跳到正文
cccskills
免费在 GitHub 公开

worker-validation

Validates code fixes by running the code, checking compilation, verifying runtime behavior, and confirming fixes resolve the reported issue. Use when verifying that bug fixes actually work at runtime.

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.md3.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Worker Validator

Validates that code fixes are correct by running the code, checking compilation, verifying runtime behavior, and confirming the reported issue is resolved.

Instructions

1. Identify the Problem

From the bug report or issue description, determine:

  • What was broken (e.g., "files not found", "TypeError: not a function")
  • What the expected behavior should be
  • What the minimal reproduction is

2. Apply the Fix

Make the proposed changes to the affected files.

3. Verify Runtime Behavior

Run the code and check that the fix works:

# Run the entry point or test
node path/to/entry.ts
# or
ts-node path/to/entry.ts
# or
npx pi [command]

Check:

  • Exit code is 0 (no unhandled errors)
  • Expected output is produced
  • No new errors appear in stderr

4. Verify Data Integrity

For data-processing fixes, verify the data is correct:

# Check files exist and are readable
ls -la .pi/consolidations/

# Verify path resolution
node -e "const p = require('path'); console.log(p.isAbsolute(p.join('/base', 'file')))"

# Parse and inspect data
node -e "const data = JSON.parse(require('fs').readFileSync('file.json', 'utf-8')); console.log(Object.keys(data))"

Verify:

  • All expected files are found
  • Paths are absolute (where expected)
  • Data parses successfully
  • Key data fields are present and correct

5. Check Compilation

If the project uses TypeScript or another compile-time language:

# Check for compilation errors
npx tsc --noEmit
# or
npx tsc

Note: Not all projects have tsc installed. Some run via an agent's internal runtime. Check if compilation is applicable.

6. Verify Specific Claims

For each claim in the fix description, verify independently:

# Claim: "export function createSession exists"
grep "export function createSession" file.ts && echo "[PASS]" || echo "[FAIL]"

# Claim: "6 files found in directory"
ls directory/ | wc -l

# Claim: "Latest file parses successfully"
node -e "require('fs').readFileSync('latest-file.json', 'utf-8')" && echo "[PASS]" || echo "[FAIL]"

7. Check for Remaining Concerns

After the fix is verified, note any remaining issues:

  • Stub files or incomplete refactoring
  • Functions that still need implementation
  • Known limitations or TODOs
  • Future work that depends on this fix

8. Report Findings

Structure the validation report as:

## Fixes Applied

### Fix N: [Description]
**Files changed**: `[path/to/file]`

**Problem**: [Brief description of what was broken]

**Fix**: [What was changed]

**Verification**:
- [PASS] [Verification step 1]
- [PASS] [Verification step 2]
- [PASS] Exit code: 0

## [Compilation/Type Checking]
**Status**: [Pass/Fail/Not applicable] -- [Explanation]

## Remaining Concerns
- [Concern 1]
- [Concern 2]

## Summary
[What the fix enables, what still needs work]

Use status symbols:

  • [PASS] -- Verified working
  • [FAIL] -- Verification failed
  • [INFO] -- Not applicable or informational

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

Distills enduring architectural decisions and design rationale from wave orchestration plans or historical git changes into structured, tracked Architecture Decision Records (ADRs). Use pre-wave to resolve active architectural constraints or post-wave to record enduring decisions in docs/decisions/.

中文简介正在准备中。当前显示原文说明。

AndrewBrown-USDA/aigb-skills-usda72026年10月22日 更新

Create and maintain AGENTS.md files for project onboarding and grounding. Use when initialized in a new project, when project structure changes significantly, or when creating subfolder-level AGENTS.md files for complex monorepos.

中文简介正在准备中。当前显示原文说明。

AndrewBrown-USDA/aigb-skills-usda72026年10月22日 更新

Audit and update an arbitrary codebase to follow the Code.mil federal open-source licensing model (MIT with 17 U.S.C. Section 105 disclaimers and INTENT.md), including CRAN/R package DESCRIPTION setup.

中文简介正在准备中。当前显示原文说明。

AndrewBrown-USDA/aigb-skills-usda72026年10月22日 更新

Migrates ArcPy and ArcGIS Pro workflows to explicit, testable open-source Python geospatial workflows. Use when removing ArcPy dependencies, porting geoprocessing scripts, or documenting ArcGIS behavior that will not be migrated.

中文简介正在准备中。当前显示原文说明。

AndrewBrown-USDA/aigb-skills-usda72026年10月22日 更新

caveman

免费

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

中文简介正在准备中。当前显示原文说明。

AndrewBrown-USDA/aigb-skills-usda72026年10月22日 更新

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes - Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

中文简介正在准备中。当前显示原文说明。

AndrewBrown-USDA/aigb-skills-usda72026年10月22日 更新

查看 AndrewBrown-USDA 的全部技能

报告此技能的问题