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

Junshi Fazheng

by aruis in aruis/codex-cookbook

Use only when junshi is already active in the current thread and 法正 has been explicitly delegated by junshi; never trigger from a direct end-user request alone.

MITAuto-check passed

Install Junshi Fazheng

skills CLI
$ npx skills add aruis/codex-cookbook --skill junshi-fazheng -a claude-code

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

GitHub CLI
$ gh skill install aruis/codex-cookbook junshi-fazheng --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/aruis/codex-cookbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/junshi-fazheng .claude/skills/junshi-fazheng && 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
junshi-fazheng
GitHub stars
165
Token cost
~623 tokens
SKILL.md length
308 words
Files
2
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Use only when junshi is already active in the current thread and 法正 has been explicitly delegated by junshi; never trigger from a direct end-user request alone.

  • Works in 4 steps: review and validation closure → test execution when assigned → submit-readiness judgment → …
  • From a direct end-user request alone
  • SKILL.md covers Role, Default Work, Style and Output Shape, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Junshi Fazheng is an agent skill from aruis/codex-cookbook. Use only when junshi is already active in the current thread and 法正 has been explicitly delegated by junshi; never trigger from a direct end-user request alone. 法正 is the single-seat review, test, submit-readiness, and commit-handling role in the junshi system.

Its SKILL.md is about 620 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: Codex prompt cookbook and collaboration templates. The licence is MIT.

When your agent uses it

  • From a direct end-user request alone

Example prompts

  • “/junshi-fazheng”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. review and validation closure
  2. test execution when assigned
  3. submit-readiness judgment
  4. commit-side handling only when explicitly assigned by 军师

What it can do on your machine

Read from SKILL.md and the folder at commit 0d1e8b3. 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

Junshi Fazheng loads about 623 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 308 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~623

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 aruis/codex-cookbook at commit 0d1e8b3, republished under its MIT licence (© aruis). 308 words, ~623 tokens.

Download SKILL.mdSave it as .claude/skills/junshi-fazheng/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
junshi-fazheng
description
Use only when junshi is already active in the current thread and 法正 has been explicitly delegated by junshi; never trigger from a direct end-user request alone. 法正 is the single-seat review, test, submit-readiness, and commit-handling role in the junshi system.

军师法正

Use this skill when the assigned role is 法正.

Role

You are not the lead agent. You are 法正 serving 军师.

Your job is to help 军师 converge work cleanly through review, validation closure, test execution, submit-readiness checks, and commit-side handling when assigned.

法正 is a single-seat role. Do not treat it like a pool, and do not run parallel 法正 work on the same task line.

Default priority order:

  1. review and validation closure
  2. test execution when assigned
  3. submit-readiness judgment
  4. commit-side handling only when explicitly assigned by 军师

Default Work

Focus on work such as:

  • review of current changes
  • acceptance-scope checks
  • checklist cleanup
  • test execution or verification closure
  • submit-readiness checks
  • commit-side handling when 军师 assigns it

commit-side handling may include:

  • preparing commit readiness
  • staging or commit execution when explicitly assigned
  • reporting commit outcome back to 军师

commit-side handling does not imply:

  • automatic push
  • PR creation
  • taking over unrelated release actions

Prefer answering:

  • whether the work stayed within the approved boundary
  • whether known leftovers are explicit
  • whether validation is sufficient
  • whether the work is ready to converge
  • whether test or commit-side handling completed cleanly

Style

  • review for signal, not ceremony
  • be concise and concrete
  • distinguish must-fix from optional polish
  • prefer bounded findings over broad commentary

Output Shape

Default output should usually contain:

  • review or execution scope checked
  • validation or test result
  • leftovers or unresolved items
  • submit-readiness or commit-handling result

Do Not

  • do not become the main implementer
  • do not silently redefine planning direction
  • do not run multiple 法正 threads in parallel for the same task
  • do not silently expand commit-side handling into push, release, or unrelated repository actions
  • do not demand perfection before every convergence point

Escalation

If technical facts are missing for a fair review or a safe commit-side action, explicitly ask 军师 to supplement with a 武将 validation pass instead of guessing.

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

Files

SKILL.md and 1 other file in skills/junshi-fazheng of aruis/codex-cookbook.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 0d1e8b3

Compare with similar skills

Junshi Fazheng 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.

Junshi Fazheng compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Junshi Fazheng this skillaruis/codex-cookbook165—~623Automated safety check: PassMIT
Modeling Activation MetricsPostHog/posthog40k—~1.4kAutomated safety check: PassCustom licence
Turn This Into A Threadsickn33/agentic-awesome-skills47k1 repos~1.4kAutomated safety check: PassMIT
Summarize Activityalpinejs/alpine32k—~1.6kAutomated safety check: NotesMIT
Duplicate Id Activethedaviddias/Front-End-Checklist74k—~440Automated safety check: PassMIT
Puzzle Activity Plannersickn33/agentic-awesome-skills47k1 repos~790Automated safety check: PassMIT

Similar skills

  • Modeling Activation Metrics

    PostHog/posthog

    Official

    Build reusable activation models — an activation-rate metric and a per-user/per-account activated flag — on either PostHog data-warehouse views (HogQL) or an external dbt project.

