New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Verify Goal

by k1ein-chen in k1ein-chen/Harness-Starter

Independently verifies whether a completed task meets its defined goal conditions.

MITAuto-check passed

Install Verify Goal

skills CLI
$ npx skills add k1ein-chen/Harness-Starter --skill verify-goal -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install k1ein-chen/Harness-Starter verify-goal --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/verify-goal .claude/skills/verify-goal && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
verify-goal
GitHub stars
119
Token cost
~502 tokens
SKILL.md length
107 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Independently verifies whether a completed task meets its defined goal conditions.

  • Works in 4 steps: ：获取目标定义 → ：逐条验证 → ：输出验证报告 → …
  • SKILL.md covers 核心理念, 触发条件, 工作流 and 与相关 skill 的关系
  • Calls npm, tsc and git

What it does

Verify Goal is an agent skill from k1ein-chen/Harness-Starter. Independently verifies whether a completed task meets its defined goal conditions. Implements maker/checker separation — the agent that wrote the code does not grade its own work. Use after task execution to validate completion before marking done.

Its SKILL.md is about 500 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with npm. The repository describes itself as: 一套成熟完善的开箱即用的 Claude Code Harness Engineering 模板。三层自动化（安全/感知/审查），集成 LSP、OpenSpec SDD 工作流和 AI 一键初始化。新项目和已有项目均可使用。 The licence is MIT.

Example prompts

  • “/verify-goal”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. ：获取目标定义
  2. ：逐条验证
  3. ：输出验证报告
  4. ：判断下一步

What it can do on your machine

Read from SKILL.md and the folder at commit c211c43. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • tsc
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Verify Goal loads about 502 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 107 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~502

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from k1ein-chen/Harness-Starter at commit c211c43, republished under its MIT licence (© k1ein-chen). 107 words, ~502 tokens.

Download SKILL.mdSave it as .claude/skills/verify-goal/SKILL.md (or your agent's skills folder).
name
verify-goal
description
Independently verifies whether a completed task meets its defined goal conditions. Implements maker/checker separation — the agent that wrote the code does not grade its own work. Use after task execution to validate completion before marking done.

Verify Goal

核心理念

写代码的 Agent 不能给自己打分。

一个任务执行完毕时，所谓的"完成了"只是执行者的声称。verify-goal 作为独立的验证者，以完成条件为基准逐条验证，输出 PASS / FAIL / PARTIAL 结果。

触发条件

在以下场景中必须触发：

  • /goal 循环的每一轮结束后
  • 多步骤任务执行完毕后，声称"完成了"之前
  • 提交 PR 前的最终检查

不触发：

  • 用户只是问问题，不需要执行
  • 简单的文件操作（重命名、移动、删除）

工作流

Step 1：获取目标定义

从以下来源获取完成条件（按优先级）：

  1. 本次任务中用户或 AI 显式定义的完成条件（推荐格式见 CLAUDE.md Goal-Driven Execution）
  2. 对话上下文中可推导的隐含完成条件
  3. 任务本身的性质（如"修 bug" → 定义是"bug 复现步骤不再触发"）
Step 2：逐条验证

对每条完成条件，执行对应的验证命令并记录结果：

条件类型验证方式示例
测试通过运行测试命令npm test -- --testPathPattern=auth
类型检查运行类型检查tsc --noEmit
Lint运行 linternpm run lint
构建运行 buildnpm run build
边界条件检查文件是否被误改git diff --name-only 核对范围
自定义执行用户定义的条件按实际情况
Step 3：输出验证报告

使用以下固定格式输出：

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔎 目标完成验证报告
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

目标：[本次任务的目标描述]

验证结果：✅ 全部通过 / ⚠️ 部分通过 / ❌ 未通过

逐项验证：
  1. [条件 A] ✅ PASS — [命令] → [输出摘要]
  2. [条件 B] ❌ FAIL — [命令] → [失败摘要]
  3. [条件 C] ✅ PASS — [命令] → [输出摘要]

─────────────────────────────────────
[全部通过]
  结论：目标已完成，可进入下一步。

[部分通过 / 未通过]
  失败项：
  - [条件 B] → [失败原因]
  建议：返回执行 Agent 修复后重新验证。
  降级：连续 3 次验证未通过 → 停止循环，汇报给人类。
─────────────────────────────────────
Step 4：判断下一步

根据验证结果决定后续动作：

验证结果后续动作
✅ 全部通过标记完成，更新状态文件，通知主流程继续
⚠️ 部分通过将失败项返回执行 Agent 修复，修复后重新验证
❌ 全部未通过停止循环，汇报给人类
连续 3 次 FAILCircuit Breaker 触发 — 停止循环，等待人类介入

与相关 skill 的关系

tech-review（事前）     verify-goal（事后）      acceptance（终验）
  方案查完了没有？   →   做完了条件满足了没？   →   整个流程走完了没？
  执行前触发           每轮 / 每次任务后触发       项目初始化结束时触发

三者形成完整链条：事前查方案 → 事后验结果 → 终验看全貌。

© k1ein-chen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/verify-goal of k1ein-chen/Harness-Starter.

