es-toolkit is a JavaScript utility library providing commonly used functions such as debouncing, delaying, chunking, summing, and selecting values, with TypeScript types and a compatibility layer for Lodash. JavaScript and TypeScript developers use it when they need utility code with small bundles and performance-focused implementations, while the catalogue skills support AI coding tools working with the library.
Borrowing it
Nothing to install: this file belongs to toss/es-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/toss/es-toolkit/main/.claude/skills/pr-review/SKILL.mdgit clone --depth 1 https://github.com/toss/es-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/toss/es-toolkit/pr-review)<a href="https://agentmods.dev/skills/toss/es-toolkit/pr-review"><img src="https://agentmods.dev/badge/skills/toss/es-toolkit/pr-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/toss/es-toolkit/pr-review"><img src="https://agentmods.dev/badge/skills/toss/es-toolkit/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.00697 |
| Opus 5.5 | $0.00006 | $0.00279 |
| Sonnet 5.5 | $0.00003 | $0.00139 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
pr-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review
Fetch recent PRs, classify, read source code, and produce contextual reviews.
Input
$ARGUMENTS — Number of PRs (default: 10)
Examples:
/pr-review— 10 most recent open PRs/pr-review 20— 20 PRs
Workflow
1. Fetch recent PRs
gh pr list --repo toss/es-toolkit --state open --limit {count} --json number,title,author,labels,createdAt
2. Triage each PR
Run /pr-triage {number} for each PR to classify.
3. Deep review per PR
For each PR, go beyond classification — read the actual source code and provide context:
a. Read current code
Read the files being modified on main to understand the current behavior:
- Function source: what it does, how it works
- Existing tests: what's already covered
- JSDoc: documented behavior and examples
b. Understand the PR change
Read the diff to understand what's changing:
- What's the before vs after?
- Why does the contributor say this change is needed?
- Does the change match what the code actually needs?
c. Assess impact
- Breaking changes: Does the function signature change? Will existing users be affected?
- JS spec alignment: Does current behavior follow JS/lodash conventions? Does the PR break that?
- Scope: Are all affected files updated? (e.g., docs in all 4 languages, related functions)
- Design principles: Does this align with es-toolkit's 85% use case / simplicity philosophy?
d. Label-specific checks
- compat-fix: Run
/compat-review {number} - new-function: Check completeness (impl + spec + re-export + 4 lang docs)
- core-change:
yarn vitest run src/{category}/{fn}.spec.ts+ review breaking impact - docs: Check all 4 language files updated consistently
- types:
tsc --noEmit
4. Detect duplicates
Group PRs by same function name or same files modified.
5. Report per PR
For each PR, output:
### PR #{number} — {title}
**Classification**: {labels}
**Changed files**: {summary}
**Current code**: {what the function does now, with code snippet}
**PR change**: {what's changing and why, with before/after}
**Context**: {JS spec, lodash behavior, design principle considerations}
**Checkpoints**:
- {specific things to verify}
**Verdict**: {merge / merge with changes / hold for discussion / reject}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 105 lines · 14 tokens per session scan A 49b57795b940
pr-review is a skill published in the GitHub repository toss/es-toolkit (11,378 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 697 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…