5. BUILD. Implement the approved proposals using the appropriate mode above (create skill, create agent, etc.).
  6. VALIDATE. Run tests and validators on new/changed components.
  7. EVOLVE. Update evolution history at references/toolkit-evolution/evolution-history.md.

Load references/toolkit-evolution.md for the full pipeline.


Generate CLAUDE.md

4-phase pipeline: SCAN -> DETECT -> GENERATE -> VALIDATE.

  1. SCAN. Check for existing CLAUDE.md. If present, write to CLAUDE.md.generated for comparison. Detect language, framework, build system from repo files.
  2. DETECT. Identify domain enrichment opportunities. Load references/generate-claudemd/examples-and-errors.md for language-specific patterns.
  3. GENERATE. Load template from references/generate-claudemd/CLAUDEMD_TEMPLATE.md. Fill sections: overview, commands, architecture, conventions, testing, deployment.
  4. VALIDATE. Run all documented commands. Verify paths exist. Check for secrets in output.

Optional modes: subdirectory CLAUDE.md for monorepos; minimal mode (overview + commands + architecture only).


Deep References

Load when the task needs detailed schemas, templates, or methodology.

Mode Key References
Skill Creator references/skill-creator.md, references/skill-creator/{skill-template,progressive-disclosure,complexity-tiers,error-catalog,enrichment-workflow}.md
Agent Creator references/agent-creator.md, references/agent-creator/{agent-design-patterns,agent-frontmatter-template,agent-eval-design}.md
Weak-Model Uplift references/weak-model-uplift.md
Agent Comparison references/agent-comparison.md, references/agent-comparison/{methodology,grading-rubric,benchmark-tasks,report-template,optimize-phase}.md
Blind A/B Tests references/blind-ab-tests.md: difficulty pilot, real-bug corpus, arm parity, grader validation, position bias, power, pre-registration, recompute audit
Agent Evaluation references/agent-evaluation.md, references/agent-evaluation/{scoring-rubric,report-templates,batch-evaluation}.md
Skill Composer references/skill-composer.md, references/skill-composer/{compatibility-matrix,composition-patterns,skill-patterns,examples}.md
Routing Tables references/routing-table-updater.md, references/routing-table-updater/{routing-format,extraction-patterns,conflict-resolution,examples}.md
Toolkit Evolution references/toolkit-evolution.md, references/toolkit-evolution/{diagnose-scripts,evolution-history,evolve-preferred-patterns}.md
Generate CLAUDE.md references/generate-claudemd.md, references/generate-claudemd/{CLAUDEMD_TEMPLATE,examples-and-errors}.md