Open the folder on GitHubat commit c211c43

Compare with similar skills

Verify Goal next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Verify Goal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verify Goal this skillk1ein-chen/Harness-Starter119—~502Automated safety check: PassMIT
Defuddlekepano/obsidian-skills49k11 repos~208Automated safety check: PassMIT
Vercel Deploybytedance/deer-flow84k10 repos~797Automated safety check: PassMIT
Knap Markdown Templateskepano/obsidian-skills49k2 repos~986Automated safety check: PassMIT
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
Nx Run Tasksnomcopter/react-mosaic4.8k8 repos~613Automated safety check: PassCustom licence

Similar skills

  • Defuddle

    kepano/obsidian-skills

    Uses the Defuddle CLI to pull clean, readable Markdown, JSON or metadata from web pages, stripping navigation, ads and clutter to save tokens.

    49k GitHub starsUsed in 11 repos~208 tokens
    Knowledge ManagementAuto-check passed

  • Vercel Deploy

    bytedance/deer-flow

    Deploys a project to Vercel with one script and no login, then returns a live preview URL and a claim link for moving the deployment into your own Vercel account.

    84k GitHub starsUsed in 10 repos~797 tokens
    DevOps & CloudAuto-check passed

  • Knap Markdown Templates

    kepano/obsidian-skills

    Renders Markdown notes from Knap templates and JSON data on the command line, including notes built from Defuddle web page output.

    49k GitHub starsUsed in 2 repos~986 tokens
    Documents & OfficeAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Nx Run Tasks

    nomcopter/react-mosaic

    Helps with running tasks in an Nx workspace. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 8 repos~613 tokens
    DevelopmentAuto-check passed

  • OpenHarness End-to-End Evals

    HKUDS/OpenHarness

    Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.

    16k GitHub starsUsed in 1 repo~2.1k tokens
    Testing & QAAuto-check: notes

More from k1ein-chen/Harness-Starter

  • Harness Init

    k1ein-chen/Harness-Starter

    Initialize this project with the Harness Engineering starter template.

    119 GitHub stars~995 tokensUpdated 16 days ago
    Auto-check: notes

  • Harness Start

    k1ein-chen/Harness-Starter

    Entry point for new users — guides through initialization, architecture review, and cleanup.

    119 GitHub stars~718 tokensUpdated 16 days ago
    Auto-check passed

  • Handover

    k1ein-chen/Harness-Starter

    将当前会话中的技术决策、运维流程或阶段性研发进展，归档为标准工程文档（ADR / SOP / Handover），并自动更新模块内的 README 归档索引。

    119 GitHub stars~752 tokensUpdated 16 days ago
    Auto-check passed

  • Harness Mode

    k1ein-chen/Harness-Starter

    Switch Harness workflow mode (full/hotfix/tweak) and development phase (design/build/fix).

    119 GitHub stars~273 tokensUpdated 16 days ago
    Auto-check: notes

  • Tech Review

    k1ein-chen/Harness-Starter

    Reviews technical decisions before implementation. An agent skill from k1ein-chen/Harness-Starter.

    119 GitHub stars~396 tokensUpdated 16 days ago
    Auto-check passed

  • Harness Gc

    k1ein-chen/Harness-Starter

    Garbage Collection Agent — 定期扫描项目健康状态，检测文档/代码一致性漂移，自动发起修复提案。

    119 GitHub stars~360 tokensUpdated 16 days ago
    Auto-check passed

Works with

Questions about Verify Goal

What does Verify Goal do?

Independently verifies whether a completed task meets its defined goal conditions. Verify Goal is an agent skill from k1ein-chen/Harness-Starter. Independently verifies whether a completed task meets its defined goal conditions.

How do I install Verify Goal in Claude Code?

Run `npx skills add k1ein-chen/Harness-Starter --skill verify-goal -a claude-code`. Or copy the skill folder (.claude/skills/verify-goal in k1ein-chen/Harness-Starter) into .claude/skills/verify-goal in your project. Claude Code loads it when a task matches its description.

How do I install Verify Goal in Codex?

Run `npx skills add k1ein-chen/Harness-Starter --skill verify-goal -a codex`. Or copy the skill folder (.claude/skills/verify-goal in k1ein-chen/Harness-Starter) into .agents/skills/verify-goal in your project. Codex loads it when a task matches its description.

Can I use Verify Goal in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add k1ein-chen/Harness-Starter --skill verify-goal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify-goal, .gemini/skills/verify-goal, .github/skills/verify-goal and .opencode/skills/verify-goal in your project.

What does Verify Goal need to run?

Going by SKILL.md and its folder, Verify Goal needs the command-line tools its instructions call (npm, tsc and git).

Does Verify Goal access the network?

SKILL.md contains no URLs. Its commands use npm and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Verify Goal safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Verify Goal use?

Verify Goal is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verify Goal use?

About 502 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Verify Goal?

Skills that share tags, products or a category with Verify Goal: Defuddle (kepano/obsidian-skills, 49k stars), Vercel Deploy (bytedance/deer-flow, 84k stars), Knap Markdown Templates (kepano/obsidian-skills, 49k stars) and MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify Goal?

k1ein-chen (a GitHub user) maintains it in k1ein-chen/Harness-Starter, which has 119 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 24, 2026.

Source: k1ein-chen/Harness-Starter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.