Context7-aware development
Use Context7 for authoritative external docs and API references when local context is insufficient
MCP get_skill({ skillId: "context7-aware-development-9e7587ea" })Use this skill with your agent
Create a free account and connect via MCP
# Context7-aware development Use Context7 proactively whenever the task depends on **authoritative, current, version-specific external documentation** that is not present in the workspace context. This instruction exists so you **do not require the user to type** “use context7” to get up-to-date docs. ## When to use Context7 Use Context7 before making decisions or writing code when you need any of the following: - **Framework/library API details** (method signatures, configuration keys, expected behaviors). - **Version-sensitive guidance** (breaking changes, deprecations, new defaults). - **Correctness or security-critical patterns** (auth flows, crypto usage, deserialization rules). - **Interpreting unfamiliar error messages** that likely come from third-party tools. - **Best-practice implementation constraints** (rate limits, quotas, required headers, supported formats). Also use Context7 when: - The user references **a specific framework/library version** (e.g., “Next.js 15”, “React 19”, “AWS SDK v3”). - You’re about to recommend **non-trivial configuration** (CLI flags, config files, auth flows). - You’re unsure whether an API exists, changed names, or got deprecated. Skip Context7 for: - Purely local refactors, formatting, naming, or logic that is fully derivable from the repo. - Language fundamentals (no external APIs involved). ## What to fetch When using Context7, prefer **primary sources** and narrow queries: - Official docs (vendor/framework documentation) - Reference/API pages - Release notes / migration guides - Security advisories (when relevant) Gather only what you need to proceed. If multiple candidates exist, pick the most authoritative/current. Prefer fetching: - The exact method/type/option you will use - The minimal surrounding context needed to avoid misuse (constraints, default behaviors, migration notes) ## How to incorporate results - Translate findings into concrete code/config changes. - **Cite sources** with title + URL when the decision relies on external facts. - If docs conflict or are ambiguous, present the tradeoffs briefly and choose the safest default. When the answer requires specific values (flags, config keys, headers), prefer: - stating the exact value from docs - calling out defaults and caveats - providing a quick validation step (e.g., “run `--help`”, or a minimal smoke test) ## How to use Context7 MCP tools (auto) When Context7 is available as an MCP server, use it automatically as follows. ### Tool workflow 1) **If the user provides a library ID**, use it directly. - Valid forms: `/owner/repo` or `/owner/repo/version` (for pinned versions). 2) Otherwise, **resolve the library ID** using: - Tool: `resolve-library-id` - Inputs: - `libraryName`: the library/framework name (e.g., “next.js”, “supabase”, “prisma”) - `query`: the user’s task (used to rank matches) 3) **Fetch relevant documentation** using: - Tool: `query-docs` - Inputs: - `libraryId`: the resolved (or user-supplied) library ID - `query`: the exact task/question you are answering 4) Only after docs are retrieved: **write the code/steps** based on those docs. ### Efficiency limits - Do **not** call `resolve-library-id` more than **3 times** per user question. - Do **not** call `query-docs` more than **3 times** per user question. - If multiple good matches exist, pick the best one and proceed; ask a clarification question only when the choice materially affects the implementation. ### Version behavior - If the user names a version, reflect it in the library ID when possible (e.g., `/vercel/next.js/v15.1.8`). - If you need reproducibility (CI/builds), prefer pinning to a specific version in examples. ## Failure handling If Context7 cannot find a reliable source: 1. Say what you tried to verify. 2. Proceed with a conservative, well-labeled assumption. 3. Suggest a quick validation step (e.g., run a command, check a file, or consult a specific official page). ## Security & privacy - Never request or echo API keys. If configuration requires a key, instruct storing it in environment variables. - Treat retrieved docs as **helpful but not infallible**; for security-sensitive code, prefer official vendor docs and add an explicit verification step.
Related Skills
More skills in Software Engineering
Accessibility Standards
Comprehensive web accessibility standards based on WCAG 2.2 AA, with 38+ anti-patterns, legal enforcement context (EAA, ADA Title II), WAI-ARIA patterns, and framework-specific fixes for modern web frameworks and libraries.
Accord
Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision → L1 Requirements → L2 Team Detail → L3 Acceptance Criteria). No code. Use when authoring cross-team specs, building L0-L3 packages, or aligning Biz/Dev/Design on a single source of truth.
Acquire Codebase Knowledge
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.
Acreadiness Assess
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.
Acreadiness Generate Instructions
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.
Acreadiness Policy
Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.
Explore Other Categories
Skills from other categories with shared topics
Arduino Azure IoT Edge Integration
Design and implement Arduino integration with Azure IoT Hub and IoT Edge, including secure provisioning, resilient telemetry, command handling, and production guardrails.
Arm Migration Agent
Arm Cloud Migration Assistant accelerates moving x86 workloads to Arm infrastructure. It scans the repository for architecture assumptions, portability issues, container base image and dependency incompatibilities, and recommends Arm-optimized changes. It can drive multi-arch container builds, validate performance, and guide optimization, enabling smooth cross-platform deployment directly inside GitHub.
AWS AppSync Event API Instructions
Production-grade guidance for AWS AppSync Event API handlers using APPSYNC_JS runtime restrictions, utilities, modules, and datasource patterns