skills/forge-playbook-refine/SKILL.md
[writes] Review and apply playbook refinement proposals. Use when playbooks have accumulated run data and proposals are ready for review. Trigger: /forge-playbook-refine [playbook_id]
npx skillsauth add quantumbitcz/dev-pipeline forge-playbook-refineInstall 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.
Review and apply improvement proposals generated from pipeline run data. Proposals are evidence-backed suggestions for making playbooks produce better code.
See shared/skill-contract.md for the standard exit-code table.
.claude/forge.local.md exists.forge/run-history.db exists.forge/playbook-refinements/ has at least one fileIf prerequisites fail, STOP with guidance:
$ARGUMENTS = optional playbook_id. If omitted, list playbooks with pending proposals.
.forge/playbook-refinements/*.json files.forge/playbook-refinements/{playbook_id}.jsonstatus: ready proposals only## Proposal: {id}
**Type:** {type}
**Target:** {target}
**Confidence:** {confidence} ({agreement})
**Current:** {current_value}
**Proposed:** {proposed_value}
**Evidence:** {evidence}
**Expected Impact:** {impact_estimate}
Options:
.claude/forge-playbooks/{playbook_id}.mdshared/playbooks/{playbook_id}.md.claude/forge-playbooks/ first (project override)scoring_gap / acceptance_gap → append to acceptance_criteria: liststage_focus → modify stages.focus arrayparameter_default → modify parameters[].defaultversion in playbook frontmatter.forge/playbook-refinements/{playbook_id}.json:
status: appliedstatus: rejectedstatus: deferredforge-log.md: [REFINE-APPLIED] {playbook_id} v{old}→v{new}: {proposal_ids}<!-- locked --> fences in playbook files — skip proposals targeting locked sectionspass_threshold, concerns_threshold, or scoring weights/forge-playbooks — Create, list, run, and analyze pipeline playbooks/forge-insights — Cross-run analytics including playbook effectiveness/forge-run — Execute the pipeline (generates the run data that feeds refinements)development
[writes] Build, fix, deploy, review, or modify code in this project. Universal entry for the forge pipeline. Auto-bootstraps on first run; brainstorms before planning when given a feature description. Use when you want to take any productive action: implementing features, fixing bugs, reviewing branches, deploying, committing, running migrations.
tools
[writes] Manage forge state and configuration: recovery, abort, config edits, session handoff, automations, playbooks, output compression, knowledge graph maintenance. Use when you need to recover from broken pipeline state, edit settings, or manage long-lived state.
development
[writes] Create, list, show, resume, or search forge session handoffs. Use when context is getting heavy and you want to transfer a forge run or conversation into a fresh Claude Code session, or to resume from a prior handoff artefact. Subcommands - no args (write), list, show, resume, search.
development
[writes] Manage the Neo4j knowledge graph. Subcommands: init, rebuild (writes); status, query <cypher>, debug (read-only). Requires Docker. No default — an explicit subcommand is required. Use when setting up the graph for the first time, rebuilding after major refactors, checking graph health, or running ad-hoc Cypher diagnostics.