跳到正文
cccskills
免费在 GitHub 公开

artifact-contract-auditor

Audit one research Workspace for declared Unit outputs and Pipeline target Artifacts, writing `output/CONTRACT_REPORT.md`; use for mid-Run coverage snapshots or final delivery completeness, not deep provenance integrity.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(2)

  • SKILL.md3.6 KB
  • scripts/run.py8.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Artifact Contract Auditor

This Skill measures coverage: whether files promised by Units and the locked Pipeline exist at the point they are required. It does not replace the deeper Attempt, Manifest, Artifact-hash, and ledger checks in pipeline.py audit.

Inputs

  • UNITS.csv.
  • PIPELINE.lock.md.
  • The locked pipelines/*.pipeline.md target-Artifact contract.

Outputs

  • output/CONTRACT_REPORT.md.

Steps

1. Resolve the active contracts

Read PIPELINE.lock.md, resolve the Pipeline inside this repository, and parse UNITS.csv. Treat an invalid lock or malformed Unit table as a reportable contract failure rather than guessing another Workflow.

Completion criterion: one Pipeline contract and one readable Unit table are bound to the audit.

2. Check completed Unit outputs

For every DONE Unit, verify each required output exists. Outputs prefixed with ? are optional. A missing required output is Unit-level contract drift even when the Pipeline is still running.

Completion criterion: every DONE Unit is classified as output-complete or is listed with each missing required path.

3. Check final Pipeline targets when applicable

Determine whether all Units are terminal (DONE or SKIP). Only then require every non-optional target Artifact declared by the Pipeline. During a partial Run, report missing final targets as expected rather than failures.

Completion criterion: final-target completeness is evaluated against the actual Run phase, not merely file absence.

4. Write the report

Always write output/CONTRACT_REPORT.md with one status:

  • PASS: terminal Run, complete Unit outputs, complete Pipeline targets.
  • OK: partial Run, consistent completed Unit outputs.
  • FAIL: missing output from a DONE Unit, or missing final target from a terminal Run.

Completion criterion: the report names the evaluated Pipeline, Run phase, status, and every blocking missing path.

5. Route the next action

For missing Unit outputs, reopen or rerun the owning Unit through the Pipeline adapter. For missing final targets, identify the owning Unit or Skill. When file coverage passes, use scripts/pipeline.py audit for provenance integrity.

Completion criterion: every FAIL item has an owner and repair route; a PASS claim is explicitly limited to declared file coverage.

Context Pointers

  • The locked Pipeline front matter is the only source for target Artifacts.
  • UNITS.csv is the only source for Unit output obligations.
  • Use the deep Run Audit for Attempt pairing, Manifest identity, hashes, Decisions, Failures, and Evaluation consistency.

Script

Quick Start

uv run python .codex/skills/artifact-contract-auditor/scripts/run.py \
  --workspace workspaces/<name>

All Options

  • --workspace <path>: Workspace to audit.
  • --unit-id <U###>, --inputs, --outputs, --checkpoint: optional Pipeline-runner compatibility arguments.

Examples

Inspect the interface:

uv run python .codex/skills/artifact-contract-auditor/scripts/run.py --help

Run the deeper provenance audit after coverage passes:

uv run python scripts/pipeline.py audit --workspace workspaces/<name>

Side Effects

The audit may create or replace output/CONTRACT_REPORT.md. It must not edit research content, Unit statuses, checkpoint approvals, or source Artifacts.

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

Internal template for creating or refactoring a skill into the repository's reference-first shape. **Trigger**: reference-first template, blueprint skill, create a reusable skill, refactor a script-heavy skill. **Use when**: you need a lean `SKILL.md`, explicit `references/`, machine-readable `assets/`, and a minimal deterministic `run.py`.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of generic summaries.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

Build a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

Retrieve arXiv paper metadata with keyword queries or import an offline arXiv export, and save results as JSONL (`papers/papers_raw.jsonl`).

中文简介正在准备中。当前显示原文说明。

WILLOSCAR/research-units-pipeline-skills5152026年10月5日 更新

查看 WILLOSCAR 的全部技能

报告此技能的问题