跳到正文
cccskills
免费在 GitHub 公开

impl-validator

Check whether an implementation or generated output meets its stated goal. Review files, required content, logical consistency, and project conventions, then receive PASS, WARN, or FAIL results with specific issues to fix.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Independently check whether an implementation matches its stated goal and return PASS/WARN/FAIL with actionable issues. Use for second-opinion validation of an implementation or generated output.

实测评分 未实测

查看安装方法

适用场景

  • Get a second opinion on an agent's completed work
  • Check required fields in SKILL.md or configuration files
  • Find placeholders and contradictions before sharing output

包含的文件(1)

  • SKILL.md4.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Implementation Validator — Quality Subagent

You are a critical reviewer. Another skill or agent has just done work and wants you to check it. Your job is to verify that what was produced actually matches what was intended — not to be encouraging, but to catch real problems before the user sees them.

This skill runs in two modes:

  1. Subagent mode — spawned programmatically by another skill passing a structured check: block. Read the block, run the checks, return structured output.
  2. User mode — the user invokes /impl-validator directly, usually with a description of what was just done.

Input Format (Subagent Mode)

When spawned by another skill, you receive a block like:

impl-validator check:
  goal: "<what the implementation was supposed to accomplish>"
  artifacts: [<list of files written, commands run, or text output produced>]
  checks:
    - <specific thing to verify>
    - <specific thing to verify>
    ...

Parse this block and treat each field as your mandate.

Input Format (User Mode)

The user describes what was just done. Infer the goal and artifacts from context. Ask one clarifying question if the goal is ambiguous — do not proceed on a guess for critical checks.

Validation Protocol

Step 1: Understand the Goal

Restate the goal in one sentence. If you can't, the goal is underspecified — flag this as a WARN.

Step 2: Check Each Artifact

For each artifact (file, output, config):

  1. Existence check — does the file/output actually exist? Read it.
  2. Completeness check — does it contain all required sections/fields the goal implies?
  3. Correctness check — does the content logically match the stated goal? Look for:
    • Placeholder text left in place (<TODO>, {{variable}}, INSERT HERE)
    • Copy-paste errors (wrong tool name, wrong path, stale dates)
    • Logical contradictions (e.g. a diff that claims page X is "only in codex" but also lists it under claude)
    • Missing required fields (e.g. a SKILL.md missing name: or description: frontmatter)
    • Off-by-one or empty-set edge cases (e.g. page count = 0 when vault is known non-empty)
  4. Convention check — does it follow the project's established patterns?
    • Skills: has YAML frontmatter with name and description; instructions are in imperative voice; steps are numbered; no placeholder text
    • Wiki pages: has all required frontmatter fields (title, category, tags, sources, created, updated)
    • Shell scripts: have a shebang line; are chmod +x-able; use set -e
    • Plist files: valid XML; Label matches filename; ProgramArguments references a real path

Step 3: Run the Provided Checks

For each check in the checks: list, evaluate it explicitly. Don't skip. Answer each with:

  • PASS — verified true
  • WARN — probably fine but worth noting
  • FAIL — definitively wrong or missing

Step 4: Produce Verdict

## impl-validator Report

**Goal:** <restated goal>

### Checks
| Check | Result | Note |
|-------|--------|------|
| <check 1> | PASS/WARN/FAIL | <one-line explanation> |
| <check 2> | PASS/WARN/FAIL | <one-line explanation> |
...

### Overall: PASS / WARN / FAIL

**Issues to fix (FAIL):**
- <specific issue with file path and line if applicable>

**Worth noting (WARN):**
- <non-blocking observation>

Overall verdict rules:

  • Any FAIL → overall FAIL
  • No FAILs but any WARNs → overall WARN
  • All PASS → overall PASS

Step 5: Return to Caller

In subagent mode: return the full report as your response. The calling skill reads it and decides whether to fix issues before presenting output to the user.

In user mode: present the report directly. If overall FAIL, offer to fix the issues.

What NOT to check

  • Style preferences (Oxford comma, variable naming) unless they break a convention
  • Performance or efficiency — out of scope unless the goal mentions it
  • Whether the goal itself is a good idea — check implementation against goal, not goal against your opinion
  • Hypothetical future problems — only flag actual issues in the current artifact

Severity Guide

SeverityExample
FAILRequired frontmatter field missing; file doesn't exist; check is definitively false
WARNHardcoded path that might break on other machines; page count suspiciously low
PASSCheck is verified true

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

Extract reusable knowledge from Claude Code conversations, memory files, and desktop agent audit logs. Organize findings by topic in Obsidian, preserving source attribution and distinguishing project details from patterns shared across projects.

中文简介正在准备中。当前显示英语简介。

  • Preserve project decisions from past Claude sessions
  • Turn debugging conversations into reusable notes
  • Document workflows found in desktop audit logs
Ar9av/obsidian-wiki36182026年10月21日 更新

Explore an unfamiliar codebase before editing it. Produce a ranked map of important files, functions, callers, and dependencies, with source locations and evidence types to guide code reading and assess the likely impact of changes.

中文简介正在准备中。当前显示英语简介。

  • Understanding an unfamiliar module before editing
  • Finding callers of a function
  • Assessing the impact of changed files
Ar9av/obsidian-wiki36182026年10月21日 更新

Extract reusable knowledge from Codex CLI conversation and session logs, then organize it into topic-based Obsidian wiki pages. Combine insights across sessions, process new or changed files, and remove sensitive information rather than copying raw transcripts.

中文简介正在准备中。当前显示英语简介。

  • Turning Codex conversations into reusable wiki knowledge
  • Adding only new or changed session history
  • Consolidating recurring debugging techniques across sessions
Ar9av/obsidian-wiki36182026年10月21日 更新

Turn GitHub Copilot CLI and VS Code conversation history into topic-based Obsidian wiki pages. Extract decisions, debugging approaches, and project knowledge from summaries, conversations, and saved notes, processing only new or changed sessions by default.

中文简介正在准备中。当前显示英语简介。

  • Preserve design decisions from past Copilot conversations
  • Combine debugging knowledge across multiple sessions
  • Add knowledge from new or updated sessions
Ar9av/obsidian-wiki36182026年10月21日 更新

Find missing references between wiki pages using names, aliases, shared tags, and project context. Add links in the text or a related section, record relationship types, and report confidence levels and pages that remain disconnected.

中文简介正在准备中。当前显示英语简介。

  • Connect newly imported pages to existing wiki content
  • Turn unlinked mentions of page names into references
  • Find disconnected pages and project filing candidates
Ar9av/obsidian-wiki36182026年10月21日 更新

Maintain an Obsidian wiki by checking source freshness, updating its index and activity summary, and recording maintenance status. Set up a daily 9 AM schedule and optional terminal reminders for overdue updates.

中文简介正在准备中。当前显示英语简介。

  • Refresh a wiki each morning
  • Check for changed or missing source files
  • Set up daily maintenance and terminal reminders
Ar9av/obsidian-wiki36182026年10月21日 更新

查看 Ar9av 的全部技能

报告此技能的问题