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

Deep Review

by dyad-sh in dyad-sh/dyad

Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported.

Custom licenceAuto-check passedDevelopment

Install Deep Review

skills CLI
$ npx skills add dyad-sh/dyad --skill deep-review -a claude-code

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

GitHub CLI
$ gh skill install dyad-sh/dyad deep-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/dyad-sh/dyad.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/deep-review .claude/skills/deep-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
deep-review
GitHub stars
22k
Token cost
~1.4k tokens
SKILL.md length
760 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Custom licence

At a glance

Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported.

  • Works in 5 steps: Determine the diff to review → Gather shared context → Launch the review workflow → …
  • The user asks for a deep
  • SKILL.md covers Step 1: Determine the diff to…, Step 2: Gather shared context, Step 3: Launch the review… and Step 4: Report, plus 1 more section
  • Calls git and gh

What it does

Deep Review is an agent skill from dyad-sh/dyad. Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported. Local equivalent of /code-review ultra. Use when the user asks for a deep, thorough, or multi-agent review of their branch, working diff, or a PR before merging. Usage: /deep-review (reviews current branch vs main, including uncommitted changes) or /deep-review <PR-number.

Its SKILL.md is about 1.4k 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 Pull requests and Code review. It works with DeepSeek, Google Gemini, Ollama and OpenAI. The repository describes itself as: Local, open-source AI app builder for power users ✨ v0 / Lovable / Replit / Bolt alternative 🌟 Star if you like it!

When your agent uses it

  • The user asks for a deep
  • Multi-agent review of their branch
  • A PR before merging

Example prompts

  • “/deep-review”

Workflow steps

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

  1. Determine the diff to review
  2. Gather shared context
  3. Launch the review workflow
  4. Report
  5. False positives — exclude these (give this list to every finder and verifier)

What it can do on your machine

Read from SKILL.md and the folder at commit 4764c7f. 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
    • gh

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

  • Network

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

Deep Review loads about 1.4k tokens when it runs. Until then it costs about 121 tokens; SKILL.md has 760 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
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); files beside SKILL.md 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 760 words (~1,405 tokens).

“Run a deep, high-signal code review of a diff using many parallel agents. The design mirrors ultrareview: broad coverage (independent finder agents, each with a different lens) followed by independent verification (skeptical agents that try to refute each finding). Only…”

— opening of SKILL.md by dyad-sh, Custom licence
name
deep-review

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/deep-review of dyad-sh/dyad.

Open the folder on GitHubat commit 4764c7f

Compare with similar skills

Deep 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.

Deep Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deep Review this skilldyad-sh/dyad22k—~1.4kAutomated safety check: PassCustom licence
Code ReviewHyk260/PureChat546—~645Automated safety check: PassMIT
Open Code Review CLIalibaba/open-code-review46k—~3.1kAutomated safety check: PassApache-2.0
Create SkillHyk260/PureChat5461 repos~823Automated safety check: PassMIT
DeepChat Provider IntegrationThinkInAIXYZ/deepchat6.4k—~1.2kAutomated safety check: PassApache-2.0
Code Reviewtimwuhaotian/the-pair379—~250Automated safety check: PassMIT

Similar skills

  • Code Review

    Hyk260/PureChat

    Perform code reviews (CR) for changed files in the current repository.

    546 GitHub stars~645 tokensUpdated 24 days ago
    DevelopmentAuto-check passed

  • Open Code Review CLI

    alibaba/open-code-review

    Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.

    46k GitHub stars~3.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Create Skill

    Hyk260/PureChat

    Create a new skill in the current repository. An agent skill from Hyk260/PureChat.

    546 GitHub starsUsed in 1 repo~823 tokens
    DevelopmentAuto-check passed

  • DeepChat Provider Integration

    ThinkInAIXYZ/deepchat

    Guides adding an LLM provider to DeepChat through explicit source changes: collect the provider details, pick a transport path and add registry entries and tests.

    6.4k GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Code Review

    timwuhaotian/the-pair

    Comprehensive code review with security and performance checks

    379 GitHub stars~250 tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Release Extension

    Yorick-Ryu/deep-share

    Release browser extensions or similar small packaged apps by upgrading a semantic version, packaging build artifacts, creating a git commit and tag, pushing to the remote, and publishing a GitHub…

    144 GitHub stars~1.3k tokensUpdated 6 days ago
    DevelopmentAuto-check passed

More from dyad-sh/dyad

  • Remember Learnings

    dyad-sh/dyad

    Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.

    22k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Deep Review

What does Deep Review do?

Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported. Deep Review is an agent skill from dyad-sh/dyad. Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported.

When should I use Deep Review?

Deep Review fits situations like: the user asks for a deep; multi-agent review of their branch; A PR before merging.

How do I install Deep Review in Claude Code?

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

How do I install Deep Review in Codex?

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

Can I use Deep 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 dyad-sh/dyad --skill deep-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/deep-review, .gemini/skills/deep-review, .github/skills/deep-review and .opencode/skills/deep-review in your project.

What does Deep Review need to run?

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

Does Deep Review access the network?

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

Is Deep 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 Deep Review use?

Deep Review 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 Deep Review use?

About 1.4k tokens (SKILL.md is roughly 5.6k 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 Deep Review?

Skills that share tags, products or a category with Deep Review: Code Review (Hyk260/PureChat, 546 stars), Open Code Review CLI (alibaba/open-code-review, 46k stars), Create Skill (Hyk260/PureChat, 546 stars) and DeepChat Provider Integration (ThinkInAIXYZ/deepchat, 6.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deep Review?

dyad-sh (a GitHub organization) maintains it in dyad-sh/dyad, which has 21,804 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 9, 2026.

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