get-api-docs
Use this skill to get documentation for third-party APIs, SDKs or libraries before writing code that uses them to ensure you have the latest, most accurate documentation. This is a better way to find documentation than doing web search. This includes when a user asks for tasks like "use the OpenAI API", "call the Stripe API", "use the Anthropic SDK", "query Pinecone", or any other time the user asks you to write code against an external service and you need current API reference. Fetch the docs with chub before answering, rather than relying on your pre-trained knowledge, which may be outdated because of recent changes to these APIs. Be sure to use this skill when the user asks for the latest docs, latest API behavior, or explicitly mentions chub or Context Hub. Ensure `chub` is available, run `chub --help`, then follow the instructions there.
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent trigger term coverage and clear completeness, explicitly stating both what the skill does and when to use it with concrete examples. The main weakness is that it's somewhat verbose and repetitive, and the specificity of actions is limited since it essentially describes one action (fetching documentation) rather than multiple distinct capabilities. The use of second person ('you') in places like 'you need current API reference' slightly detracts from the preferred third-person voice.
Suggestions
Condense the description to reduce repetition—the core message about fetching docs before coding is stated multiple times in slightly different ways.
Rewrite in third-person voice throughout (e.g., 'Fetches documentation for third-party APIs...' instead of 'Use this skill to get documentation...' and 'you need current API reference').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (third-party API/SDK documentation) and the core action (fetching docs with chub before writing code), but it doesn't list multiple distinct concrete actions—it's essentially one action (fetch documentation) described repeatedly in different ways. | 2 / 3 |
Completeness | Clearly answers both 'what' (fetch third-party API/SDK documentation using chub before writing code) and 'when' (when user asks to write code against external services, asks for latest docs, mentions chub or Context Hub). Explicit trigger guidance is provided with multiple examples. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'use the OpenAI API', 'call the Stripe API', 'use the Anthropic SDK', 'query Pinecone', 'latest docs', 'latest API behavior', 'chub', 'Context Hub'. These are realistic phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The skill has a clear niche—fetching third-party API documentation via the 'chub' tool—and explicitly distinguishes itself from web search. The specific tool name 'chub'/'Context Hub' and the focus on API/SDK docs make it unlikely to conflict with general coding or web search skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill that provides clear step-by-step guidance for using the chub CLI to fetch API documentation. Its main weaknesses are moderate verbosity from repeated 'follow chub --help if there's a conflict' disclaimers and a lack of explicit validation/error-handling checkpoints between steps. The concrete commands and examples make it immediately usable.
Suggestions
Remove the repeated 'follow chub --help if there is a conflict' caveat — state it once at the top and trust Claude to remember it.
Add a brief validation step after 'chub get' (e.g., 'Verify the fetched docs cover the specific endpoints/methods needed before writing code; if not, search for a more specific id').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary hedging and repetition, such as repeatedly saying 'follow the instructions from chub --help if there is a conflict' in multiple steps. Some phrasing could be tightened (e.g., 'This gives you the current, correct API' is slightly redundant given context). | 2 / 3 |
Actionability | Provides concrete, executable bash commands at every step — install, search, get, annotate, and feedback. Commands include specific flags (--json, --lang py) and realistic examples of IDs and annotation strings. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (1-4) with a logical flow from installation to usage to feedback. However, there's no explicit validation checkpoint — e.g., no step to verify the fetched docs are correct/complete before using them, and no error-handling guidance if 'chub search' returns no results beyond 'try broader terms'. | 2 / 3 |
Progressive Disclosure | For a skill of this size and scope (~50 lines, single tool), the content is well-organized into clear sequential sections without needing external references. The delegation to 'chub --help' for latest instructions is an appropriate form of progressive disclosure. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- andrewyng/context-hub
- Commit
eeb895b
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.