Agent skill

PR Hard Review Report

by TheAceTeam in TheAceTeam/AceHarness

用 rulesregistry 辅助 PR/代码评审:准备 diff(git/PR/编码 agent 上下文)→ L0 扫描 → selectrules 路由 → 四步判定 → rule-issue-reports 上报。

Custom licenceAuto-check passedDevelopment

Install PR Hard Review Report

skills CLI
$ npx skills add TheAceTeam/AceHarness --skill pr-hard-review-report -a claude-code

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

GitHub CLI
$ gh skill install TheAceTeam/AceHarness pr-hard-review-report --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/TheAceTeam/AceHarness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pr-hard-review-report .claude/skills/pr-hard-review-report && 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
pr-hard-review-report
GitHub stars
105
Token cost
~1.4k tokens
SKILL.md length
320 words
Files
140 (incl. scripts)
Skills in repo
8
Repo updated
First seen
Licence
Custom licence

At a glance

用 rulesregistry 辅助 PR/代码评审:准备 diff(git/PR/编码 agent 上下文)→ L0 扫描 → selectrules 路由 → 四步判定 → rule-issue-reports 上报。

  • Works in 3 steps: 编码 agent 上下文(优先) → git 补全(在被 review 仓库根执行) → PR / 已有 diff
  • Tasks that involve Git workflow
  • SKILL.md covers 路径约定(与 IDE 无关), 规则来源, 全流程 and 阶段一:准备, plus 5 more sections
  • Calls python, gh and git

What it does

PR Hard Review Report is an agent skill from TheAceTeam/AceHarness. 用 rulesregistry 辅助 PR/代码评审:准备 diff(git/PR/编码 agent 上下文)→ L0 扫描 → selectrules 路由 → 四步判定 → rule-issue-reports 上报。 适用于 code review、PR 审查、仓颉/Cangjie;可运行于 Cursor / OpenCode / Claude Code 等任意 Agent 环境。

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 141 other files, including scripts (for example `checkpoint_rules.json`, `final-97-rules.md` and `review-examples.md`).

It sits in Development, covering Git workflow. It works with Git.

When your agent uses it

  • Tasks that involve Git workflow

Example prompts

  • “/pr-hard-review-report”

Requirements

  • Python 3

Workflow steps

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

  1. 编码 agent 上下文(优先)
  2. git 补全(在被 review 仓库根执行)
  3. PR / 已有 diff

What it can do on your machine

Read from SKILL.md and the folder at commit 7122bf6. 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

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • gh
    • git
    • curl

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

  • Network

    No URLs in SKILL.md. Its commands use gh, git and curl, 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

PR Hard Review Report loads about 1.4k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 320 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 320 words (~1,381 tokens).

name
pr-hard-review-report

Read the full SKILL.md on GitHub

Files

SKILL.md and 139 other files (scripts) in skills/pr-hard-review-report of TheAceTeam/AceHarness.

  • SKILL.md
  • checkpoint_rules.json
  • final-97-rules.md
  • requirements.txt
  • review-examples.md
  • rules.md
  • rules/cards/function-assertion_precondition-5be8f689e42d.md
  • rules/cards/function-assertion_precondition-ad97b9c2bf7f.md
  • rules/cards/function-boundary_overflow-12952a94e41b.md
  • rules/cards/function-boundary_overflow-1e49af60351d.md
  • rules/cards/function-boundary_overflow-2dbdace8dc27.md
  • rules/cards/function-boundary_overflow-8b1889127f2c.md
  • rules/cards/function-boundary_overflow-e9406d11082a.md
  • rules/cards/function-compiler_internal-4240cf1f14dc.md
  • rules/cards/function-compiler_internal-5889d4737881.md
  • rules/cards/function-compiler_internal-b8bd44a550d9.md
  • rules/cards/function-concurrency-13fe18275149.md
  • rules/cards/function-exception_error-028dfaa2e18b.md
  • rules/cards/function-exception_error-ca2be0ebd46f.md
  • … and 121 more

Open the folder on GitHubat commit 7122bf6

Compare with similar skills

PR Hard Review Report 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.

PR Hard Review Report compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PR Hard Review Report this skillTheAceTeam/AceHarness105—~1.4kAutomated safety check: PassCustom licence
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Migrate Internal Package into GhostTryGhost/Ghost56k—~3.8kAutomated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Git Merge Conflict Resolvertailcallhq/forgecode7.6k1 repos~4.5kAutomated safety check: PassApache-2.0

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.

