Shepherd PRs
flutter/flutter
Automate shepherding, checking status, updating branches, and landing open PRs or approved third-party contributor PRs in the flutter/flutter repository using the gh CLI.
Default Looper review method for implementation and spec PRs.
MITAuto-check passed
Install Looper Review
$ npx skills add nexu-io/looper --skill looper-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nexu-io/looper looper-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nexu-io/looper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/internal/reviewer/reviewskills/builtin .claude/skills/looper-review && rm -rf skills-srcUse ~/.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/
Install the "looper-review" agent skill from https://github.com/nexu-io/looper/tree/main/internal/reviewer/reviewskills/builtin into .claude/skills/looper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looper-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nexu-io/looper/tree/main/internal/reviewer/reviewskills/builtinType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nexu-io/looper --skill looper-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nexu-io/looper looper-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nexu-io/looper.git skills-src && mkdir -p .agents/skills && cp -r skills-src/internal/reviewer/reviewskills/builtin .agents/skills/looper-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "looper-review" agent skill from https://github.com/nexu-io/looper/tree/main/internal/reviewer/reviewskills/builtin into .agents/skills/looper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looper-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nexu-io/looper --skill looper-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nexu-io/looper looper-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nexu-io/looper.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/internal/reviewer/reviewskills/builtin .cursor/skills/looper-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "looper-review" agent skill from https://github.com/nexu-io/looper/tree/main/internal/reviewer/reviewskills/builtin into .cursor/skills/looper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looper-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nexu-io/looper.git --path internal/reviewer/reviewskills/builtin--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nexu-io/looper --skill looper-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nexu-io/looper looper-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nexu-io/looper.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/internal/reviewer/reviewskills/builtin .gemini/skills/looper-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "looper-review" agent skill from https://github.com/nexu-io/looper/tree/main/internal/reviewer/reviewskills/builtin into .gemini/skills/looper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looper-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nexu-io/looper looper-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nexu-io/looper --skill looper-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nexu-io/looper.git skills-src && mkdir -p .github/skills && cp -r skills-src/internal/reviewer/reviewskills/builtin .github/skills/looper-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "looper-review" agent skill from https://github.com/nexu-io/looper/tree/main/internal/reviewer/reviewskills/builtin into .github/skills/looper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looper-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nexu-io/looper --skill looper-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nexu-io/looper looper-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nexu-io/looper.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/internal/reviewer/reviewskills/builtin .opencode/skills/looper-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "looper-review" agent skill from https://github.com/nexu-io/looper/tree/main/internal/reviewer/reviewskills/builtin into .opencode/skills/looper-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looper-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
looper-review- GitHub stars
- 133
- Token cost
- ~722 tokens
- SKILL.md length
- 346 words
- Files
- 6 (incl. references)
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Default Looper review method for implementation and spec PRs.
- Works in 7 steps: Understand stated intent from the PR… → Enumerate in-scope changed files/ranges… → Read the surrounding context needed to… → …
- SKILL.md covers Procedure and References
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Looper Review is an agent skill from nexu-io/looper. Default Looper review method for implementation and spec PRs. Read before reviewing. Covers correctness, tests, concurrency, contracts, and comment quality.
Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/comment-quality.md`, `references/css-lint.md` and `references/evidence.md`).
The repository describes itself as: 🔁 Run AI coding agents as an autonomous dev team across all your GitHub repos — plan, review, fix, and ship, on a loop. The licence is MIT.
Example prompts
- “/looper-review”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Understand stated intent from the PR seed, title/body, linked spec, and stated goals/non-goals.
- Enumerate in-scope changed files/ranges with local Git at the seeded base/head SHAs. Do not shrink that set because a specialty skill…
- Read the surrounding context needed to judge each change (callers, tests, contracts, lifecycle).
- For large PRs (roughly ≥15 changed files, or changes that cross packages), write an internal related-file plan grouping…
- Establish concrete evidence for each independent in-scope finding: implementation trigger → code path → wrong consequence, or spec/docs…
- Run a counterexample pass on those evidence-backed candidates in the same context before finalizing. The authority for dropping a…
- Deliver the existing disposition schema from the Looper prompt (must_fix | follow_up | needs_human, severity, scopeBasis, scopeEvidence)…
What it can do on your machine
Read from SKILL.md and the folder at commit 6abd8ff. 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
Looper Review loads about 722 tokens when it runs, and up to ~5.1k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 346 words of instructions outside code blocks.
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 nexu-io/looper at commit 6abd8ff, republished under its MIT licence (© nexu-io). 346 words, ~722 tokens.
Download SKILL.mdSave it as
.claude/skills/looper-review/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- looper-review
- description
- Default Looper review method for implementation and spec PRs. Read before reviewing. Covers correctness, tests, concurrency, contracts, and comment quality.
Looper review method
Read this file, then read every always-required referenced file below before reviewing. Read on-demand references only when their trigger matches the changed set.
Do not treat skill selection as a scope reduction: if no specialty skill matches, still complete the base review using this looper-review method. Apply the disposition schema, publish split, and repair-frontier contracts from the Looper reviewer prompt; this skill does not restate those execution contracts.
Procedure
- Understand stated intent from the PR seed, title/body, linked spec, and stated goals/non-goals.
- Enumerate in-scope changed files/ranges with local Git at the seeded base/head SHAs. Do not shrink that set because a specialty skill matches.
- Read the surrounding context needed to judge each change (callers, tests, contracts, lifecycle).
- For large PRs (roughly ≥15 changed files, or changes that cross packages), write an internal related-file plan grouping interface/impl/callers, db/readers, and prod/tests. Stay one reviewer; do not spawn sub-agents or subtasks.
- Establish concrete evidence for each independent in-scope finding: implementation trigger → code path → wrong consequence, or spec/docs section/omission → ambiguity or contradiction → implementation/validation consequence. Investigate uncertain candidates and omit unsupported claims from published findings. Group only the same root cause; keep unrelated concerns separate.
- Run a counterexample pass on those evidence-backed candidates in the same context before finalizing. The authority for dropping a candidate is that same review context (diff, callers, tests, contracts), not the agent's first structured finding list. Drop an evidence-backed candidate only when evidence proves it factually wrong or a same-root-cause duplicate. A missing reproduction is not disproof; static evidence can establish a finding.
- Deliver the existing disposition schema from the Looper prompt (
must_fix|follow_up|needs_human, severity, scopeBasis, scopeEvidence). Write comments that meet the quality bar in the reference files.
References
Always read:
Read on demand:
- CSS linting — when the change set includes CSS parsing or linting logic, including Go, TypeScript, or other non-style implementations. Do not require a CSS or style file in the changed set. Ordinary CSS-only edits do not need this fixture-matrix guidance.
© nexu-io, 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 5 other files (references) in internal/reviewer/reviewskills/builtin of nexu-io/looper.
- SKILL.md
- references/comment-quality.md
- references/css-lint.md
- references/evidence.md
- references/implementation-rubric.md
- references/spec-rubric.md
Open the folder on GitHubat commit 6abd8ff
Compare with similar skills
Looper 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Looper Review this skillnexu-io/looper | 133 | — | ~722 | Automated safety check: Pass | MIT | |
| Shepherd PRsflutter/flutter | 180k | — | ~1.7k | Automated safety check: Pass | BSD-3-Clause | |
| Tag Duplicate PRs Issuesopenclaw/openclaw | 392k | — | ~4k | Automated safety check: Pass | MIT | |
| Good PRsClickHouse/ClickHouse | 50k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Santa Methodaffaan-m/ECC | 277k | 3 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Santa Methodaffaan-m/ECC | 276k | — | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Tag Duplicate PRs Issues
openclaw/openclaw
Use gitcrawl to search duplicate OpenClaw PRs/issues, group related work in prtags, and sync duplicate state to GitHub.
Good PRs
ClickHouse/ClickHouse
Show a report of open ClickHouse PRs whose only non-green CI check is "CH Inc sync" (or that are fully green) — i.e.
Santa Method
affaan-m/ECC
Multi-agent adversarial verification: two independent reviewers with the same rubric must both pass before output ships, with a fix-and-re-review convergence loop and human escalation cap.
Santa Method
affaan-m/ECC
収束ループを持つマルチエージェント敵対的検証。2つの独立したレビューエージェントが両方合格して初めて出力を出荷できます。
Santa Method
affaan-m/ECC
具有收敛循环的多智能体对抗验证。两个独立的审查代理必须都通过，输出才能发送。
More from nexu-io/looper
PR Takeover
nexu-io/looper
A skill your agent uses when asked to take over, adopt, or babysit a GitHub pull request until it merges — read review feedback, fix it, resolve threads, dismiss unreasonable change requests, and…
Questions about Looper Review
What does Looper Review do?
Default Looper review method for implementation and spec PRs. Looper Review is an agent skill from nexu-io/looper. Default Looper review method for implementation and spec PRs.
How do I install Looper Review in Claude Code?
Run `npx skills add nexu-io/looper --skill looper-review -a claude-code`. Or copy the skill folder (internal/reviewer/reviewskills/builtin in nexu-io/looper) into .claude/skills/looper-review in your project. Claude Code loads it when a task matches its description.
How do I install Looper Review in Codex?
Run `npx skills add nexu-io/looper --skill looper-review -a codex`. Or copy the skill folder (internal/reviewer/reviewskills/builtin in nexu-io/looper) into .agents/skills/looper-review in your project. Codex loads it when a task matches its description.
Can I use Looper 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 nexu-io/looper --skill looper-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/looper-review, .gemini/skills/looper-review, .github/skills/looper-review and .opencode/skills/looper-review in your project.
What does Looper Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Looper Review is instructions for the agent only.
Does Looper 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 Looper 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 Looper Review use?
Looper 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 Looper Review use?
About 722 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.4k tokens, read only when the agent opens those files.
What are the alternatives to Looper Review?
Skills that share tags, products or a category with Looper Review: Shepherd PRs (flutter/flutter, 180k stars), Tag Duplicate PRs Issues (openclaw/openclaw, 392k stars), Good PRs (ClickHouse/ClickHouse, 50k stars) and Santa Method (affaan-m/ECC, 277k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Looper Review?
nexu-io (a GitHub organization) maintains it in nexu-io/looper, which has 133 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 2026.
Source: nexu-io/looper on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.