docs
Search and access Anthropic documentation covering Claude Code CLI, API, Agent SDK, and more. Supports natural language queries, content search, and direct topic lookup. Trigger on: /docs, documentation questions about Claude Code, Claude API, Agent SDK, prompt engineering, MCP, hooks, skills, tool use, streaming, batch processing, extended thinking, or any Anthropic platform feature.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 skill description that clearly communicates its purpose (searching Anthropic documentation), lists specific capabilities, and provides an extensive explicit trigger clause covering many natural user terms. The description is well-structured, uses third person voice, and would be easily distinguishable from other skills in a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Search and access Anthropic documentation', 'natural language queries', 'content search', 'direct topic lookup'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (search and access Anthropic documentation, supports natural language queries, content search, direct topic lookup) and 'when' (explicit 'Trigger on:' clause with comprehensive list of trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: '/docs', 'Claude Code', 'Claude API', 'Agent SDK', 'prompt engineering', 'MCP', 'hooks', 'skills', 'tool use', 'streaming', 'batch processing', 'extended thinking'. These are terms users would naturally use when seeking documentation. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Anthropic documentation specifically, with distinct triggers like '/docs' and specific Anthropic product names. Unlikely to conflict with general coding or document processing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with strong actionability and clear workflow sequencing. The search commands are concrete and executable, and the decision logic for disambiguation is well-defined. The main weaknesses are moderate verbosity (some inline content could be offloaded to reference files) and the inability to verify that referenced files actually exist in the bundle.
Suggestions
Move the Domain Concept Map table and Cross-Reference Guide into reference files to reduce the SKILL.md token footprint, keeping only a brief summary inline with links.
Trim explanatory text that Claude can infer — e.g., the exact file/manifest count caveat and the detailed file naming convention examples could be condensed to one line each.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary detail that Claude doesn't need — e.g., the exact count of '571 files, 573 manifest paths', the approximate path counts per category, and the domain concept map table could be more compact. The file naming convention explanation is useful but slightly verbose. Overall mostly efficient with some tightening possible. | 2 / 3 |
Actionability | The skill provides fully executable bash commands for every search scenario, concrete fallback commands, specific file paths, and a clear quick reference section. The commands are copy-paste ready and cover content search, path search, direct lookup, freshness checks, and fallback grep. | 3 / 3 |
Workflow Clarity | The 4-step workflow (Analyze Intent → Run Search → Decide → Read and Present) is clearly sequenced with explicit decision points (same category vs. multiple categories). The cross-reference guide provides clear routing for ambiguous queries. The fallback path when the helper script is unavailable adds error recovery. The decision to synthesize vs. ask the user serves as a validation checkpoint. | 3 / 3 |
Progressive Disclosure | The skill references two external files (references/search-guide.md and references/category-map.md) with a clear navigation table, which is good structure. However, no bundle files were provided, so we cannot verify these references exist. Additionally, a significant amount of detail (the domain concept map, cross-reference guide, full command reference) is inline in the SKILL.md when some of it could be offloaded to reference files, making the main file leaner. | 2 / 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
- seanGSISG/claude-depot
- Commit
dd10cc1
- 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.