Agent skill

Code Review

by polyipseity in polyipseity/obsidian-terminal

A skill your agent uses when reviewing PRs, code changes, or conducting code audits in obsidian-terminal.

AGPL-3.0Auto-check passedDevelopment

Install Code Review

skills CLI
$ npx skills add polyipseity/obsidian-terminal --skill code-review -a claude-code

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

GitHub CLI
$ gh skill install polyipseity/obsidian-terminal code-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/polyipseity/obsidian-terminal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/code-review .claude/skills/code-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
code-review
GitHub stars
948
Token cost
~1.6k tokens
SKILL.md length
716 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when reviewing PRs, code changes, or conducting code audits in obsidian-terminal.

  • Works in 6 steps: Identify the base and head refs (e.g.,… → Get a compact diff overview: git diff ..… → Read the full diff: git diff ... → …
  • Conducting code audits in obsidian-terminal
  • SKILL.md covers Preparation, Review Dimensions, Step-by-Step Workflow and References
  • Calls git, vitest and node

What it does

Code Review is an agent skill from polyipseity/obsidian-terminal. Use when reviewing PRs, code changes, or conducting code audits in obsidian-terminal. Covers correctness, type safety, architecture fit, test coverage, localization, and completeness.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Internationalization, Type safety and Test coverage. It works with Obsidian and Git. The repository describes itself as: Integrate consoles, shells, and terminals. The licence is AGPL-3.0.

When your agent uses it

  • Conducting code audits in obsidian-terminal
  • Tasks that involve Internationalization
  • Tasks that involve Type safety

Example prompts

  • “/code-review”

Workflow steps

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

  1. Identify the base and head refs (e.g., git log --oneline HEAD...main, or check the PR's base branch).
  2. Get a compact diff overview: git diff .. --stat.
  3. Read the full diff: git diff ...
  4. Identify all changed files and their types (.ts, .json, .mjs, .md, etc.).
  5. For each changed file, read the full file (not just the diff) to understand context.
  6. Read related integration points: e.g., if src/terminal/view.ts changed, also read src/terminal/load.ts and relevant interfaces.

What it can do on your machine

Read from SKILL.md and the folder at commit 8cbff89. 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

    Shell commands in SKILL.md call:

    • git
    • vitest
    • node
    • bun

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

  • Network

    No URLs in SKILL.md. Its commands use git, 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

Code Review loads about 1.6k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 716 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 polyipseity/obsidian-terminal at commit 8cbff89, republished under its AGPL-3.0 licence (© polyipseity). 716 words, ~1,615 tokens.

Download SKILL.mdSave it as .claude/skills/code-review/SKILL.md (or your agent's skills folder).
name
code-review
description
Use when reviewing PRs, code changes, or conducting code audits in obsidian-terminal. Covers correctness, type safety, architecture fit, test coverage, localization, and completeness.

Code Review Skill — obsidian-template-plugin

Use this skill to perform structured, thorough code reviews of this repository. Follow the preparation steps, then check each dimension using its checklist.

Preparation

  1. Identify the base and head refs (e.g., git log --oneline HEAD...main, or check the PR's base branch).
  2. Get a compact diff overview: git diff <base>..<head> --stat.
  3. Read the full diff: git diff <base>..<head>.
  4. Identify all changed files and their types (.ts, .json, .mjs, .md, etc.).
  5. For each changed file, read the full file (not just the diff) to understand context.
  6. Read related integration points: e.g., if src/terminal/view.ts changed, also read src/terminal/load.ts and relevant interfaces.

