Agent skill

Perfection Review

by srid in srid/emanote

Adversarial "perfection" review — hold a change to an ideal bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure.

Custom licenceAuto-check passed

Install Perfection Review

skills CLI
$ npx skills add srid/emanote --skill perfection-review -a claude-code

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

GitHub CLI
$ gh skill install srid/emanote perfection-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/srid/emanote.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/perfection-review .claude/skills/perfection-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
perfection-review
GitHub stars
963
Token cost
~773 tokens
SKILL.md length
390 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
Custom licence

At a glance

Adversarial "perfection" review — hold a change to an ideal bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure.

  • Works in 5 steps: Ground in the diff, not the story — the… → Letter vs effect — a safety added but… → Unspellable > absent — make the wrong… → …
  • The user asks to review for perfection
  • SKILL.md covers Method, Verify adversarially — use… and Report
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Perfection Review is an agent skill from srid/emanote. Adversarial "perfection" review — hold a change to an ideal bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure. Use when the user asks to review "for perfection", to make a defect "impossible to express", or to hunt where a defect "relocates" across review rounds. Grounds every claim in the diff, fans out adversarial verifiers via Workflow, and reports residual surfaces with a structural fix for each. ONLY invoke when the user explicitly asks for a perfection / ideal-bar…

Its SKILL.md is about 770 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: Emanate a structured view of your plain-text notes.

When your agent uses it

  • The user asks to review for perfection
  • Make a defect impossible to express
  • Hunt where a defect relocates across review rounds
  • Explicitly asks for a perfection / ideal-bar review

Example prompts

  • “perfection”
  • “for perfection”
  • “impossible to express”
  • “/perfection-review”

Workflow steps

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

  1. Ground in the diff, not the story — the PR body, commit messages, docs, and the
  2. Letter vs effect — a safety added but never exercised is inert. Require a real path
  3. Unspellable > absent — make the wrong thing impossible to write, not merely
  4. Reconcile claim and code — an overclaiming comment or doc is itself a defect: make the
  5. Finish the blast radius — not done until every dependent and downstream is carried to

What it can do on your machine

Read from SKILL.md and the folder at commit 9d01037. 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

Perfection Review loads about 773 tokens when it runs. Until then it costs about 136 tokens; SKILL.md has 390 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~136
When it runs · the whole SKILL.md, loaded when a task matches
~773

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 390 words (~773 tokens).

“The bar is not "closed" but "the defect can no longer be expressed." Assume eternal time, unlimited energy, no deadline. "Overridable", "acceptable for scope", and "documented intent" are still holes.”

— opening of SKILL.md by srid, Custom licence
name
perfection-review
argument-hint
[<pr-number>] [--base <branch>] [--post]

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/perfection-review of srid/emanote.

Open the folder on GitHubat commit 9d01037

Compare with similar skills

Perfection 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.

Perfection Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Perfection Review this skillsrid/emanote963—~773Automated safety check: PassCustom licence
Legal Holdanthropics/claude-for-legal9.6k1 repos~3.8kAutomated safety check: PassApache-2.0
Ideal Customer Profilephuryn/pm-skills27k—~1.5kAutomated safety check: PassMIT
Adversarial Reviewmengxi-ream/read-frog10k1 repos~905Automated safety check: PassGPL-3.0
Bar Prep Questionsanthropics/claude-for-legal9.6k2 repos~4.9kAutomated safety check: PassApache-2.0
Audit Adversarial Inputben-manes/caffeine18k—~438Automated safety check: PassApache-2.0

Similar skills

  • Legal Hold

    anthropics/claude-for-legal

    Official

    Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh.

    9.6k GitHub starsUsed in 1 repo~3.8k tokens
    Documents & OfficeAuto-check passed
  • Ideal Customer Profile

    phuryn/pm-skills

    Identify the Ideal Customer Profile (ICP) from research data with demographics, behaviors, JTBD, and needs.

    27k GitHub stars~1.5k tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Adversarial Review

    mengxi-ream/read-frog

    Adversarial code review using cross-model approach. An agent skill from mengxi-ream/read-frog.

    10k GitHub starsUsed in 1 repo~905 tokens
    DevelopmentAuto-check passed
  • Bar Prep Questions

    anthropics/claude-for-legal

    Official

    Bar prep questions — MBE or essay, targeted at your weak subjects and bar jurisdiction.

    9.6k GitHub starsUsed in 2 repos~4.9k tokens
    Auto-check passed
  • Audit Adversarial Input

    ben-manes/caffeine

    Analyze behavior under adversarial or extreme API inputs. An agent skill from ben-manes/caffeine.

    18k GitHub stars~438 tokensUpdated 2 days ago
    Auto-check passed
  • Agent Prompt Quality Bar

    mastra-ai/mastra

    Universal quality bar and final audit rubric for any agent system prompt.

    29k GitHub stars~2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from srid/emanote

All 25 skills in this repo
  • Codex Debate

    srid/emanote

    Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit.

    963 GitHub stars~8.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Do

    srid/emanote

    Do a task end-to-end — implement, PR, CI loop, ship. An agent skill from srid/emanote.

    963 GitHub stars~12k tokensUpdated 2 mo ago
    Auto-check passed
  • Be Review

    srid/emanote

    Run /be's review gauntlet SERIALLY — /lens-debate (lowy ⇄ hickey), then /codex-debate, then /simplify, then code-police, each editing and committing on the live branch in turn.

    963 GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check passed
  • CI

    srid/emanote

    Reference for the odu runner — how to invoke a full pipeline, a single recipe, or a platform-pinned node, and how to attach to a live run, from a project whose CI odu runs.

    963 GitHub stars~2.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Forge PR

    srid/emanote

    Write engaging PR titles and descriptions for any forge (GitHub today; Bitbucket planned).

    963 GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Kolu

    srid/emanote

    Drive one AI agent from another through kolu's terminals: spawn a Claude Code / Codex / opencode session in a PTY, prompt it, watch the screen for its reply, read it, and prompt again — a…

    963 GitHub stars~2.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Perfection Review

What does Perfection Review do?

Adversarial "perfection" review — hold a change to an ideal bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure. Perfection Review is an agent skill from srid/emanote. Adversarial "perfection" review — hold a change to an ideal bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure.

When should I use Perfection Review?

Perfection Review fits situations like: the user asks to review for perfection; make a defect impossible to express; hunt where a defect relocates across review rounds; explicitly asks for a perfection / ideal-bar review.

How do I install Perfection Review in Claude Code?

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

How do I install Perfection Review in Codex?

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

Can I use Perfection 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 srid/emanote --skill perfection-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/perfection-review, .gemini/skills/perfection-review, .github/skills/perfection-review and .opencode/skills/perfection-review in your project.

What does Perfection Review need to run?

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

Does Perfection 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 Perfection 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 Perfection Review use?

Perfection 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 Perfection Review use?

About 773 tokens (SKILL.md is roughly 3.1k 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 Perfection Review?

Skills that share tags, products or a category with Perfection Review: Legal Hold (anthropics/claude-for-legal, 9.6k stars), Ideal Customer Profile (phuryn/pm-skills, 27k stars), Adversarial Review (mengxi-ream/read-frog, 10k stars) and Bar Prep Questions (anthropics/claude-for-legal, 9.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Perfection Review?

srid (a GitHub user) maintains it in srid/emanote, which has 963 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on July 26, 2026.

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