    56k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Git Merge Conflict Resolver

    tailcallhq/forgecode

    Resolves Git merge conflicts with a plan-first workflow that keeps both sides' intent, regenerates lock files and backs up deleted-but-modified files.

    7.6k GitHub starsUsed in 1 repo~4.5k tokens
    DevelopmentAuto-check passed
  • Git Branch Naming

    makeplane/plane

    Names a new Git branch with a type prefix, the lowercased work item ID and a short kebab-case description, so the ID can be extracted later from the branch name.

    61k GitHub stars~594 tokensUpdated 2 days ago
    DevelopmentAuto-check passed

More from TheAceTeam/AceHarness

All 8 skills in this repo
  • Werewolf Tabletalk

    TheAceTeam/AceHarness

    A skill your agent uses when the user wants AI to play Chinese-style Werewolf, host a Werewolf table, simulate roles such as seer/werewolf/witch/hunter/guard/villager, or produce structured…

    105 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Aceharness Spec Coding

    TheAceTeam/AceHarness

    ACEHarness Spec Coding skill for generating, reviewing, revising, and executing spec-first requirements/design/tasks artifacts tied to workflow steps.

    105 GitHub stars~2.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Aceharness Sqlite

    TheAceTeam/AceHarness

    使用 ACEHarness 运行时提供的 workspace SQLite 能力创建和维护 Skill 数据库. An agent skill from TheAceTeam/AceHarness.

    105 GitHub stars~324 tokensUpdated 1 mo ago
    Auto-check passed
  • Aceharness Workflow Creator

    TheAceTeam/AceHarness

    ACEHarness workflow creation skill. An agent skill from TheAceTeam/AceHarness.

    105 GitHub stars~526 tokensUpdated 1 mo ago
    Auto-check passed
  • Aceharness Chat Card

    TheAceTeam/AceHarness

    通用可视化卡片渲染技能。

    105 GitHub stars~856 tokensUpdated 1 mo ago
    Auto-check passed
  • Aceharness RAG

    TheAceTeam/AceHarness

    使用 ACEHarness 内置 RAG/LanceDB 知识库进行只读检索。

    105 GitHub stars~195 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about PR Hard Review Report

What does PR Hard Review Report do?

用 rulesregistry 辅助 PR/代码评审:准备 diff(git/PR/编码 agent 上下文)→ L0 扫描 → selectrules 路由 → 四步判定 → rule-issue-reports 上报。. PR Hard Review Report is an agent skill from TheAceTeam/AceHarness.

When should I use PR Hard Review Report?

PR Hard Review Report fits situations like: tasks that involve Git workflow.

How do I install PR Hard Review Report in Claude Code?

Run `npx skills add TheAceTeam/AceHarness --skill pr-hard-review-report -a claude-code`. Or copy the skill folder (skills/pr-hard-review-report in TheAceTeam/AceHarness) into .claude/skills/pr-hard-review-report in your project. Claude Code loads it when a task matches its description.

How do I install PR Hard Review Report in Codex?

Run `npx skills add TheAceTeam/AceHarness --skill pr-hard-review-report -a codex`. Or copy the skill folder (skills/pr-hard-review-report in TheAceTeam/AceHarness) into .agents/skills/pr-hard-review-report in your project. Codex loads it when a task matches its description.

Can I use PR Hard Review Report 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 TheAceTeam/AceHarness --skill pr-hard-review-report -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr-hard-review-report, .gemini/skills/pr-hard-review-report, .github/skills/pr-hard-review-report and .opencode/skills/pr-hard-review-report in your project.

What does PR Hard Review Report need to run?

Going by SKILL.md and its folder, PR Hard Review Report needs the command-line tools its instructions call (python, gh, git and curl). Our summary lists: Python 3.

Does PR Hard Review Report access the network?

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

Is PR Hard Review Report 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does PR Hard Review Report use?

PR Hard Review Report has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does PR Hard Review Report use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 PR Hard Review Report?

Skills that share tags, products or a category with PR Hard Review Report: Finishing a Development Branch (obra/superpowers, 297k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars), Migrate Internal Package into Ghost (TryGhost/Ghost, 56k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR Hard Review Report?

TheAceTeam (a GitHub organization) maintains it in TheAceTeam/AceHarness, which has 105 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 3, 2026.

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