Review Dimensions

Correctness
  • Logic errors: off-by-one, null/undefined dereference, missing early returns.
  • State management: does the change properly read, mutate, and persist state? Are race conditions possible?
  • Async handling: are await/.then() used correctly? Are promises caught?
  • Edge cases: empty states, boundary values, rapid toggling, concurrent access.
  • Backward compatibility: default values preserve existing behavior. Old saved data still loads correctly.
Type Safety
  • No as casts (check project coding conventions — this repo disallows them).
  • No any types. unknown used where input is untrusted.
  • Runtime type guards or .fix() validators used to narrow unknown before use.
  • Public API has explicit return types and parameter types.
  • No deeply inferred anonymous types at package boundaries.
Architecture Fit
  • Follows existing patterns: .fix() for settings validation, linkSetting/resetButton for UI, Manager classes for lifecycle.
  • Uses SettingsManager and LanguageManager as shown in src/main.ts.
  • Localization uses createI18n(PluginLocales.RESOURCES, ...) and language.value.t(...).
  • New files follow the src/ directory layout and naming conventions.
  • No new architecture introduced where an existing pattern would suffice.
Test Coverage
  • Behavioral changes have tests added (per project convention: "test that fails before implementing the change").
  • Follows one test file per source file convention under tests/.
  • Unit tests (*.spec.*) are fast, hermetic, BDD-style.
  • Integration tests (*.test.*) are isolated and documented.
  • Tests use vi.fn(), vi.spyOn(), vi.mocked() per conventions.
  • vitest run is used (never watch mode) in automated flows.
  • Locale keys have existence tests if adding user-facing strings.
Localization
  • New keys added to assets/locales/en/translation.json first.
  • {{...}} placeholders and $t(...) calls kept intact, not translated.
  • Icon key added to assets/locales/en/asset.json if a settings icon is needed.
  • Alphabetical ordering maintained in locale JSON files.
  • Sync script run: node scripts/sync-locale-keys.mjs to propagate to all locales.
  • Description text is clear about behavior (not just label).
  • Follows .agents/instructions/localization.instructions.md.
Build & Scripts
  • Changes to scripts/build.mjs have corresponding tests in tests/scripts/build.test.mjs.
  • Changes to scripts/obsidian-install.mjs have corresponding tests in tests/scripts/obsidian-install.test.mjs.
  • manifest.json changes are reflected in versions.json if needed.
  • No hardcoded paths or environment-dependent behavior in scripts.
Show full SKILL.md (295 more words)Show less
Documentation
  • Changeset added (.changeset/) with correct bump type (major/minor/patch) and PR reference.
  • Changeset follows Conventional Commits style.
  • AGENTS.md updated if infra, testing conventions, or agent-visible patterns changed.
  • In-code docs updated if public API changed.
  • Commit message follows Conventional Commits: header ≤72 chars, body wrapped at 100 chars.
Regression Risk
  • Default values preserve existing behavior (false/opt-in for new features).
  • Changes are backward-compatible with saved user data (old data.json still loads).
  • Existing tests still pass (run bun x vitest run).
  • The change is minimal — no unrelated refactoring or reformatting.
Completeness
  • All integration points checked: settings-data (interface, DEFAULT, fix), settings UI, view behavior, locale keys, changeset.
  • No TODO comments or placeholder code left in.
  • Every changed file is consistent with the overall feature/change.
  • The diff --stat shows all expected files and no unexpected ones.

Step-by-Step Workflow

  1. Preparation — check out the branch, read the diff, read changed files in full context.
  2. Architecture check — does the change follow existing patterns? Identify any new patterns introduced.
  3. Correctness pass — trace the logical flow: entry point → data flow → output. Check edge cases.
  4. Type safety pass — scan for as, any, missing type guards.
  5. Test pass — verify tests exist and follow conventions. Check the actual test content if present.
  6. Localization pass — verify locale keys, sync, and ordering.
  7. Documentation pass — verify changeset, commit messages, AGENTS.md updates.
  8. Regression check — are defaults safe? Are old behaviors preserved? Do existing tests pass?
  9. Completeness check — re-read the diff stat and confirm every piece is accounted for.
  10. Report — produce a structured review with:
    • Overview of the change
    • What's done well
    • Issues found (with severity and file:line references)
    • Concrete fix recommendations
    • Completion checklist (✅/⚠️/❌)

References

© polyipseity, AGPL-3.0. 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 .agents/skills/code-review of polyipseity/obsidian-terminal.

Open the folder on GitHubat commit 8cbff89

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in polyipseity/obsidian-terminal, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Code 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.

