ReactUse is a TypeScript library of reusable React Hooks for browser APIs, state, sensors, animations, and DOM interactions. React developers use it when building React applications that need these common behaviors. The catalogue skills and commands help coding agents discover or work with ReactUse hooks.
Borrowing it
Nothing to install: this file belongs to childrentime/reactuse. 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/childrentime/reactuse/main/.claude/skills/pr-description/SKILL.mdgit clone --depth 1 https://github.com/childrentime/reactuseWrote 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/childrentime/reactuse/pr-description)<a href="https://agentmods.dev/skills/childrentime/reactuse/pr-description"><img src="https://agentmods.dev/badge/skills/childrentime/reactuse/pr-description/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/childrentime/reactuse/pr-description"><img src="https://agentmods.dev/badge/skills/childrentime/reactuse/pr-description.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 | $0.00055 | $0.00562 |
| Opus 5.5 | $0.00022 | $0.00225 |
| Sonnet 5.5 | $0.00011 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
pr-description 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 2mo 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.
What it actually says
pr-description — describe a change the ReactUse way
Generate a title + body from the real diff, matching this repo's conventions. Don't invent scope or impact — read what actually changed.
Step 1 — Read the change
git status
git diff --stat
git diff # or: git diff origin/main...HEAD for a branch
git log --oneline -10 # match the prevailing style
Step 2 — Title: conventional commits with a scope
Format: type(scope): summary — imperative, lowercase, no trailing period.
Types seen in this repo: feat, fix, docs, chore, refactor, test.
Common scopes: core (hooks), website, blog, readme, mcp, skill.
Real examples from history:
feat(core): add useMicrophone hook (#198)fix(core): emit default values in generated API docsdocs(website): add useMicrophone hook documentation (#199)docs(blog): add React event hooks post (en, zh-Hans, zh-Hant)chore: release v6.3.3
Pick the type by the dominant change. A new hook is feat(core):; its docs are
docs(website):; they're usually separate commits/PRs.
Step 3 — Body
Keep it tight. Include only sections that apply:
## What
- bullet of each meaningful change
## Why
- the motivation / problem solved
## Test plan
- pnpm --filter @reactuses/core test useX
- pnpm lint
- (for docs) built locally / live demo renders
## AI assistance
- e.g. scaffolded with the new-hook skill (optional, see .claude/ai-policy.md)
Rules
- Verify every hook reference against
scripts/hook-registry.json— never invent a hook name, category, or URL. Links must be the lowercase canonical form. - Multi-locale doc/blog changes: note all three locales like history does
(
(en, zh-Hans, zh-Hant)). - Mention the issue/PR number if one exists.
- Disclosing AI use is recommended (see
ai-policy.md), not required.
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.
- 2mo ago First seen · 66 lines · 55 tokens per session scan A d463448bd69b
pr-description is a skill published in the GitHub repository childrentime/reactuse (1,068 stars, last pushed 8d ago), licensed Unlicense. It adds 55 tokens to every session and 562 once invoked, about $0.0002 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.
pr-description compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pr-descriptionchildrentime/reactuse | Skill | 1.1k | 8d ago | Unlicense | A | 55 | Claude Code |
| ce-commitEveryInc/compound-engineering-plugin | Skill | 26k | yesterday | MIT | A | 38 | Claude Code |
| ce-commit-push-prEveryInc/compound-engineering-plugin | Skill | 26k | yesterday | MIT | A | 42 | Claude Code |
| commitf5/unovis | Skill | 2.9k | yesterday | Apache-2.0 | A | 90 | Claude Code, Codex |
| open-prf5/unovis | Skill | 2.9k | yesterday | Apache-2.0 | A | 67 | Claude Code, Codex |
| changelogRemocn/remocn | Skill | 1.7k | yesterday | MIT | A | 70 | Claude Code |
| git-workflowjezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 52 | Claude Code |