Scripts and Agents

Mode Scripts Agents
Skill Creator scripts/skill-creator/ agents/skill-creator/
Skill Composer scripts/skill-composer/ --
Weak-Model Uplift scripts/weak_model_run.py (repo root) --
Routing Tables scripts/routing-table-updater/ --
Agent Comparison scripts/agent-comparison/ --
Files (vexjoy-agent)
  • agents
    • skill-creator
      • analyzer.md 4.8 KB
        Loading…
      • comparator.md 4.7 KB
        Loading…
      • grader.md 3.9 KB
        Loading…
  • assets
    • skill-creator
      • eval_viewer.html 57.1 KB · in bundle
  • references
    • agent-comparison
      • benchmark-tasks.md 6.8 KB
        Loading…
      • do-creation-compliance-tasks.json 8.5 KB
        Loading…
      • examples-and-errors.md 1 KB
        Loading…
      • grading-rubric.md 4.3 KB
        Loading…
      • methodology.md 7.4 KB
        Loading…
      • optimization-guide.md 12 KB
        Loading…
      • optimization-tasks.example.json 853 B
        Loading…
      • optimize-phase.md 9.3 KB
        Loading…
      • read-only-ops-short-tasks.json 375 B
        Loading…
      • report-template.md 3.8 KB
        Loading…
      • socratic-debugging-body-short-tasks.json 372 B
        Loading…
      • socratic-debugging-trigger-tasks.json 2.8 KB
        Loading…
    • agent-creator
      • agent-design-patterns.md 12.1 KB
        Loading…
      • agent-eval-design.md 7.3 KB
        Loading…
      • agent-frontmatter-template.md 8.7 KB
        Loading…
    • agent-evaluation
      • batch-evaluation.md 1.6 KB
        Loading…
      • common-issues.md 2.1 KB
        Loading…
      • report-templates.md 2.2 KB
        Loading…
      • scoring-rubric.md 2.4 KB
        Loading…
    • generate-claudemd
      • CLAUDEMD_TEMPLATE.md 4.1 KB
        Loading…
      • examples-and-errors.md 7.4 KB
        Loading…
    • routing-table-updater
      • batch-mode.md 1.9 KB
        Loading…
      • conflict-resolution.md 3.7 KB
        Loading…
      • error-handling.md 1.9 KB
        Loading…
      • examples.md 4.7 KB
        Loading…
      • extraction-patterns.md 2.2 KB
        Loading…
      • routing-format.md 3.4 KB
        Loading…
      • skill-examples.md 2.7 KB
        Loading…
    • skill-composer
      • compatibility-matrix.md 13 KB
        Loading…
      • composition-patterns.md 4.9 KB
        Loading…
      • examples.md 17.1 KB
        Loading…
      • skill-patterns.md 12.5 KB
        Loading…
    • skill-creator
      • agent-template.md 18 KB
        Loading…
      • artifact-schemas.md 8.2 KB
        Loading…
      • bundled-components.md 2.3 KB
        Loading…
      • complexity-tiers.md 8 KB
        Loading…
      • domain-research-targets.md 13.2 KB
        Loading…
      • enrichment-workflow.md 9.9 KB
        Loading…
      • error-catalog.md 9.9 KB
        Loading…
      • preferred-patterns.md 11.7 KB
        Loading…
      • progressive-disclosure.md 8.5 KB
        Loading…
      • skill-template.md 14.5 KB
        Loading…
      • workflow-patterns.md 7.6 KB
        Loading…
    • toolkit-evolution
      • diagnose-scripts.md 9.5 KB
        Loading…
      • evolution-history.md 5.5 KB
        Loading…
      • evolution-report-template.md 716 B
        Loading…
      • evolve-preferred-patterns.md 6.9 KB
        Loading…
      • evolve-scripts.md 3.7 KB
        Loading…
    • agent-comparison.md 11.5 KB
      Loading…
    • agent-creator.md 8.8 KB
      Loading…
    • agent-evaluation.md 10.6 KB
      Loading…
    • blind-ab-tests.md 7.8 KB
      Loading…
    • generate-claudemd.md 11 KB
      Loading…
    • routing-table-updater.md 10.2 KB
      Loading…
    • skill-composer.md 9.1 KB
      Loading…
    • skill-creator.md 28.9 KB
      Loading…
    • toolkit-evolution.md 14.5 KB
      Loading…
    • weak-model-uplift.md 10.3 KB
      Loading…
  • scripts
    • agent-comparison
      • compare.py 2.3 KB
        Loading…
      • generate_variant.py 19.5 KB
        Loading…
      • optimize_loop.py 89.3 KB
        Loading…
      • trigger_eval.py 19.5 KB
        Loading…
    • routing-table-updater
      • extract_metadata.py 10.8 KB
        Loading…
      • generate_routes.py 10.5 KB
        Loading…
      • scan.py 4.7 KB
        Loading…
      • update_routing.py 12.4 KB
        Loading…
      • validate.py 7.3 KB
        Loading…
    • skill-composer
      • build_dag.py 12.5 KB
        Loading…
      • discover_skills.py 12.1 KB
        Loading…
      • validate.py 12.3 KB
        Loading…
    • skill-creator
      • aggregate_benchmark.py 10 KB
        Loading…
      • eval_compare.py 10.2 KB
        Loading…
      • optimize_description.py 12.5 KB
        Loading…
      • package_results.py 7.8 KB
        Loading…
      • run_eval.py 6.3 KB
        Loading…
  • SKILL.md 12.3 KB
    ---
    name: toolkit
    description: "Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md."
    user-invocable: true
    agent: toolkit-governance-engineer
    allowed-tools:
      - Read
      - Write
      - Edit
      - Bash
      - Glob
      - Grep
      - Agent
      - Task
      - Skill
    routing:
      force_route: true
      not_for: "application code (use workflow), code review (use review)"
      triggers:
        - "create skill"
        - "create agent"
        - "scaffold skill"
        - "scaffold agent"
        - "new skill"
        - "new agent"
        - "skill template"
        - "agent template"
        - "eval skill"
        - "evaluate agent"
        - "benchmark skill"
        - "benchmark agents"
        - "compare agents"
        - "A/B test agents"
        - "optimize description"
        - "evolve toolkit"
        - "toolkit evolution"
        - "self-improve"
        - "update routing tables"
        - "routing maintenance"
        - "generate claude.md"
        - "create claude.md"
        - "compose skills"
        - "bake-off"
        - "skill quality"
        - "weaker model"
        - "weak model uplift"
        - "improve skill for weaker models"
      category: meta-tooling
      pairs_with:
        - review
        - workflow
    ---
    
