New: 97,000+ 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

Official agent skill

Review

by getsentry in getsentry/sentry-dart

Three-axis review of the branch diff — Standards (this repo's documented standards + public API surface), Spec (the originating Linear issue / PR), and Correctness (runtime bugs + the SDK threat…

OfficialMITAuto-check passedAgent Workflows

Install Review

skills CLI
$ npx skills add getsentry/sentry-dart --skill review -a claude-code

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

GitHub CLI
$ gh skill install getsentry/sentry-dart 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/getsentry/sentry-dart.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/review .claude/skills/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
review
GitHub stars
873
Token cost
~1.3k tokens
SKILL.md length
694 words
Files
2 (incl. references)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Three-axis review of the branch diff — Standards (this repo's documented standards + public API surface), Spec (the originating Linear issue / PR), and Correctness (runtime bugs + the SDK threat…

  • Works in 4 steps: Pin the base → Identify the spec source → Spawn the sub-agents in parallel → …
  • Reviewing a branch
  • SKILL.md covers 1. Pin the base, 2. Identify the spec source, 3. Spawn the sub-agents in… and 4. Aggregate, plus 1 more section
  • Calls git and dart

What it does

Review is an agent skill from getsentry/sentry-dart, published by the product's own GitHub organization. Three-axis review of the branch diff — Standards (this repo's documented standards + public API surface), Spec (the originating Linear issue / PR), and Correctness (runtime bugs + the SDK threat model — PII, native leaks, buffers, serialization, concurrency). Runs the axes as parallel sub-agents and reports them side by side. Use when reviewing a branch, a PR, or work-in-progress changes before opening or merging, or "review since X".

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/smell-baseline.md`).

It sits in Agent Workflows, covering Subagents, Accessibility and Threat modeling. It works with Linear, Sentry, Flutter and Git. The repository describes itself as: Sentry SDK for Dart and Flutter. The licence is MIT.

When your agent uses it

  • Reviewing a branch
  • Work-in-progress changes before opening

Example prompts

  • “review since X”
  • “/review”

Workflow steps

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

  1. Pin the base
  2. Identify the spec source
  3. Spawn the sub-agents in parallel
  4. Aggregate

What it can do on your machine

Read from SKILL.md and the folder at commit 96d6367. 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
    • dart

    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

Review loads about 1.3k tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 111 tokens; SKILL.md has 694 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~111
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.9k

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 getsentry/sentry-dart at commit 96d6367, republished under its MIT licence (© getsentry). 694 words, ~1,349 tokens.

Download SKILL.mdSave it as .claude/skills/review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
review
description
Three-axis review of the branch diff — Standards (this repo's documented standards + public API surface), Spec (the originating Linear issue / PR), and Correctness (runtime bugs + the SDK threat model — PII, native leaks, buffers, serialization, concurrency). Runs the axes as parallel sub-agents and reports them side by side. Use when reviewing a branch, a PR, or work-in-progress changes before opening or merging, or "review since X".

Review the diff between HEAD and a base, on three axes:

  • Standards — does the diff conform to this repo's documented standards?
  • Spec — does it faithfully implement the originating issue / PR?
  • Correctness — will it actually work, and is it safe?

Run the axes as parallel sub-agents so none pollutes another's context, then aggregate. Report them side by side, and never rerank across axes — keeping them separate is the whole point (see Why separate axes).

This is the every-PR pass. It complements security-review (deeper security audit) and span-convention-review (tracing-span conventions) — invoke those for depth. It is not a debugger: when a bug is already known and reproducing, use diagnosing-bugs instead.

1. Pin the base

Use whatever base the user named — a commit, branch, tag, or HEAD~N. If they named none, default to the merge-base with the default branch (git merge-base HEAD origin/main). Capture once:

  • git diff <base>...HEAD (three-dot, so it compares against the merge-base)
  • git log <base>..HEAD --oneline

Confirm the ref resolves (git rev-parse <base>) and the diff is non-empty. A bad ref or empty diff fails here — not inside parallel sub-agents.

