Agent skill

Independent Review

by pyathena-dev in pyathena-dev/PyAthena

Obtain and collect an independent read-only review of a PyAthena PR after both self-review rounds, with a frozen diff and recorded findings before Ready.

MITAuto-check: notes

Install Independent Review

skills CLI
$ npx skills add pyathena-dev/PyAthena --skill independent-review -a claude-code

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

GitHub CLI
$ gh skill install pyathena-dev/PyAthena independent-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/pyathena-dev/PyAthena.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/independent-review .claude/skills/independent-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
independent-review
GitHub stars
494
Token cost
~996 tokens
SKILL.md length
519 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Obtain and collect an independent read-only review of a PyAthena PR after both self-review rounds, with a frozen diff and recorded findings before Ready.

  • SKILL.md covers Provide a bounded review package and Collect and verify
  • Calls claude

What it does

Independent Review is an agent skill from pyathena-dev/PyAthena. Obtain and collect an independent read-only review of a PyAthena PR after both self-review rounds, with a frozen diff and recorded findings before Ready.

Its SKILL.md is about 1000 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: PyAthena is a Python DB API 2.0 (PEP 249) client for Amazon Athena. The licence is MIT.

Example prompts

  • “/independent-review”

What it can do on your machine

Read from SKILL.md and the folder at commit 209549d. 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:

    • claude

    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

Independent Review loads about 996 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 519 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~996

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:31
    Exclude credentials, `.env`, local memory, and unrelated artifacts from an external review package.

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 pyathena-dev/PyAthena at commit 209549d, republished under its MIT licence (© pyathena-dev). 519 words, ~996 tokens.

Download SKILL.mdSave it as .claude/skills/independent-review/SKILL.md (or your agent's skills folder).
name
independent-review
description
Obtain and collect an independent read-only review of a PyAthena PR after both self-review rounds, with a frozen diff and recorded findings before Ready.

Independent review

Use the scope and evidence rules in development-workflow. Choose an available reviewer that did not author the change, including its repairs: a different model or a human. A fresh thread of the authoring model does not satisfy this distinction. For a Codex-authored change, use Claude Code with model claude-fable-5-1, the max profile, and effort high. Do not use an Enterprise account for this review. Resolve the locally configured max profile without committing a personal filesystem path, and verify the selected account/profile before sending review content. An API key or provider environment override must not silently route the review through a different account. When the profile uses CLAUDE_CONFIG_DIR, set it to the resolved max directory and check claude auth status for first-party Max authentication before launch. Use the Claude Code CLI directly; no reviewer plugin is required. For a Claude-authored change, use a different model or a human; a second Claude session is still self-review. An explicit user override takes precedence over these defaults. Existing authorization applies within its scope; this skill does not authorize unrelated external disclosure or contacting other people.

Provide a bounded review package

Freeze the review merge-base SHA and published head SHA, as defined in the workflow skill, and a clean source snapshot before launching. Use a detached worktree or an exported snapshot of tracked files that matches the reviewed commit. Exclude credentials, .env, local memory, and unrelated artifacts from an external review package. Supply the literal diff and relevant source/tests plus repository conventions. Keep author framing out of the review prompt: omit the PR number, PR description, commit message, prior findings, and author conclusions.

Request review only: no edits, builds, tests, commits, pushes, GitHub writes, or access to PR discussion or agent memory. Ask the reviewer to identify covered surfaces, return CLEAN or FINDINGS, and give file:line plus a concrete failure scenario for each actionable finding. For a narrow follow-up after a completed initial review, provide the bounded patch-series comparison and affected contracts described in the workflow skill.

Show full SKILL.md (185 more words)Show less

Collect and verify

Wait for completion and read the actual result. A launched job, successful authentication, or missing output does not establish a completed review. Record reviewer identity, the requested model/profile and effort where applicable, base/head SHAs, invocation constraints, session/job identifier, coverage, and actual findings. Verify that the review snapshot and PR worktree remained unchanged. Label the result as a static review unless the reviewer was separately authorized to execute validation and actually did so.

Verify findings against the code before acting. Record why any finding is rejected, deferred, or identified as pre-existing. The author fixes verified regressions, runs affected validation, applies both self-review perspectives to the repair, and obtains an independent follow-up. A repair that expands the contract requires a full review of the expanded scope.

Publish the result inline, clearly identifying a relayed reviewer result and preserving its material findings and limits. If the reviewer is unavailable or an execution/approval restriction prevents the review, record the exact reason and keep this step incomplete. Continue useful authorized work; retain Draft status until the required review is completed or the user explicitly changes the requirement.

