test-artifact-management

test-artifact-management is a skill for Claude Code, Codex from ccoalm/ccl-skills. It costs 129 tokens per session (7,852 once invoked), scanned A, original, Apache-2.0.

A workflow for turning requirements or code into structured test cases and keeping them in a Feishu Bitable, a shared online table. It supports creating, importing, updating, syncing, and retiring those records.

In plain words
What is it for?
Use it to generate test cases from requirements or code, set up the required table fields, and manage test-case status and lifecycle in Feishu.
Why use it?
It keeps test-case documents organized and connected to their source instead of leaving them scattered or outdated. It also separates written test cases from executable test code and browser tests.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the ccl-skills plugin — 33 skills, 4 commands, 7 hooks shipped together

Good fit Use it to generate test cases from requirements or code, set up the required table fields, and manage test-case status and lifecycle in Feishu.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ccoalm/ccl-skills/test-artifact-management
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ccoalm/ccl-skills --skill test-artifact-management
Clone the repo
git clone --depth 1 https://github.com/ccoalm/ccl-skills

Made for: Claude Code, Codex.

Or install ccl-skills, the plugin that ships this one along with the rest of its 33 skills, 4 commands, 7 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for test-artifact-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccoalm/ccl-skills/test-artifact-management/github.svg)](https://agentmods.dev/skills/ccoalm/ccl-skills/test-artifact-management)
Your own site
<a href="https://agentmods.dev/skills/ccoalm/ccl-skills/test-artifact-management"><img src="https://agentmods.dev/badge/skills/ccoalm/ccl-skills/test-artifact-management/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for test-artifact-management

Your own site · 80×15
<a href="https://agentmods.dev/skills/ccoalm/ccl-skills/test-artifact-management"><img src="https://agentmods.dev/badge/skills/ccoalm/ccl-skills/test-artifact-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,852 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00129 $0.07852
Opus 5 $0.00064 $0.03926
Sonnet 5 $0.00026 $0.01570
Haiku 4.5 $0.00013 $0.00785

Measured 7d ago against content hash 9d40a4f2bb66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

test-artifact-management scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (references/gen_report.py, references/run_pytestless.py, references/tc_helpers/tc.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/test-artifact-management/SKILL.md · 409 lines

How it starts

The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Artifact Management

This skill owns the workflow from source (requirements doc or code) to structured test case design to Feishu Bitable delivery. It routes test layer selection to testing-strategy and Bitable operations to references/bitable-setup.md.

Bitable ownership:

  • This skill owns testcase design and testcase-table delivery: initialize or reuse the Base/table, add missing canonical fields, and create, import, update, sync, or deprecate testcase records.
  • Use lark-base for concrete Base operations and references/bitable-setup.md as the canonical schema and safe write path. An existing .feishu/project.yaml may provide reusable identifiers, but it is optional and must not trigger creation of unrelated Wiki/Base infrastructure.

Skill Routing

  • Ambiguous "写测试用例" / "write test cases" requests mean testing-strategy first when the user wants test code, E2E/browser/device tests, CI coverage, mocks, or verification evidence. Use this skill only when the deliverable is a structured TC artifact, Feishu/Bitable sync, or source-to-TC generation workflow.
  • Use testing-strategy to decide which test layers (unit / integration / E2E / scenario) are needed after the use cases are written.
  • Test-code implementation, once test cases are approved, must go to the owning stack skill: go-microservice-dev / python-service-dev / nodejs-service-dev / web-react-dev / miniapp-product-dev / app-cross-platform-dev.
  • Use product-rd-workflow when the test case work is part of a broader feature delivery plan.
  • Use llm-inference-integration when test cases cover LLM / agent / RAG / inference behavior.
  • Use skill-extraction-workflow to feed lessons from test case generation or Feishu Bitable setup back into this skill after each delivery cycle.

Scope: one config per deployable unit

A deployable unit is anything that ships with its own release cadence and owner: a web frontend, a mini-program, an app, an admin/运营后台 frontend, one backend service. TC management is scoped per unit — not per repo.

Read the full file on GitHub · 409 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago Changed 9d40a4f2bb66
  2. 11d ago First seen · 409 lines · 129 tokens per session scan A 7a814183111d

Subscribe to this mod's changes

test-artifact-management is a skill published in the GitHub repository ccoalm/ccl-skills (6 stars, last pushed today), licensed Apache-2.0. It adds 129 tokens to every session and 7,852 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories