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

Code Review Standards

by tiramisulabs in tiramisulabs/seyfert

Review a concrete code change against an exact revision and produce evidence-backed findings.

MITAuto-check passedDevelopment

Install Code Review Standards

skills CLI
$ npx skills add tiramisulabs/seyfert --skill code-review-standards -a claude-code

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

GitHub CLI
$ gh skill install tiramisulabs/seyfert code-review-standards --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/tiramisulabs/seyfert.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/code-review-standards .claude/skills/code-review-standards && 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
code-review-standards
GitHub stars
321
Token cost
~754 tokens
SKILL.md length
361 words
Files
7 (incl. references)
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Review a concrete code change against an exact revision and produce evidence-backed findings.

  • Proposed review comments
  • SKILL.md covers Choose the review depth, Decide findings from evidence, Preserve action boundaries and Report
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Code review

What it does

Code Review Standards is an agent skill from tiramisulabs/seyfert. Review a concrete code change against an exact revision and produce evidence-backed findings. Use for PRs, patches, snapshots, or proposed review comments.

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `agents/openai.yaml`, `references/adversarial-review.md` and `references/finding-construction.md`).

It sits in Development, covering Code review. It works with Discord. The repository describes itself as: the black magic Discord framework 🧙♂️. The licence is MIT.

When your agent uses it

  • Proposed review comments
  • Tasks that involve Code review

Example prompts

  • “/code-review-standards”

What it can do on your machine

Read from SKILL.md and the folder at commit b4b333e. 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

Code Review Standards loads about 754 tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 361 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~754
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.1k

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 tiramisulabs/seyfert at commit b4b333e, republished under its MIT licence (© tiramisulabs). 361 words, ~754 tokens.

Download SKILL.mdSave it as .claude/skills/code-review-standards/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
code-review-standards
description
Review a concrete code change against an exact revision and produce evidence-backed findings. Use for PRs, patches, snapshots, or proposed review comments.

Code Review Standards

Review the requested change without editing it unless the user separately authorizes implementation. Pin the exact revision or content snapshot, preserve unrelated work, and distinguish defects introduced by the change from pre-existing behavior.

Choose the review depth

Use a bounded review for one change assessed in one sitting. Inspect the complete diff and trace relevant callers, contracts, tests, generated boundaries, and cross-repository counterparts only as far as the changed behavior requires.

Use a governed review when decisions must survive across sessions or repositories, findings will be approved one by one, publication is being prepared, or a persistent implementation handoff is required. Read governed-workflow.md before starting that mode and use templates.md only for artifacts the workflow actually needs.

An independent adversarial pass can improve a broad or consequential review when delegation is authorized and available. It is not a prerequisite for an ordinary bounded review.

Decide findings from evidence

Treat proposed comments, automated findings, and prior reviews as hypotheses. Establish the intended contract from current source, configuration, callers, tests, and runtime behavior. Read review-contract.md when deciding whether a candidate is actionable and how severe it is.

For each actionable finding:

  • show a reachable failure or concrete maintenance cost;
  • explain the violated repository-supported contract;
  • anchor inline feedback to a changed line in the exact reviewed diff;
  • calibrate severity to impact and likelihood;
  • deduplicate comments that share one cause.
Show full SKILL.md (132 more words)Show less

Read finding-construction.md when drafting or grouping publication-ready comments. Use adversarial-review.md only when running a genuinely independent pass.

A green test suite does not clear paths that were not exercised. Conversely, do not turn preferences, hypothetical edge cases, or pre-existing defects into blockers for the reviewed change.

Preserve action boundaries

A review request authorizes read-only investigation, not fixes, commits, pushes, publication, PR state changes, or deployments. Wording approval does not authorize publication. Before any authorized publication, reconfirm that the remote head still matches the reviewed revision and revalidate affected anchors if it changed.

Report

Lead with ranked findings. If there are none, say so directly and state any material evidence gaps. Identify the exact revision or snapshot reviewed and distinguish local checks, remote CI, deployment state, and live behavior whenever those boundaries matter.

© tiramisulabs, 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 6 other files (references) in .agents/skills/code-review-standards of tiramisulabs/seyfert.

  • SKILL.md
  • agents/openai.yaml
  • references/adversarial-review.md
  • references/finding-construction.md
  • references/governed-workflow.md
  • references/review-contract.md
  • references/templates.md

Open the folder on GitHubat commit b4b333e

Compare with similar skills

Code Review Standards 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.

Code Review Standards compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Review Standards this skilltiramisulabs/seyfert321—~754Automated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow156k—~3.5kAutomated safety check: NotesMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    156k GitHub stars~3.5k tokensUpdated yesterday
    DevelopmentAuto-check: notes

  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed

  • Mole Bug Patterns

    tw93/Mole

    A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed

More from tiramisulabs/seyfert

  • Coding Standards

    tiramisulabs/seyfert

    Implement, fix, or refactor repository-native code, with attention to behavioral contracts, code shape, implementation economy, and meaningful verification.

    321 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed

  • Make No Mistakes

    tiramisulabs/seyfert

    Apply proportional rigor to high-risk implementation or operations involving public contracts, security, payments, data, production, migrations, or exhaustive scope.

    321 GitHub stars~862 tokensUpdated 2 days ago
    Auto-check passed

  • Scope Discipline

    tiramisulabs/seyfert

    Prevent scope creep when a plan or implementation starts absorbing adjacent fixes, speculative compatibility work, migrations, or unrelated refactors.

    321 GitHub stars~632 tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Code Review Standards

What does Code Review Standards do?

Review a concrete code change against an exact revision and produce evidence-backed findings. Code Review Standards is an agent skill from tiramisulabs/seyfert. Review a concrete code change against an exact revision and produce evidence-backed findings.

When should I use Code Review Standards?

Code Review Standards fits situations like: proposed review comments; tasks that involve Code review.

How do I install Code Review Standards in Claude Code?

Run `npx skills add tiramisulabs/seyfert --skill code-review-standards -a claude-code`. Or copy the skill folder (.agents/skills/code-review-standards in tiramisulabs/seyfert) into .claude/skills/code-review-standards in your project. Claude Code loads it when a task matches its description.

How do I install Code Review Standards in Codex?

Run `npx skills add tiramisulabs/seyfert --skill code-review-standards -a codex`. Or copy the skill folder (.agents/skills/code-review-standards in tiramisulabs/seyfert) into .agents/skills/code-review-standards in your project. Codex loads it when a task matches its description.

Can I use Code Review Standards 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 tiramisulabs/seyfert --skill code-review-standards -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-review-standards, .gemini/skills/code-review-standards, .github/skills/code-review-standards and .opencode/skills/code-review-standards in your project.

What does Code Review Standards need to run?

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

Does Code Review Standards 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 Code Review Standards 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 Code Review Standards use?

Code Review Standards 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 Code Review Standards use?

About 754 tokens (SKILL.md is roughly 3k 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 5.4k tokens, read only when the agent opens those files.

What are the alternatives to Code Review Standards?

Skills that share tags, products or a category with Code Review Standards: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 156k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 86k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Review Standards?

tiramisulabs (a GitHub organization) maintains it in tiramisulabs/seyfert, which has 321 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 7, 2026.

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