Agent skill

Tech Review

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

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

MITAuto-check passed

Install Tech Review

skills CLI
$ npx skills add k1ein-chen/Harness-Starter --skill tech-review -a claude-code

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

GitHub CLI
$ gh skill install k1ein-chen/Harness-Starter tech-review --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/tech-review .claude/skills/tech-review && 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
tech-review
GitHub stars
119
Token cost
~396 tokens
SKILL.md length
60 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 4 steps: :提取技术决策 → :搜索验证 → :输出审查报告 → …
  • The user asks to implement something using a specific tool
  • SKILL.md covers 核心理念, 触发条件, 工作流 and 说明
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Tech Review is an agent skill from k1ein-chen/Harness-Starter. Reviews technical decisions before implementation. Detects outdated or suboptimal approaches by searching current best practices. Use when the user asks to implement something using a specific tool, library, or methodology.

Its SKILL.md is about 400 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

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.

When your agent uses it

  • The user asks to implement something using a specific tool

Example prompts

  • “Use the tech-review skill to review technical decisions before implementation. An agent skill from k1ein-chen/Harness-Starter”
  • “/tech-review”

Workflow steps

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

  1. :提取技术决策
  2. :搜索验证
  3. :输出审查报告
  4. :等待选择

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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Tech Review loads about 396 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 60 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~396

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). 60 words, ~396 tokens.

Download SKILL.mdSave it as .claude/skills/tech-review/SKILL.md (or your agent's skills folder).
name
tech-review
description
Reviews technical decisions before implementation. Detects outdated or suboptimal approaches by searching current best practices. Use when the user asks to implement something using a specific tool, library, or methodology.

Tech Review

核心理念

用户因为信息差给出了过时或不优的技术方案时,AI 有责任在执行前发现并告知。

这不是"违抗用户指令"——不执行是违抗,发现更好的方案并告知是专业化。

触发条件

必须触发:用户指令中包含"用 [X] 做 [Y]"结构的技术实现请求。X 是一个工具/库/框架/方法论,Y 是一个目标。这种结构意味着用户已经做了技术选型,这个选型需要被验证。

不触发的典型场景:

  • 纯业务逻辑("写个登录接口"——不指定具体工具)
  • 纯 debug("修一下这个 bug")
  • 纯配置变更("把端口改成 3000")
  • 用户明确说"按我说的做,不用查"
  • 你 100% 确定该方案仍是当前最佳做法

不确定要不要触发?宁查勿漏。多一次搜索远比让用户走弯路划算。

工作流

Step 1:提取技术决策

识别用户指令中所有"用 X 做 Y"性质的技术决策。可能不止一项。

Step 2:搜索验证

对提取出的每一项技术决策,执行 web search。搜索词不限以下示例,根据实际情况组织:

[X] alternative
[X] vs [已知替代方案]
[X] deprecated
[场景描述] best practice

每次审查至少搜索一次。即使你认为自己的知识是准确的,也搜索确认——因为你不知道你的训练数据截止到什么时候。

Step 3:输出审查报告

使用以下固定格式输出结果:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔍 技术方案审查
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

审查结果:[ ✅ 方案可行 / ⚠️ 有更好的选择 / ❌ 方案不推荐 ]

涉及的技术决策:
  1. [选型 A] → [结论,附搜索来源概要]
  2. [选型 B] → [结论,附搜索来源概要]

[审查结果为 ✅]
  当前方案仍是最佳做法,按原计划执行。

[审查结果为 ⚠️ 或 ❌]
替代建议:
  - 方案一:[名称] — [简要说明]
  - 方案二:[名称] — [简要说明]

─────────────────────────────────────
请选择:A) 按原方案继续  B) 改用建议方案  C) 我自己调整
─────────────────────────────────────
Step 4:等待选择
  • A — 尊重用户意愿,按原方案执行,不再质疑
  • B — 替换为建议方案,继续执行
  • C — 用户修改需求后重新来过
  • 用户不回复 — 不继续执行

说明

  • 这个 Skill 的价值不在于"AI 替用户做决定",而在于消除信息差
  • web search 会产生费用,但这是为了换取正确性
  • 如果同一领域的同类决策已在本次对话中审查过,可以跳过重复搜索

© 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/tech-review of k1ein-chen/Harness-Starter.

Open the folder on GitHubat commit c211c43

Compare with similar skills

Tech Review 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.

Tech Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tech Review this skillk1ein-chen/Harness-Starter119—~396Automated safety check: PassMIT
Tech Stack Detectivetinyfish-io/tinyfish-cookbook2.2k—~2.2kAutomated safety check: PassMIT
Threat Detectionalirezarezvani/claude-skills28k—~3.5kAutomated safety check: PassMIT
Resemble Detectgithub/awesome-copilot40k3 repos~4.1kAutomated safety check: PassApache-2.0
Pii Detectruvnet/ruflo74k—~350Automated safety check: NotesMIT
Detecting Dnp3 Protocol Anomaliesmukul975/Anthropic-Cybersecurity-Skills34k—~3.6kAutomated safety check: PassApache-2.0

Similar skills

  • Tech Stack Detective

    tinyfish-io/tinyfish-cookbook

    Reverse-engineer a company's tech stack from public signals — job listings, StackShare, GitHub, engineering blog, and their live website.

    2.2k GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • Threat Detection

    alirezarezvani/claude-skills

    A skill your agent uses when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry.

    28k GitHub stars~3.5k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Resemble Detect

    github/awesome-copilot

    Official

    Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using…

    40k GitHub starsUsed in 3 repos~4.1k tokens
    Media & CreativeAuto-check passed
  • Pii Detect

    ruvnet/ruflo

    Detect and flag personally identifiable information (PII) in text, code, and configurations.

    74k GitHub stars~350 tokensUpdated today
    Auto-check: notes
  • Detecting Dnp3 Protocol Anomalies

    mukul975/Anthropic-Cybersecurity-Skills

    Detect anomalies in DNP3 communications used in SCADA/ICS systems by monitoring unauthorized control commands, firmware update attempts, protocol violations, and deviations from baseline traffic…

    34k GitHub stars~3.6k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed
  • Detecting Attacks On Scada Systems

    mukul975/Anthropic-Cybersecurity-Skills

    This skill covers detecting cyber attacks targeting Supervisory Control and Data Acquisition (SCADA) systems including man-in-the-middle attacks on industrial protocols, unauthorized command…

    34k GitHub stars~6.9k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed

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
  • Verify Goal

    k1ein-chen/Harness-Starter

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

    119 GitHub stars~502 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

Questions about Tech Review

What does Tech Review do?

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

When should I use Tech Review?

Tech Review fits situations like: the user asks to implement something using a specific tool.

How do I install Tech Review in Claude Code?

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

How do I install Tech Review in Codex?

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

Can I use Tech Review 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 tech-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tech-review, .gemini/skills/tech-review, .github/skills/tech-review and .opencode/skills/tech-review in your project.

What does Tech Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Tech Review is instructions for the agent only.

Does Tech Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Tech Review 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 Tech Review use?

Tech Review 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 Tech Review use?

About 396 tokens (SKILL.md is roughly 1.6k 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 Tech Review?

Skills that share tags, products or a category with Tech Review: Tech Stack Detective (tinyfish-io/tinyfish-cookbook, 2.2k stars), Threat Detection (alirezarezvani/claude-skills, 28k stars), Resemble Detect (github/awesome-copilot, 40k stars) and Pii Detect (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tech Review?

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.