gh-xj
11 verified skills
rd-decide
--- name: rd-decide worker-type: verify sidecar-path: synthesis/decisions/ blocking: true requires: [rd-challenge] capabilities: [no-web-access] eval-signals: [finding-produced, question-answered] --- # rd-decide: Decision Finalization Incorporate challenge feedback and finalize the D-NNN decision file. ## When To Use - Dispatched after rd-challenge completes successfully - Final worker in the research-decision chain: gather → deliberate → challenge → decide ## Input - Draft decision from
development
rd-gather
--- name: rd-gather worker-type: triage sidecar-path: synthesis/decisions/evidence/ blocking: true requires: [] capabilities: [no-web-access] eval-signals: [evidence-chain-complete, evidence-gap] --- # rd-gather: Evidence Assembly for Decisions Assemble and assess evidence from domain findings to prepare for decision drafting. ## When To Use - Dispatched by case-dispatcher when a research-decision case (D-NNN) is opened - First worker in the research-decision chain: gather → deliberate → cha
development
rw-analyze
--- 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) #
development
rw-capture
--- name: rw-capture worker-type: verify sidecar-path: literature/corpus/ blocking: true requires: [rw-discover] capabilities: [can-run-commands] eval-signals: [source-quality-high, source-quality-low, cross-ref] --- # rw-capture: Literature Capture Worker ## Input - Discovery candidate list from rw-discover (`literature/discovery/{question-slug}-discovery.md`) - Existing `literature/catalog.md` for S-NNN ID assignment ## Output - Corpus files in `literature/corpus/{type}/` with companion h
testing
rw-discover
--- 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
data-ai
rw-reflect
--- 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
development
rw-synthesize
--- 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
rw-optimise
--- 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
testing
rw-challenge
--- name: rw-challenge worker-type: challenge sidecar-path: analysis/critiques/ blocking: true requires: [rw-synthesize] capabilities: [no-web-access] eval-signals: [budget-overfit, evidence-gap] --- # rw-challenge: Adversarial Review Worker ## Input - Findings from `synthesis/findings/F-NNN-*.md` - Cited sources from `literature/corpus/` - Analysis comparisons from `analysis/comparisons/` ## Output - `analysis/critiques/F-NNN-critique.md` — one critique per finding ## Responsibilities 1.
development
rd-deliberate
--- name: rd-deliberate worker-type: review sidecar-path: synthesis/decisions/drafts/ blocking: true requires: [rd-gather] capabilities: [no-web-access] eval-signals: [finding-produced, cross-domain-cited] --- # rd-deliberate: Decision Drafting Evaluate alternatives and draft a D-NNN decision file based on assembled evidence. ## When To Use - Dispatched after rd-gather completes successfully - Second worker in the research-decision chain: gather → deliberate → challenge → decide ## Input -
development
rd-challenge
--- name: rd-challenge worker-type: challenge sidecar-path: analysis/critiques/decisions/ blocking: true requires: [rd-deliberate] capabilities: [no-web-access] eval-signals: [budget-overfit, evidence-gap] --- # rd-challenge: Decision Challenge Adversarial review of a draft decision to stress-test rationale, alternatives evaluation, and evidence basis. ## When To Use - Dispatched after rd-deliberate completes successfully - Third worker in the research-decision chain: gather → deliberate → c
development