    # Toolkit
    
    Nine modes covering the full toolkit lifecycle: creating and improving skills
    and agents; evaluating agents; maintaining routing tables; generating CLAUDE.md;
    composing multi-skill DAGs; and running the evolution loop. Classify the request
    and follow the matching section.
    
    ## Mode Selection
    
    | Mode | Signals | Section |
    |------|---------|---------|
    | **Skill Creator** | create skill, scaffold skill, new skill, build a skill | Create Skill |
    | **Agent Creator** | create agent, scaffold agent, new agent | Create Agent |
    | **Weak-Model Uplift** | weaker model, uplift skill, make a skill work for Opus 4.6, improve guidance from generated output | Uplift for Weaker Models |
    | **Agent Comparison** | compare agents, A/B test agents, benchmark agents, benchmark skill, bake-off | Compare Agents |
    | **Agent Evaluation** | evaluate agent quality, audit agent, grade agent, eval skill | Evaluate Agent |
    | **Skill Composer** | compose skills, DAG orchestration, skill pipeline | Compose Skills |
    | **Routing Tables** | update routing tables, sync routing, routing drift | Update Routing |
    | **Toolkit Evolution** | evolve toolkit, self-improve, discover gaps | Evolve Toolkit |
    | **Generate CLAUDE.md** | generate claude.md, create claude.md, init | Generate CLAUDE.md |
    
    ---
    
    ## Create Skill
    
    Phases: **INTENT -> DRAFT -> TEST -> REGISTER**
    
    1. **Capture intent.** What should the skill do? When should it trigger? What output? Are outputs objectively verifiable (code, data) or subjective (writing, design)?
    2. **Duplicate check.** Run `grep -i "<domain>" skills/*/SKILL.md` to check existing coverage. If an umbrella skill covers the domain, add a reference file instead.
    3. **Write SKILL.md.** Follow `references/skill-creator/skill-template.md` for frontmatter structure. Apply Dense-Complete Writing standard. Frontmatter must include: name, description, routing (triggers, not_for, category, pairs_with), allowed-tools.
    4. **Test.** Try 3 should-trigger, 2 should-not-trigger, and 2 near-miss prompts with the skill loaded. Revise the SKILL.md until routing and output are right.
    5. **Register.** Run `python3 scripts/generate-skill-index.py` to update routing.
    
    Load `references/skill-creator.md` for the full workflow. Deep references in `references/skill-creator/` cover progressive disclosure, artifact schemas, complexity tiers, error catalog, enrichment workflow, and more.
    
    Scripts: `scripts/skill-creator/`
    
    ---
    
    ## Create Agent
    
    Phases: **DISCOVER -> DESIGN -> SCAFFOLD -> REGISTER -> VALIDATE**
    
    1. **Discover.** Check for domain overlap: `grep -i "<domain>" agents/*.md`. If an existing agent covers the domain, add a `references/` file instead.
    2. **Design.** Decide role type (reviewer/engineer/orchestrator), allowed tools, complexity, triggers (3-6 specific phrases), pairs_with (verify each exists), reference files, description (intent verb + domain + boundary clause), activation cases.
    3. **Scaffold.** Write the agent file using `references/agent-creator/agent-frontmatter-template.md`. Follow `docs/PHILOSOPHY.md` for operator context structure.
    4. **Register.** Run `python3 scripts/generate-agent-index.py`.
    5. **Validate.** Run `python3 scripts/validate-references.py` to check reference file integrity. Test activation with the 3+2+2 prompt set.
    
    Load `references/agent-creator.md` for full phases. Deep references in `references/agent-creator/` cover design patterns, frontmatter template, eval design.
    
