calibration-pipeline
Calibration and review-pipeline tooling guidance. Use when running or maintaining calibration scripts, review aggregation, and related deterministic assets for issue #360. DO NOT USE FOR: changing orchestration ownership or agent review policy.
- License 许可
- MIT
- 最近更新
- 2026-08-16
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- calibration-pipeline
- description
- Calibration and review-pipeline tooling guidance. Use when running or maintaining calibration scripts, review aggregation, and related deterministic assets for issue #360. DO NOT USE FOR: changing orchestration ownership or agent review policy.
02 资源文件 18
- 资产文件assets/guidance-complexity.json120 B
- 参考文档references/conductor-credit-emission.md4.6 KB
- 参考文档references/conductor-metrics-protocol.md3.8 KB
- 参考文档references/findings-construction.md2.6 KB
- 参考文档references/metrics-schema.md8.9 KB
- 参考文档references/release-hygiene-credit-emission.md4.4 KB
- 参考文档references/review-credit-emission.md3.4 KB
- 参考文档references/verdict-mapping.md819 B
- 参考文档schemas/phase-containment.schema.json4.5 KB
- 脚本scripts/aggregate-review-scores-core.ps175.2 KB
- 脚本scripts/aggregate-review-scores.ps14.0 KB
- 脚本scripts/backfill-calibration-core.ps17.8 KB
- 脚本scripts/backfill-calibration.ps1484 B
- 脚本scripts/create-improvement-issue-core.ps119.5 KB
- 脚本scripts/create-improvement-issue.ps11.3 KB
- 脚本scripts/pipeline-metrics-helpers.ps12.7 KB
- 脚本scripts/write-calibration-entry-core.ps111.7 KB
- 脚本scripts/write-calibration-entry.ps1854 B
03 SKILL.md 正文
Calibration Pipeline
Reusable entryway for deterministic tooling, committed assets, and pipeline-metrics reference material for the calibration pipeline introduced by issue #360.
Survival:
SMC-09covers raw aggregate/prosecution-depth snapshots asper-dispatchuntil selected PR-body metrics are durable.SMC-10covers thewithin-worktreeper-finding cache;SMC-11coverswithin-worktreecross-PR state. Script temp files areper-processscratch only.
When to Use
- When running or maintaining calibration writers, aggregation scripts, or helper libraries under
scripts/ - When updating committed calibration data or configuration under
assets/ - When a workflow needs the canonical pipeline-metrics schema, verdict mapping, or findings-construction rules without re-reading Code-Conductor
Purpose
- Describe the calibration and review-aggregation domain
- Provide the stable home for pipeline scripts under
scripts/ - Provide the stable home for committed pipeline data under
assets/ - Metric segmentation (sustain-rate by confidence tier) needed to make pre/post coverage-first
sustain_ratereadings comparable is deferred to umbrella #761 — see the## Gotchasentry below
Contents
scripts/contains calibration writers, aggregation tools, improvement-issue helpers, and related shared helpersassets/contains committed pipeline configuration and data consumed by those scriptsreferences/contains extracted pipeline-metrics contract material that other skills and agents can load directlyschemas/phase-containment.schema.jsonis the validation schema for<!-- phase-containment-{ID} -->ledger entries; the ledger's warn-only enforcement surface is.github/scripts/phase-containment-emission-check.ps1(hub maintainers only — repo-relative, does not resolve from a consumer repo's CWD), which sweeps the code-review, post-review-observer, design-challenge, plan-stress-test and brief-review surfaces for upheld findings missing a paired ledger block and reports the gap; it never blocks a caller flow. "Upheld" is deliberately not "judge-sustained": the design-challenge and brief-review surfaces are prosecution-only and authorize counting without a judge, which is the whole point of issue #951. Issue surfaces are routed per issue, so a brief-declared issue is swept on brief-review and not on plan-stress-test
Composite References
- references/metrics-schema.md: canonical
## Pipeline Metricsblock shape, top-level field semantics, and thewrite-calibration-entry.ps1invocation contract - references/verdict-mapping.md: judge verdict to metrics-field mapping for main and post-fix review
- references/findings-construction.md: findings-array construction, backward compatibility, malformed-entry handling, and rework-cycle population rules
- references/release-hygiene-credit-emission.md: v4 release-hygiene credit row construction (state-file reading, YAML examples) and CE Gate S2 synthetic-PR test protocol (issue #441 Step 7b)
- references/review-credit-emission.md: v4 review credit row construction via
