toolkit
Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.
Install
npx skills add https://github.com/notque/vexjoy-agent/tree/main/skills/meta/toolkit
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install notque-vexjoy-agent@llmmart
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
- Capture intent. What should the skill do? When should it trigger? What output? Are outputs objectively verifiable (code, data) or subjective (writing, design)?
- Duplicate check. Run
grep -i "<domain>" skills/*/SKILL.mdto check existing coverage. If an umbrella skill covers the domain, add a reference file instead. - Write SKILL.md. Follow
references/skill-creator/skill-template.mdfor frontmatter structure. Apply Dense-Complete Writing standard. Frontmatter must include: name, description, routing (triggers, not_for, category, pairs_with), allowed-tools. - 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.
- Register. Run
python3 scripts/generate-skill-index.pyto 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
- Discover. Check for domain overlap:
grep -i "<domain>" agents/*.md. If an existing agent covers the domain, add areferences/file instead. - 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.
- Scaffold. Write the agent file using
references/agent-creator/agent-frontmatter-template.md. Followdocs/PHILOSOPHY.mdfor operator context structure. - Register. Run
python3 scripts/generate-agent-index.py. - Validate. Run
python3 scripts/validate-references.pyto 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:
- Pick the target from data. Query
~/.claude/learning/usage.dbandlearning.dbfor heavily used or failing skills. - 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.
- Run the arms. No guidance and current guidance, two samples per task minimum, with
python3 scripts/weak_model_run.py. - Score and look. Checks, rubric, your own review of every artifact, optional Jev questions on extracted facts.
- Turn failures into rules. Concrete values, before/after examples, runnable checks; delete stale instructions; examples from unrelated products.
- Rerun the guided arm and held-out tasks; stop when gains flatten or after three rounds.
- 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.
- Select variants. Identify the agents to compare (2-4 variants).
- 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 loadreferences/blind-ab-tests.mdand pass its difficulty pilot before the main run. - Execute. Run each task with each variant. Collect: output quality, token usage, tool calls, time.
- Grade. Apply rubric from
references/agent-comparison/grading-rubric.md. Score each dimension. - Report. Use
references/agent-comparison/report-template.md. Include: methodology, per-task scores, aggregate rankings, cost analysis, recommendation. - Optimize. Load
references/agent-comparison/optimize-phase.mdto 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.
- Read the agent file. Extract frontmatter, body sections, reference files.
- 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). - Report. Use
references/agent-evaluation/report-templates.md. Include: per-category scores, specific findings, improvement recommendations. - 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.
- Define the DAG. List skills in execution order. Identify dependencies (skill B needs output from skill A).
- Check compatibility. Load
references/skill-composer/compatibility-matrix.md. Verify input/output contracts between skills. - Build the pipeline. Load
references/skill-composer/composition-patterns.mdfor orchestration patterns (serial, parallel, fan-out, conditional). - Execute. Run skills in DAG order. Pass outputs between skills via the defined contracts.
- 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.
- SCAN. Run
python3 scripts/generate-skill-index.pyto discover all skills and agents. - EXTRACT. Parse frontmatter from each SKILL.md and agent file. Extract triggers, description, category, complexity.
- GENERATE. Build
skills/INDEX.jsonandagents/INDEX.json. - UPDATE. Write index files. PostToolUse hooks auto-regenerate on individual edits; this covers bulk changes and drift.
- 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.
- DISCOVER. Audit recent sessions for routing failures, skill gaps, agent weaknesses, user friction.
- DIAGNOSE. Load
references/toolkit-evolution/diagnose-scripts.md. Run gap analysis scripts. Identify patterns. - PROPOSE. Generate 3-5 improvement proposals with expected impact, effort, risk.
- CRITIQUE. Apply multi-perspective review to proposals.
- BUILD. Implement the approved proposals using the appropriate mode above (create skill, create agent, etc.).
- VALIDATE. Run tests and validators on new/changed components.
- 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.
- SCAN. Check for existing CLAUDE.md. If present, write to
CLAUDE.md.generatedfor comparison. Detect language, framework, build system from repo files. - DETECT. Identify domain enrichment opportunities. Load
references/generate-claudemd/examples-and-errors.mdfor language-specific patterns. - GENERATE. Load template from
references/generate-claudemd/CLAUDEMD_TEMPLATE.md. Fill sections: overview, commands, architecture, conventions, testing, deployment. - 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.
Reviews (0)
No reviews yet.
No comments yet.