.claude/skills/rw-analyze/SKILL.md
--- name: rw-analyze worker-type: review sidecar-path: analysis/ blocking: true requires: [rw-capture] capabilities: [no-web-access] eval-signals: [evidence-chain-complete, evidence-gap] --- # rw-analyze: Analysis Worker ## Input - Captured corpus files from `literature/corpus/` - Q-NNN sub-questions to guide analysis focus ## Output - `analysis/notes/S-NNN-{slug}.md` — one per captured source (mandatory) - `analysis/comparisons/{topic}-v1.md` — one per sub-question (3+ sources compared) #
npx skillsauth add gh-xj/exp-job-hunter-research rw-analyzeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
literature/corpus/analysis/notes/S-NNN-{slug}.md — one per captured source (mandatory)analysis/comparisons/{topic}-v1.md — one per sub-question (3+ sources compared)catalog.md. Never reference sources by title alone.Match comparison type to the domain question:
Before completing, verify:
catalog.mdMax 2 self-correction iterations. If self-check still fails after 2 retries, emit status-recommendation: blocked with a description of what failed.
See references/analysis-conventions.md for:
development
--- name: rw-synthesize worker-type: review sidecar-path: synthesis/findings/ blocking: true requires: [rw-analyze] capabilities: [no-web-access] eval-signals: [finding-produced, question-answered, no-finding-produced] --- # rw-synthesize: Synthesis Worker ## Input - Analysis notes from `analysis/notes/` - Analysis comparisons from `analysis/comparisons/` - Existing decisions from `synthesis/decisions/` (must not contradict) ## Output - `synthesis/findings/F-NNN-{slug}.md` — one finding per
development
--- name: rw-reflect worker-type: hook sidecar-path: _reflections/ blocking: true requires: [] capabilities: [no-web-access] eval-signals: [coverage-improved] trigger: on-case-close --- # rw-reflect: Post-Case Reflection Worker ## Input - Completed case: Q-NNN (answered or deferred) or D-NNN (proposed) - All artifacts produced during the case lifecycle (discovery logs, corpus files, notes, comparisons, findings, critiques) ## Output - `{domain}/_reflections/YYYY-MM-DD-{slug}.md` ## Respons
testing
--- name: rw-optimise worker-type: custom sidecar-path: _evolution/ blocking: false requires: [rw-reflect] capabilities: [can-edit] --- # rw-optimise: MASE+ Feedback Loop Worker ## Cold Start No optimiser rules fire until 3+ cases produce reflections and quality scorecards. The first 3 cases run with default budget from `.agentops/budget.md`. This is expected — the feedback loop bootstraps from zero data points. Do not attempt to force adjustments before sufficient signal accumulates. This w
data-ai
--- name: rw-discover worker-type: triage sidecar-path: literature/discovery/ blocking: true requires: [] capabilities: [can-run-commands] eval-signals: [coverage-improved, stale-output] --- # rw-discover: Literature Discovery Worker ## Input - Q-NNN file: sub-questions list, evidence needed section - Budget allocation from `.agentops/budget.md` (3-5 queries/sub-question standard, 5-7 for critical) ## Output - `literature/discovery/{question-slug}-discovery.md` ## Responsibilities 1. **Ge