Build-ReviewCreditRow— adapter selection, RunIndex semantics, cross-tool handoff, and CE Gate S3 coverage (issue #441 Step 8b) - references/conductor-credit-emission.md: Code-Conductor-owned credit-row emission procedures — Pipeline-Entry Credit Harvest (SMC-17), Deferred Port Credit Rows,
process-reviewtrigger-absent emission, and the Post-PR Credit Row (D10 category 3) - references/conductor-metrics-protocol.md: emission timing and ownership boundary, Add-FCLCreditRow accumulator pattern, release-hygiene and review credit row pointers, and dispatch-cost samples — extracted from
agents/Code-Conductor.agent.mdvia D5 compression (issue #774)
Boundary
- This skill owns deterministic tooling and static assets only
- Review orchestration, judgment, and step execution stay with the owning agents and existing methodology skills
Gotchas
| Trigger | Gotcha | Fix |
|---|---|---|
| Adding review pipeline helpers | Tooling and orchestration responsibilities get mixed together | Keep scripts and assets here, but leave routing and judgment with the owning agents |
| Reading sustain_rate trends across the #784 coverage-first prosecution change (dated 2026-07-02) | Coverage-first prosecution reports more low-confidence findings that were previously silently omitted, mechanically lowering sustain_rate even though prosecutor quality is unchanged | Treat sustain-rate readings from before vs. after the coverage-first epoch as non-comparable; do not trigger prosecution-depth auto-tuning on a low-confidence-driven sustain-rate dip. Metric segmentation (sustain-rate by confidence tier) is deferred to umbrella #761. |
04 同仓库更多 Skills
webapp-testing
Playwright end-to-end testing guidance for web apps, with practical patterns and setup steps. Use when creating or improving browser-based E2E coverage, test stability, and CI execution. DO NOT USE FOR: React component tests (use ui-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), or randomized property tests (use property-based-testing).
verification-before-completion
Evidence-based verification checklist before marking work complete. Use before PRs, releases, marking tickets done, or any "I'm finished" declaration; also when naming a baseline commit for a differential suite claim, when designing a mutation campaign or red-run evidence, when making an absence claim, a universal claim, or a one-time demonstration offered as a standing guarantee, when attributing a measurement or claiming a sweep or verification loop is complete, and when stating what a check or a CI suite will do about a change. DO NOT USE FOR: post-merge cleanup or archival (use post-pr-review) or processing GitHub review comments (use code-review-intake).
validation-methodology
Reusable validation and review methodology for staged validation, failure triage, and prosecution-depth setup. Use when running validation ladders, triaging failures, or executing adversarial review passes. DO NOT USE FOR: CE Gate orchestration, specialist dispatch ownership, or step execution flow (keep those in Code-Conductor).
upstream-onboarding
Shared opening-phase protocol for upstream agents (Experience-Owner, Solution-Designer, Issue-Planner) and Code-Conductor when invoked on an existing GitHub issue. Renders a scaled context brief and runs a standards check on inherited work at each phase boundary. Use when a user-invocable agent receives a request referencing an existing GitHub issue and must load solution-authoring and upstream-onboarding at the opening phase. DO NOT USE FOR: subagent dispatches (which already operate within an assessed session context); post-merge review (use post-pr-review); research or non-tree subagents.
ui-testing
Resilient React component testing strategies focusing on user behavior. Use when writing or reviewing component-level React tests, fixing flaky component tests, or establishing React testing patterns. DO NOT USE FOR: Playwright E2E tests (use webapp-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), UI component design (use frontend-design), or randomized property tests (use property-based-testing).
ui-iteration
Reusable screenshot-driven UI polish workflow for iterative visual refinement. Use when improving layout, hierarchy, spacing, feedback, or Tailwind-based presentation through repeated review-and-adjust passes. DO NOT USE FOR: functional bug fixing, accessibility-only audits, or major redesign strategy work (use Code-Smith or frontend-design).