Code Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Review this skillpolyipseity/obsidian-terminal948—~1.6kAutomated safety check: PassAGPL-3.0
Code Reviewjackfranklin/dotfiles255—~2kAutomated safety check: PassMIT
Code ReviewPrismer-AI/PrismerCloud1.6k—~2.1kAutomated safety check: NotesMIT
Review Codetobihagemann/turbo406—~3.2kAutomated safety check: PassMIT
Worktrunk Tend CI Guidancemax-sixty/worktrunk8.9k—~6.4kAutomated safety check: PassCustom licence
Evaluate PR Testsdotnet/maui23k—~2.9kAutomated safety check: PassMIT

Similar skills

  • Code Review

    jackfranklin/dotfiles

    Aggressive maintainability review focused on structural simplification, deleting complexity, type safety compiler soundness, resource leaks, accessibility, localization, and concurrency.

    255 GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Code Review

    Prismer-AI/PrismerCloud

    Review a diff against its acceptance criteria in four segments (convention adherence, bug scan, historical-context regressions, test-coverage gaps) as a NON-implementing agent.

    1.6k GitHub stars~2.1k tokensUpdated 7 days ago
    DevelopmentAuto-check: notes
  • Review Code

    tobihagemann/turbo

    Review code for bugs, security vulnerabilities, API misuse, consistency issues, simplicity problems, or test coverage gaps and low-value tests by running internal reviews and a peer review in…

    406 GitHub stars~3.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Worktrunk Tend CI Guidance

    max-sixty/worktrunk

    Adds Worktrunk-specific rules to the tend CI workflows: Codecov polling, Rust test commands, labels and review criteria for pull requests handled in CI.

    8.9k GitHub stars~6.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Official

    Reviews the tests added in a pull request for fix coverage, quality, edge cases and test type, and recommends lighter test types where they would do.

    23k GitHub stars~2.9k tokensUpdated today
    Testing & QAAuto-check passed
  • Sendou Code Review

    sendou-ink/sendou.ink

    Multi-agent code review that checks the current diff from multiple angles (spec compliance, bugs from two lenses, conventions/modernization, abstraction reuse, security, DB query performance, test…

    297 GitHub stars~5.2k tokensUpdated today
    DevelopmentAuto-check passed

More from polyipseity/obsidian-terminal

  • Plugin Testing

    polyipseity/obsidian-terminal

    Skill for testing Obsidian plugin features in this repository.

    948 GitHub stars~828 tokensUpdated 4 days ago
    Auto-check passed

Works with

Questions about Code Review

What does Code Review do?

A skill your agent uses when reviewing PRs, code changes, or conducting code audits in obsidian-terminal. Code Review is an agent skill from polyipseity/obsidian-terminal. Use when reviewing PRs, code changes, or conducting code audits in obsidian-terminal.

When should I use Code Review?

Code Review fits situations like: conducting code audits in obsidian-terminal; tasks that involve Internationalization; tasks that involve Type safety.

How do I install Code Review in Claude Code?

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

How do I install Code Review in Codex?

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

Can I use Code 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 polyipseity/obsidian-terminal --skill code-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/code-review, .gemini/skills/code-review, .github/skills/code-review and .opencode/skills/code-review in your project.

What does Code Review need to run?

Going by SKILL.md and its folder, Code Review needs the command-line tools its instructions call (git, vitest, node and bun).

Does Code Review access the network?

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

Is Code 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 Code Review use?

Code Review is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Review use?

About 1.6k tokens (SKILL.md is roughly 6.5k 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 Code Review?

Skills that share tags, products or a category with Code Review: Code Review (jackfranklin/dotfiles, 255 stars), Code Review (Prismer-AI/PrismerCloud, 1.6k stars), Review Code (tobihagemann/turbo, 406 stars) and Worktrunk Tend CI Guidance (max-sixty/worktrunk, 8.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Review?

polyipseity (a GitHub user) maintains it in polyipseity/obsidian-terminal, which has 948 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 3, 2026.

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