cogworks-learn
Skill Writer Expert
Role
Create or revise agent skills so they are:
- faithful to source material
- immediately actionable
- context-efficient
- structurally valid for their target runtime
For generated skills, the priority order is: fidelity > judgment density > drift resistance > context efficiency > composability
When To Use
Use this skill when:
- creating or revising a cogworks-generated skill
- revising an existing
SKILL.mdthat must preserve an explicit skill contract
More from williamhallatt/cogworks
cogworks
Start here — turn source material into a validated agent skill. Orchestrates cogworks-encode (synthesis) and cogworks-learn (skill generation).
29cogworks-encode
Use when combining 2+ sources on a single topic to produce a unified, decision-first knowledge base — especially when sources conflict, overlap, or must be mapped to explicit decision rules. Handles multi-source synthesis, contradiction resolution, and cross-source relationship extraction. Does not handle single-source summarization, copy-editing, or format conversion.
25claude-prompt-engineering
Optimize Claude Code prompts for Opus 4.6, Sonnet 4.5, and Haiku 4.5 with model-aware reasoning settings, context control, safe tool use, and concise output shaping.
8skill-evaluation
Guides systematic evaluation of Claude Code skills through eval-driven development, SMART success criteria, layered grading (deterministic then LLM-as-judge then human), four-category test datasets with negative controls, and observable behavior checks. Apply when designing skill tests, defining quality metrics, building test cases, grading skill outputs, choosing graders, calibrating LLM judges, or assessing whether a skill is production-ready. Use when asked "how do I test this skill", "is this ready to ship", or "what should my success criteria be".
6codex-prompt-engineering
Optimize Codex/GPT prompts for gpt-5.1, gpt-5.2, and gpt-5.2-codex with calibrated reasoning effort, autonomous execution patterns, correct tool contracts (apply_patch, exec_command, update_plan), compact outputs, evaluation flywheel loops, and production security controls.
4