© pyathena-dev, MIT. 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/independent-review of pyathena-dev/PyAthena.

Open the folder on GitHubat commit 209549d

Compare with similar skills

Independent 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.

Independent Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Independent Review this skillpyathena-dev/PyAthena494—~996Automated safety check: NotesMIT
Agent Collective Intelligence Coordinatorruvnet/ruflo74k2 repos~1kAutomated safety check: PassMIT
Collection Digestoutline/outline41k—~498Automated safety check: PassCustom licence
Postman Collection Generatorsickn33/agentic-awesome-skills47k1 repos~1.4kAutomated safety check: PassMIT
Dossier Collectruvnet/ruflo74k—~1.1kAutomated safety check: NotesMIT
Collecting Indicators Of Compromisemukul975/Anthropic-Cybersecurity-Skills34k—~2.7kAutomated safety check: PassApache-2.0

Similar skills

  • Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator

    74k GitHub starsUsed in 2 repos~1k tokens
    Auto-check passed
  • Collection Digest

    outline/outline

    Summarize what changed in an Outline collection since a date; use when the user asks what is new, what was updated, or wants a digest of recent documents.

    41k GitHub stars~498 tokensUpdated yesterday
    Knowledge ManagementAuto-check passed
  • Postman Collection Generator

    sickn33/agentic-awesome-skills

    Generate complete, import-ready Postman Collection v2.1 JSON files from natural language API descriptions or cURL commands.

    47k GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Dossier Collect

    ruvnet/ruflo

    Build a graph-structured dossier on a seed entity via parallel fan-out + recursive expansion across web, memory, knowledge-graph, codebase, ADR index, and git intel

    74k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check: notes
  • Collecting Indicators Of Compromise

    mukul975/Anthropic-Cybersecurity-Skills

    Systematically collects, categorizes, and distributes indicators of compromise (IOCs) during and after security incidents to enable detection, blocking, and threat intelligence sharing.

    34k GitHub stars~2.7k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Changelog Collect

    NG-ZORRO/ng-zorro-antd

    Collect and draft NG-ZORRO changelog entries between releases or branches.

    9.2k GitHub stars~443 tokensUpdated yesterday
    DevelopmentAuto-check passed

More from pyathena-dev/PyAthena

  • Development Workflow

    pyathena-dev/PyAthena

    Deliver a PyAthena change through a dedicated worktree, Draft PR, two distinct self-reviews, independent review, and current CI once marked Ready.

    494 GitHub stars~2.1k tokensUpdated today
    Auto-check: notes
  • Self Review

    pyathena-dev/PyAthena

    Run the first PyAthena self-review after creating a Draft PR, checking implementation behavior, public contracts, simplicity, and regression coverage.

    494 GitHub stars~740 tokensUpdated today
    Auto-check passed
  • Self Review Round Two

    pyathena-dev/PyAthena

    Run the second PyAthena self-review after round one, auditing factual claims, caller compatibility, AWS operational effects, and evidence from a user's perspective before Ready.

    494 GitHub stars~820 tokensUpdated today
    Auto-check passed

Questions about Independent Review

What does Independent Review do?

Obtain and collect an independent read-only review of a PyAthena PR after both self-review rounds, with a frozen diff and recorded findings before Ready. Independent Review is an agent skill from pyathena-dev/PyAthena. Obtain and collect an independent read-only review of a PyAthena PR after both self-review rounds, with a frozen diff and recorded findings before Ready.

How do I install Independent Review in Claude Code?

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

How do I install Independent Review in Codex?

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

Can I use Independent 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 pyathena-dev/PyAthena --skill independent-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/independent-review, .gemini/skills/independent-review, .github/skills/independent-review and .opencode/skills/independent-review in your project.

What does Independent Review need to run?

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

Does Independent 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 Independent Review safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Independent Review use?

Independent 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 Independent Review use?

About 996 tokens (SKILL.md is roughly 4k 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 Independent Review?

Skills that share tags, products or a category with Independent Review: Agent Collective Intelligence Coordinator (ruvnet/ruflo, 74k stars), Collection Digest (outline/outline, 41k stars), Postman Collection Generator (sickn33/agentic-awesome-skills, 47k stars) and Dossier Collect (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Independent Review?

pyathena-dev (a GitHub organization) maintains it in pyathena-dev/PyAthena, which has 494 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 10, 2026.

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