2. Identify the spec source

Look for the originating spec, in order:

  1. Linear issue references in commit messages or the PR (fetch the issue via the Linear tools).
  2. The PR description (motivation / what it does).
  3. A path the user passed.

If none is found, ask. If there genuinely is no spec, the Spec sub-agent skips and reports "no spec available".

3. Spawn the sub-agents in parallel

Send one message with three Agent tool calls (general-purpose subagent for each). Give each the diff command and the commit list, plus its brief:

Standards sub-agent:

Read .agents/skills/code-guidelines/SKILL.md and .agents/skills/test-guidelines/SKILL.md, then review the diff against them. Top priority — public API surface: for any change to a barrel file (lib/sentry.dart, lib/sentry_flutter.dart, or an integration package's barrel), classify each exported symbol as added / removed / signature-changed / behavior-changed. Flag every removal or incompatible change as a breaking change (semver-major) and check it carries a deprecation path (per code-guidelines). Then report, per file/hunk, every place the diff violates a documented standard — cite the rule. For areas the docs don't cover, apply the smell baseline in .agents/skills/review/references/smell-baseline.md as judgement calls. Distinguish hard violations from judgement calls; a documented standard overrides the baseline. Skip anything dart analyze / dart format / lints enforce. Under 400 words.

Spec sub-agent (skip and note if no spec):

Report: (a) requirements the spec asked for that are missing or partial; (b) behavior in the diff that wasn't asked for (scope creep); (c) requirements that look implemented but wrong. Quote the spec line for each finding. Under 400 words.

Show full SKILL.md (260 more words)Show less

Correctness sub-agent:

Find bugs and unsafe code the diff introduces — not style, which Standards owns. Check, per file/hunk:

  • Runtime bugs — unawaited / fire-and-forget futures, uncancelled stream subscriptions, late used before init, null/empty edge cases, swallowed errors, missing cleanup in close() / dispose(), races / TOCTOU.
  • SDK threat model — PII collected without gating on options.sendDefaultPii; sensitive data leaking into breadcrumbs, logs, or event payloads; native memory not released (JNI local refs, malloc) or a native exception that could crash the host app; unbounded buffers / queues / caches (memory growth); serialization correctness (toJson/fromJson round-trip, null handling); isolate / thread safety; rate-limiter or retry correctness. For each finding give file:line, a one-line severity (critical/high/medium/low), why it's real (not already handled, no covering test), and a concrete fix. Skip anything the analyzer or existing tests already catch. Under 400 words.

4. Aggregate

Present the reports under ## Standards, ## Spec, and ## Correctness headings, verbatim or lightly cleaned. Do not merge or rerank findings across axes.

End with a one-line summary per axis: total findings, and the worst issue within that axis. Don't pick a single winner across axes — that's the reranking the separation exists to prevent.

Why separate axes

A change can pass on one axis and fail on another, and a merged list lets one mask the others:

  • Follows every standard but implements the wrong thing → Standards pass, Spec fail.
  • Does what the issue asked but breaks conventions → Spec pass, Standards fail.
  • Clean and on-spec but leaks a native ref or drops a sendDefaultPii check → Standards & Spec pass, Correctness fail.

Reporting them separately stops any one axis from hiding another.

© getsentry, 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 (references) in .agents/skills/review of getsentry/sentry-dart.

  • SKILL.md
  • references/smell-baseline.md

Open the folder on GitHubat commit 96d6367

Compare with similar skills

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.

Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review this skillgetsentry/sentry-dart873—~1.3kAutomated safety check: PassMIT
Reviewgetsentry/sentry-react-native1.8k—~1.9kAutomated safety check: PassMIT
Reviewfossasia/eventyay-interpretation1.6k34 repos~996Automated safety check: PassApache-2.0
Frb PR Reviewfzyzcjy/flutter_rust_bridge5.4k—~485Automated safety check: PassMIT
Git Worktree Precommit Hook Flutter Failuredivinevideo/divine-mobile265—~1kAutomated safety check: PassMPL-2.0
AccessibilityVeryGoodOpenSource/vgv-ai-flutter-plugin169—~4.2kAutomated safety check: PassMIT

Similar skills

  • Review

    getsentry/sentry-react-native

    Official

    Three-axis review of the branch diff — Standards (this repo's documented standards + public API/bridge surface), Spec (the originating Linear/GitHub issue or PR), and Correctness (runtime bugs + the…

    1.8k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Review

    fossasia/eventyay-interpretation

    Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match…

    1.6k GitHub starsUsed in 34 repos~996 tokens
    Product & Project ManagementAuto-check passed

  • Frb PR Review

    fzyzcjy/flutter_rust_bridge

    Review a flutterrustbridge PR before treating it as ready, including subagent checks for correctness and test weakening.

    5.4k GitHub stars~485 tokensUpdated yesterday
    MobileAuto-check passed

  • Git Worktree Precommit Hook Flutter Failure

    divinevideo/divine-mobile

    Fix git pre-commit hook failures in Flutter projects when using git worktrees.

    265 GitHub stars~1k tokensUpdated today
    DevelopmentAuto-check passed

  • Accessibility

    VeryGoodOpenSource/vgv-ai-flutter-plugin

    Audits or remediates Flutter widgets against WCAG 2.2 conformance levels A, AA, or AAA across iOS, Android, Web, macOS, Windows, and Linux, covering Semantics labels and screen reader output under…

    169 GitHub stars~4.2k tokensUpdated yesterday
    Frontend & DesignAuto-check passed

  • UI UX Pro Max

    Ohh-889/skyroc

    UI/UX design intelligence. An agent skill from Ohh-889/skyroc.

    795 GitHub starsUsed in 26 repos~3.6k tokens
    Frontend & DesignAuto-check: notes

More from getsentry/sentry-dart

  • Code Guidelines

    getsentry/sentry-dart

    Official

    Enforce Sentry Dart/Flutter SDK code guidelines for implementation, refactoring, and review.

    873 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Test Guidelines

    getsentry/sentry-dart

    Official

    Enforce Sentry Dart/Flutter SDK test conventions for naming, structure, and fixtures.

    873 GitHub stars~3.1k tokensUpdated today
    Auto-check passed

  • Design First

    getsentry/sentry-dart

    Official

    Shape non-trivial work before writing it — decide the modules, the seams, and the public API surface up front.

    873 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Diagnosing Bugs

    getsentry/sentry-dart

    Official

    A discipline for hard bugs, flaky tests, CI hangs, and performance regressions in this SDK.

    873 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Review

What does Review do?

Three-axis review of the branch diff — Standards (this repo's documented standards + public API surface), Spec (the originating Linear issue / PR), and Correctness (runtime bugs + the SDK threat…. Review is an agent skill from getsentry/sentry-dart, published by the product's own GitHub organization. Three-axis review of the branch diff — Standards (this repo's documented standards + public API surface), Spec (the originating Linear issue / PR), and Correctness (runtime bugs + the SDK threat model — PII, native leaks, buffers, serialization, concurrency).

When should I use Review?

Review fits situations like: reviewing a branch; work-in-progress changes before opening.

How do I install Review in Claude Code?

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

How do I install Review in Codex?

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

Can I use 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 getsentry/sentry-dart --skill 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/review, .gemini/skills/review, .github/skills/review and .opencode/skills/review in your project.

What does Review need to run?

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

Does 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 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 Review use?

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 Review use?

About 1.3k tokens (SKILL.md is roughly 5.4k 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 580 tokens, read only when the agent opens those files.

What are the alternatives to Review?

Skills that share tags, products or a category with Review: Review (getsentry/sentry-react-native, 1.8k stars), Review (fossasia/eventyay-interpretation, 1.6k stars), Frb PR Review (fzyzcjy/flutter_rust_bridge, 5.4k stars) and Git Worktree Precommit Hook Flutter Failure (divinevideo/divine-mobile, 265 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review?

getsentry (a GitHub organization, an official publisher) maintains it in getsentry/sentry-dart, which has 873 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.

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