AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Documentation Lookup

skill-prisma-ddti-skills-documentation-lookup · by prisma-ddti

Fetch current library, framework, and API documentation via the Context7 MCP instead of relying on training data. Use this skill whenever the user asks a question that depends on accurate, up-to-date behavior of any library, framework, SDK, or API — including setup/configuration questions, code examples, API references, migration guides, or version-specific behavior. Trigger even if the user does…

No reviews yet
0 installs
42 views
0.0% view→install

Install

$ agentstack add skill-prisma-ddti-skills-documentation-lookup

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-prisma-ddti-skills-documentation-lookup)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Documentation Lookup? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Documentation Lookup (Context7)

Answer library/framework/API questions using live documentation from the Context7 MCP, not training data. Two tools are available: resolve-library-id (find the Context7 library ID) and query-docs (fetch docs for that ID).

Workflow

1. Resolve the library ID

Call resolve-library-id with:

  • libraryName: the library or product name from the user's question.
  • query: the user's full question (improves relevance ranking).

This returns candidate library IDs. Pick the best match by considering exact name match, benchmark score (higher = better docs quality), source reputation, and version alignment if the user specified one.

A valid library ID is required before calling query-docs. If resolution returns no results, tell the user the library wasn't found in Context7 and offer to help via web search or training knowledge instead.

2. Fetch the documentation

Call query-docs with:

  • libraryId: the ID selected in step 1.
  • query: the user's specific question. Be precise — vague queries return vague results.

If the returned content doesn't answer the question, try one more query-docs call with a rephrased question before falling back. State uncertainty clearly rather than guessing.

3. Answer using the fetched docs

Respond using the current documentation. Include relevant code examples from the docs when helpful, and cite the library version when it matters.

Constraints

  • Max 3 MCP calls per question (combined resolve + query). Each call adds latency and token cost; keep it efficient. If 3 calls aren't enough, use the best information gathered so far and flag gaps honestly.
  • No secrets in queries: strip API keys, passwords, tokens, and other credentials from any text sent to resolve-library-id or query-docs.

Failure handling

  • No resolution results: the library may not be indexed in Context7. Say so and offer alternative approaches (web search, training knowledge).
  • Irrelevant docs returned: rephrase the query once. If still off-target, answer with what you have and note the limitation.
  • User didn't specify a library: if the question implies a library dependency but doesn't name one, ask which library they're using before calling resolve.

Example

User asks how to configure middleware in a web framework.

  1. Call resolve-library-id with the framework name and the user's question.
  2. From results, pick the official library ID (best name match + highest benchmark score). If the user mentioned a version, prefer a version-specific ID if available.
  3. Call query-docs with that ID and the question.
  4. Answer using the returned docs, including a minimal code example if the docs provide one.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.