跳到正文
cccskills
免费在 GitHub 公开

cc-scorecard

Evaluate deliverable quality — scorecard, outcome tracking, regression checklist, and aggregate stats.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

scorecard

Invoke as $cc-scorecard. The user request follows the skill mention.

Scorecard Evaluation Workflow

Scope: $ARGUMENTS


Step 0 — CCEP Bootstrap

Command: scorecard (fixed for this workflow — do not infer from user text)

  1. Run: npx cc-codeconductor ccep profile scorecard --output json to get the phases and their roles.
  2. For each delegated phase, run: npx cc-codeconductor ccep compile --command scorecard --phase <phase-id> "$ARGUMENTS" --view prompt --output json
  3. After planner/intake JSON is available, run: npx cc-codeconductor ccep evaluate --command scorecard --input <planner.json> --output json. If stop is true, show questions or risks and wait for human input.
  4. Pass each subagent only the compiled prompt for its phase — never forward raw $ARGUMENTS to planners.

Step 1 — Identify task

Use $ARGUMENTS as task id (e.g. BC-001) or read active item from npx cc-codeconductor openspec status.

If a change folder exists, run npx cc-codeconductor openspec analyze --output json first. --from-diff overlays FR/SC coverage onto acceptance and TDD evidence onto tests.


Step 2 — Create scorecard with auto-signals

npx cc-codeconductor scorecard create --task <id> --agent reviewer --from-diff

Review auto-suggested criteria (minimal diff, cc-gain). Complete remaining scores 0–3 per docs/agent-scorecard.md.


Step 3 — Regression (optional)

npx cc-codeconductor scorecard regression

If required checks fail, STOP and report failures.


Step 4 — Record outcome

npx cc-codeconductor scorecard record --task <id> --agent reviewer --model <model> --verdict PASS --score 2.5

Include --cost and --tokens when available from session metrics.


Step 5 — Aggregate

npx cc-codeconductor scorecard aggregate

Report pass rate and average weighted score.


Routing on verdict

  • PASS — accept deliverable; update backlog if applicable
  • REVISE — return to implementer/tester with findings
  • REJECT — route to task-coach for re-scoping

Apply skill evaluation.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when adding monitoring, metrics, logging, or tracing to Spring AI or LLM integration code. Covers token tracking, latency measurement, cost estimation, and prompt/response logging. Use when user mentions AI monitoring, token costs, or LLM observability.

中文简介正在准备中。当前显示原文说明。

lgzarturo/springboot-course32026年10月20日 更新

android

免费

Provides expert knowledge for building modern native Android apps using Kotlin, Jetpack Compose, Material Design 3, MVI architecture, Hilt dependency injection, and Media3/ExoPlayer.

中文简介正在准备中。当前显示原文说明。

lgzarturo/springboot-course32026年10月20日 更新

Design, implement, review, and audit Android Jetpack Compose UI/UX for phone interfaces. Use when a request concerns concrete Compose layout, components, interaction, accessibility, or visual behavior. Do not activate for framework or dependency presence alone; non-UI Android work is excluded.

中文简介正在准备中。当前显示原文说明。

lgzarturo/springboot-course32026年10月20日 更新

Provides expert knowledge for designing, implementing, and managing REST API versioning strategies with deprecation workflows.

中文简介正在准备中。当前显示原文说明。

lgzarturo/springboot-course32026年10月20日 更新

astro

免费

Provides expert knowledge for building Astro 5+ sites with Islands Architecture, Content Collections, TypeScript, and performance-first rendering strategies.

中文简介正在准备中。当前显示原文说明。

lgzarturo/springboot-course32026年10月20日 更新

Audits token storage mechanisms to prevent XSS-based JWT theft.

中文简介正在准备中。当前显示原文说明。

lgzarturo/springboot-course32026年10月20日 更新

查看 lgzarturo 的全部技能

报告此技能的问题