    ---
    
    ## Uplift for Weaker Models
    
    Improve a skill, agent, or shared guide until a weaker model produces strong output with it. Load `references/weak-model-uplift.md` and follow its steps:
    
    1. **Pick the target from data.** Query `~/.claude/learning/usage.db` and `learning.db` for heavily used or failing skills.
    2. **Build tasks and checks first.** 4–8 tasks plus 1–2 held-out tasks; deterministic checks and a yes/no rubric written before any run.
    3. **Run the arms.** No guidance and current guidance, two samples per task minimum, with `python3 scripts/weak_model_run.py`.
    4. **Score and look.** Checks, rubric, your own review of every artifact, optional Jev questions on extracted facts.
    5. **Turn failures into rules.** Concrete values, before/after examples, runnable checks; delete stale instructions; examples from unrelated products.
    6. **Rerun** the guided arm and held-out tasks; stop when gains flatten or after three rounds.
    7. **Report and ship** a per-round table with held-out results, cost, and caveats in the PR body.
    
    ---
    
    ## Compare Agents
    
    Controlled benchmarks comparing agent variants on identical tasks.
    
    1. **Select variants.** Identify the agents to compare (2-4 variants).
    2. **Design benchmark.** Load `references/agent-comparison/benchmark-tasks.md`. Select 5-10 representative tasks covering the agent's domain. When the result decides a ship, also load `references/blind-ab-tests.md` and pass its difficulty pilot before the main run.
    3. **Execute.** Run each task with each variant. Collect: output quality, token usage, tool calls, time.
    4. **Grade.** Apply rubric from `references/agent-comparison/grading-rubric.md`. Score each dimension.
    5. **Report.** Use `references/agent-comparison/report-template.md`. Include: methodology, per-task scores, aggregate rankings, cost analysis, recommendation.
    6. **Optimize.** Load `references/agent-comparison/optimize-phase.md` to improve the winning variant further.
    
    Load `references/agent-comparison.md` for the full methodology.
    
    ---
    
    ## Evaluate Agent
    
    Static structural and standards-compliance grading with a 90-point deterministic scorer.
    
    1. **Read the agent file.** Extract frontmatter, body sections, reference files.
    2. **Score.** Apply rubric from `references/agent-evaluation/scoring-rubric.md`. Categories: identity (15 pts), expertise (20 pts), routing (15 pts), references (15 pts), workflow (15 pts), standards (10 pts).
    3. **Report.** Use `references/agent-evaluation/report-templates.md`. Include: per-category scores, specific findings, improvement recommendations.
    4. **Batch mode.** For multiple agents: `references/agent-evaluation/batch-evaluation.md`.
    
    Load `references/agent-evaluation.md` for the full methodology.
    
    ---
    
    ## Compose Skills
    
    DAG-based multi-skill orchestration with dependency resolution.
    
    1. **Define the DAG.** List skills in execution order. Identify dependencies (skill B needs output from skill A).
    2. **Check compatibility.** Load `references/skill-composer/compatibility-matrix.md`. Verify input/output contracts between skills.
    3. **Build the pipeline.** Load `references/skill-composer/composition-patterns.md` for orchestration patterns (serial, parallel, fan-out, conditional).
    4. **Execute.** Run skills in DAG order. Pass outputs between skills via the defined contracts.
    5. **Validate.** Check all skills completed. Verify final output meets the composite goal.
    
    Load `references/skill-composer.md` for the full methodology. See `references/skill-composer/examples.md` for worked examples.
    
    Scripts: `scripts/skill-composer/`
    
    ---
    
    ## Update Routing
    
    5-phase pipeline: SCAN -> EXTRACT -> GENERATE -> UPDATE -> VERIFY.
    
    1. **SCAN.** Run `python3 scripts/generate-skill-index.py` to discover all skills and agents.
    2. **EXTRACT.** Parse frontmatter from each SKILL.md and agent file. Extract triggers, description, category, complexity.
    3. **GENERATE.** Build `skills/INDEX.json` and `agents/INDEX.json`.
    4. **UPDATE.** Write index files. PostToolUse hooks auto-regenerate on individual edits; this covers bulk changes and drift.
    5. **VERIFY.** Compare generated index against discovered files. Report missing entries, conflicts, or stale entries.
    
