mcpbeat Sign in

Dependency Handling Agent Skill

|

1k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
147
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/serpro69/claude-toolbox --skill dependency-handling

What comes with it

1 845 bytes besides the instruction
shared-capy-knowledge-protocol.md

The instruction itself

5 sections, as written by the author

<!-- codex: tool-name mapping applied. See .codex/scripts/session-start.sh -->

Dependency & External API Handling

Conventions

  • Read capy knowledge base conventions at shared-capy-knowledge-protocol.md.

Workflow

Mandatory order — lookup before usage. Do not write, modify, or recommend any call, import, config key, or version specifier involving the dependency until you have completed the lookup cascade below. Guessing a signature or API version and fixing it after the fact is the failure mode this skill exists to prevent.

  • Extract the dependency identity. From the calling context, identify the dependency name, the version constraint (declared or inferred), and the specific API surface being used (function, config key, API version, image tag). This is the minimal scope — enough to drive the lookup, not enough to guess the answer.
  • Capy search. Search kk:lang-idioms and kk:project-conventions for previously indexed knowledge about this dependency.
  • Context7 lookup. Use the context7 MCP to fetch documentation. The doc version MUST match the declared dependency version.
  • Web fallback. Only if context7 has no coverage.
  • Apply. With verified knowledge now loaded, write or recommend the call, import, or config.

Rules

  • Prefer the latest stable version when introducing a new dependency. Pin deliberately; don't inherit a stale version by copy-paste.
  • Never assume how an external dependency behaves. If you are not 100% sure of the signature, config, or semantics, look it up. Guessing is the failure mode this skill exists to prevent.
  • Capy search first. Before hitting external docs, search kk:lang-idioms and kk:project-conventions for previously indexed knowledge about the dependency.
  • Context7 second. Use the context7 MCP to fetch documentation for libraries, SDKs, APIs, and frameworks.
  • IMPORTANT: the doc version MUST match the declared dependency version. A right answer against the wrong version is a wrong answer.
  • Only fall back to web search if context7 has no coverage.
  • Index what you learn. If context7 or web search yields a best-practice nugget that isn't obvious from the docs themselves, index it as kk:lang-idioms so the next agent doesn't pay the lookup cost again.

IaC and config artifacts

The cascade rule (capy-first, context7-second, web-last) applies uniformly to all dependency categories — libraries, SDKs, frameworks, APIs, IaC API versions, CRDs, Helm charts, and container images. Per-domain lookup targets (which context7 library to query, which local command to run, which registry to consult) live in each profile's overview.md under a "Looking up dependencies" heading. When the k8s profile is active, consult ../../profiles/k8s/overview.md under the ## Looking up Kubernetes dependencies heading for Kubernetes API versions, third-party CRDs, Helm chart versions, and container image targets.

Other skills for the same job

different authors, same section of the catalogue
MCP Builder
by anthropics
vendor ×13

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

30k tokens scripts
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
MCP Builder
by JayZeeDesign
×7

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

37k tokens scripts
Vercel React Native Skills
by vercel-labs
vendor ×6

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

39k tokens
Vercel React Best Practices
by ratacat
×5

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

34k tokens
Next Best Practices
by vercel-labs
vendor ×4

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

20k tokens
Using Git Worktrees
by ZhanlinCui
×4

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

1k tokens

How to use it

Copy the folder

Take serpro69/claude-toolbox-dependency-handling from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.