    40k GitHub stars~1.4k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

  • Turn This Into A Thread

    sickn33/agentic-awesome-skills

    Turn a long idea, transcript, article or draft into a Twitter/X thread where every tweet stands alone.

    47k GitHub starsUsed in 1 repo~1.4k tokens
    Writing & ContentAuto-check passed

  • Summarize Activity

    alpinejs/alpine

    Summarize recent GitHub activity — discussions, PRs, issues, events, traffic — into an actionable report so you can stay on top of the project without reading everything.

    32k GitHub stars~1.6k tokensUpdated 6 days ago
    Backend & APIsAuto-check: notes

  • Duplicate Id Active

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Use unique IDs for active elements.

    74k GitHub stars~440 tokensUpdated 5 days ago
    Frontend & DesignAuto-check passed

  • Puzzle Activity Planner

    sickn33/agentic-awesome-skills

    Plan puzzle-based activities for classrooms, parties, and events with pre-configured generator links

    47k GitHub starsUsed in 1 repo~790 tokens
    Auto-check passed

  • Adding Activity Logging

    PostHog/posthog

    Official

    Adds or changes activity logging (the audit trail) for a Django model in PostHog.

    40k GitHub stars~1.5k tokensUpdated yesterday
    Backend & APIsAuto-check passed

More from aruis/codex-cookbook

  • Junshi

    aruis/codex-cookbook

    Use only when the user explicitly enters 军师 mode, such as saying “召唤军师”, “军师跟进”, or “让军师看一下”, and keep using it for later turns in the same thread until the user explicitly exits 军师 mode or 军师…

    165 GitHub stars~1.3k tokensUpdated 5 mo ago
    Auto-check passed

  • Junshi Moushi

    aruis/codex-cookbook

    Use only when junshi is already active in the current thread and this role has been explicitly delegated by junshi; never trigger from a direct end-user request alone.

    165 GitHub stars~469 tokensUpdated 5 mo ago
    Auto-check passed

  • Junshi Wujiang

    aruis/codex-cookbook

    Use only when junshi is already active in the current thread and this role has been explicitly delegated by junshi; never trigger from a direct end-user request alone.

    165 GitHub stars~422 tokensUpdated 5 mo ago
    Auto-check passed

Questions about Junshi Fazheng

What does Junshi Fazheng do?

Use only when junshi is already active in the current thread and 法正 has been explicitly delegated by junshi; never trigger from a direct end-user request alone. Junshi Fazheng is an agent skill from aruis/codex-cookbook. Use only when junshi is already active in the current thread and 法正 has been explicitly delegated by junshi; never trigger from a direct end-user request alone.

When should I use Junshi Fazheng?

Junshi Fazheng fits situations like: from a direct end-user request alone.

How do I install Junshi Fazheng in Claude Code?

Run `npx skills add aruis/codex-cookbook --skill junshi-fazheng -a claude-code`. Or copy the skill folder (skills/junshi-fazheng in aruis/codex-cookbook) into .claude/skills/junshi-fazheng in your project. Claude Code loads it when a task matches its description.

How do I install Junshi Fazheng in Codex?

Run `npx skills add aruis/codex-cookbook --skill junshi-fazheng -a codex`. Or copy the skill folder (skills/junshi-fazheng in aruis/codex-cookbook) into .agents/skills/junshi-fazheng in your project. Codex loads it when a task matches its description.

Can I use Junshi Fazheng 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 aruis/codex-cookbook --skill junshi-fazheng -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/junshi-fazheng, .gemini/skills/junshi-fazheng, .github/skills/junshi-fazheng and .opencode/skills/junshi-fazheng in your project.

What does Junshi Fazheng need to run?

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

Does Junshi Fazheng 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 Junshi Fazheng 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 Junshi Fazheng use?

Junshi Fazheng 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 Junshi Fazheng use?

About 623 tokens (SKILL.md is roughly 2.5k 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 Junshi Fazheng?

Skills that share tags, products or a category with Junshi Fazheng: Modeling Activation Metrics (PostHog/posthog, 40k stars), Turn This Into A Thread (sickn33/agentic-awesome-skills, 47k stars), Summarize Activity (alpinejs/alpine, 32k stars) and Duplicate Id Active (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Junshi Fazheng?

aruis (a GitHub user) maintains it in aruis/codex-cookbook, which has 165 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on April 25, 2026.

Source: aruis/codex-cookbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.