    Load `references/routing-table-updater.md` for full phases. Deep references in `references/routing-table-updater/` cover routing format, extraction patterns, conflict resolution, batch mode.
    
    ---
    
    ## Evolve Toolkit
    
    7-phase pipeline: DISCOVER -> DIAGNOSE -> PROPOSE -> CRITIQUE -> BUILD -> VALIDATE -> EVOLVE.
    
    1. **DISCOVER.** Audit recent sessions for routing failures, skill gaps, agent weaknesses, user friction.
    2. **DIAGNOSE.** Load `references/toolkit-evolution/diagnose-scripts.md`. Run gap analysis scripts. Identify patterns.
    3. **PROPOSE.** Generate 3-5 improvement proposals with expected impact, effort, risk.
    4. **CRITIQUE.** Apply multi-perspective review to proposals.
    5. **BUILD.** Implement the approved proposals using the appropriate mode above (create skill, create agent, etc.).
    6. **VALIDATE.** Run tests and validators on new/changed components.
    7. **EVOLVE.** Update evolution history at `references/toolkit-evolution/evolution-history.md`.
    
    Load `references/toolkit-evolution.md` for the full pipeline.
    
    ---
    
    ## Generate CLAUDE.md
    
    4-phase pipeline: SCAN -> DETECT -> GENERATE -> VALIDATE.
    
    1. **SCAN.** Check for existing CLAUDE.md. If present, write to `CLAUDE.md.generated` for comparison. Detect language, framework, build system from repo files.
    2. **DETECT.** Identify domain enrichment opportunities. Load `references/generate-claudemd/examples-and-errors.md` for language-specific patterns.
    3. **GENERATE.** Load template from `references/generate-claudemd/CLAUDEMD_TEMPLATE.md`. Fill sections: overview, commands, architecture, conventions, testing, deployment.
    4. **VALIDATE.** Run all documented commands. Verify paths exist. Check for secrets in output.
    
    Optional modes: subdirectory CLAUDE.md for monorepos; minimal mode (overview + commands + architecture only).
    
    ---
    
    ## Deep References
    
    Load when the task needs detailed schemas, templates, or methodology.
    
    | Mode | Key References |
    |------|---------------|
    | Skill Creator | `references/skill-creator.md`, `references/skill-creator/{skill-template,progressive-disclosure,complexity-tiers,error-catalog,enrichment-workflow}.md` |
    | Agent Creator | `references/agent-creator.md`, `references/agent-creator/{agent-design-patterns,agent-frontmatter-template,agent-eval-design}.md` |
    | Weak-Model Uplift | `references/weak-model-uplift.md` |
    | Agent Comparison | `references/agent-comparison.md`, `references/agent-comparison/{methodology,grading-rubric,benchmark-tasks,report-template,optimize-phase}.md` |
    | Blind A/B Tests | `references/blind-ab-tests.md`: difficulty pilot, real-bug corpus, arm parity, grader validation, position bias, power, pre-registration, recompute audit |
    | Agent Evaluation | `references/agent-evaluation.md`, `references/agent-evaluation/{scoring-rubric,report-templates,batch-evaluation}.md` |
    | Skill Composer | `references/skill-composer.md`, `references/skill-composer/{compatibility-matrix,composition-patterns,skill-patterns,examples}.md` |
    | Routing Tables | `references/routing-table-updater.md`, `references/routing-table-updater/{routing-format,extraction-patterns,conflict-resolution,examples}.md` |
    | Toolkit Evolution | `references/toolkit-evolution.md`, `references/toolkit-evolution/{diagnose-scripts,evolution-history,evolve-preferred-patterns}.md` |
    | Generate CLAUDE.md | `references/generate-claudemd.md`, `references/generate-claudemd/{CLAUDEMD_TEMPLATE,examples-and-errors}.md` |
    
    ## Scripts and Agents
    
    | Mode | Scripts | Agents |
    |------|---------|--------|
    | Skill Creator | `scripts/skill-creator/` | `agents/skill-creator/` |
    | Skill Composer | `scripts/skill-composer/` | -- |
    | Weak-Model Uplift | `scripts/weak_model_run.py` (repo root) | -- |
    | Routing Tables | `scripts/routing-table-updater/` | -- |
    | Agent Comparison | `scripts/agent-comparison/` | -- |
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.