Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service — even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your training data may not reflect recent API changes or version updates. Always use for: API syntax questions, configuration options, version migration issues, "how do I" questions mentioning a
.claude/skills/mxyhi-find-docs/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 92% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 196% | 0% |
| case-07 | ✓→✗ | ▼ Worse | 31% | 0% |
| case-13 | ✓→✗ | ▼ Worse | 85% | 0% |
Retrieve current documentation and code examples for any library using the Context7 CLI.
Run commands with npx ctx7@latest so setup always uses the latest CLI without a global install:
bashnpx ctx7@latest library <name> "<query>" npx ctx7@latest docs <libraryId> "<query>"
Optionally install globally if you prefer a bare ctx7 command:
bashnpm install -g ctx7@latest
Two-step process: resolve the library name to an ID, then query docs with that ID.
bash# Step 1: Resolve library ID npx ctx7@latest library <name> "<query>" # Step 2: Query documentation npx ctx7@latest docs <libraryId> "<query>"
You MUST call library first to obtain a valid library ID UNLESS the user explicitly provides a library ID in the format /org/project or /org/project/version.
IMPORTANT: Do not run these commands more than 3 times per question. If you cannot find what you need after 3 attempts, use the best result you have.
Resolves a package/product name to a Context7-compatible library ID and returns matching libraries.
bashnpx ctx7@latest library React "How to clean up useEffect with async operations" npx ctx7@latest library "Next.js" "How to set up app router with middleware" npx ctx7@latest library Prisma "How to define one-to-many relations with cascade delete"
Use the official library name with proper punctuation (e.g., "Next.js" not "nextjs", "Customer.io" not "customerio", "Three.js" not "threejs"). If results look wrong, try alternate spellings such as next.js before changing the query.
Always pass a query argument — it is required and directly affects result ranking. Use the user's intent to form the query, which helps disambiguate when multiple libraries share a similar name. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query.
Each result includes:
/org/project)/org/project/version.If the user mentions a specific version, use a version-specific library ID:
bash# General (latest indexed) npx ctx7@latest docs /vercel/next.js "How to set up app router" # Version-specific npx ctx7@latest docs /vercel/next.js/v14.3.0-canary.87 "How to set up app router"
The available versions are listed in the library command output. Use the closest match to what the user specified.
Retrieves up-to-date documentation and code examples for the resolved library.
bashnpx ctx7@latest docs /facebook/react "How to clean up useEffect with async operations" npx ctx7@latest docs /vercel/next.js "How to add authentication middleware to app router" npx ctx7@latest docs /prisma/prisma "How to define one-to-many relations with cascade delete"
The query directly affects the quality of results. Be specific and include relevant details, but keep each query to one topic — if the question spans multiple distinct concepts, run a separate docs command per concept instead of combining them, unless the question is about how the concepts interact. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query.
| Quality | Example | |---------|---------| | Good | "How to set up authentication with JWT in Express.js" | | Good | "React useEffect cleanup function with async operations" | | Bad (too vague) | "auth" | | Bad (too vague) | "hooks" | | Bad (too broad) | "routing and auth and caching in Next.js" |
Describe what to look up in the library's documentation, rather than the task to complete — vague one-word queries return generic results, and multi-topic queries dilute ranking and return shallow results for each topic.
The output contains two types of content: code snippets (titled, with language-tagged blocks) and info snippets (prose explanations with breadcrumb context).
Works without authentication. For higher rate limits:
bash# Option A: environment variable export CONTEXT7_API_KEY=your_key # Option B: OAuth login npx ctx7@latest login
If a command fails with a quota error ("Monthly quota reached" or "quota exceeded"):
npx ctx7@latest loginDo not silently fall back to training data — always tell the user why Context7 was not used.
/ prefix — /facebook/react not facebook/reactnpx ctx7@latest library first — npx ctx7@latest docs react "hooks" will fail without a valid ID"React useEffect cleanup function" not "hooks""routing and auth and caching" into a separate docs command per concept, unless the question is about how they interact| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,027 | 4,861 | -63% | 1 | 1 | 0% | 2,429 | 1,829 | -25% | 0 | 0 | — |
case-02 | fail→fail | 12,329 | 5,768 | -53% | 1 | 1 | 0% | 2,293 | 1,871 | -18% | 0 | 0 | — |
case-03 | fail→fail | 10,442 | 28,529 | +173% | 1 | 1 | 0% | 1,963 | 6,077 | +210% | 0 | 0 | — |
case-04 | fail→fail | 6,360 | 4,111 | -35% | 1 | 1 | 0% | 551 | 1,681 | +205% | 0 | 0 | — |
case-05 | fail→fail | 10,680 | 3,809 | -64% | 1 | 1 | 0% | 1,997 | 1,717 | -14% | 0 | 0 | — |
case-06 | fail→fail | 11,246 | 5,822 | -48% | 1 | 1 | 0% | 2,250 | 1,806 | -20% | 0 | 0 | — |
case-07 | pass→fail | 6,434 | 4,781 | -26% | 1 | 1 | 0% | 1,349 | 1,773 | +31% | 0 | 0 | — |
case-08 | fail→fail | 8,517 | 4,125 | -52% | 1 | 1 | 0% | 431 | 1,702 | +295% | 0 | 0 | — |
case-09 | fail→pass | 7,648 | 3,082 | -60% | 1 | 1 | 0% | 1,324 | 2,053 | +55% | 0 | 0 | — |
case-10 | fail→fail | 7,148 | 6,835 | -4% | 1 | 1 | 0% | 1,581 | 2,078 | +31% | 0 | 0 | — |
case-11 | fail→pass | 6,281 | 4,558 | -27% | 1 | 1 | 0% | 1,226 | 2,357 | +92% | 0 | 0 | — |
case-12 | fail→fail | 8,283 | 3,425 | -59% | 1 | 1 | 0% | 1,647 | 1,689 | +3% | 0 | 0 | — |
case-13 | pass→fail | 5,780 | 5,514 | -5% | 1 | 1 | 0% | 964 | 1,787 | +85% | 0 | 0 | — |
case-14 | fail→pass | 3,940 | 2,513 | -36% | 1 | 1 | 0% | 651 | 1,930 | +196% | 0 | 0 | — |
case-15 | fail→fail | 5,259 | 3,854 | -27% | 1 | 1 | 0% | 939 | 1,743 | +86% | 0 | 0 | — |
case-16 | pass→fail | 10,618 | 3,770 | -64% | 1 | 1 | 0% | 2,190 | 1,682 | -23% | 0 | 0 | — |
case-17 | pass→pass | 8,701 | 4,744 | -45% | 1 | 1 | 0% | 1,863 | 2,463 | +32% | 0 | 0 | — |
case-18 | fail→fail | 8,628 | 4,770 | -45% | 1 | 1 | 0% | 1,650 | 1,777 | +8% | 0 | 0 | — |
case-19 | pass→pass | 11,696 | 12,994 | +11% | 1 | 1 | 0% | 2,503 | 3,627 | +45% | 0 | 0 | — |
case-20 | pass→pass | 8,252 | 6,889 | -17% | 1 | 1 | 0% | 1,693 | 2,930 | +73% | 0 | 0 | — |
case-21 | pass→pass | 10,957 | 7,205 | -34% | 1 | 1 | 0% | 2,226 | 2,884 | +30% | 0 | 0 | — |
case-22 | pass→pass | 4,721 | 4,373 | -7% | 1 | 1 | 0% | 954 | 2,442 | +156% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 9 counted toward the lift figure. The other 13 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 9 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/3/2026 | +13% |
Other measured skills in the registry, with their headline benchmark lift.