CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

81%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with a well-structured multi-step workflow and concrete executable commands, but it is significantly over-verbose. It explains concepts Claude already understands (git operations, grep usage, file naming conventions in excessive detail), repeats information across sections (sync workflow mentioned in Steps 1, Keeping Docs Current, and Cross-Reference Guide), and inlines content that should be in reference files. The progressive disclosure structure is partially implemented but undermined by the amount of inline content.

Suggestions

Cut the Domain Concept Map section to ~5 lines: just list the 4 categories with their directory paths. Remove the table format, approximate counts, and explanations of what each category covers — Claude can discover this from the files.

Remove the ripgrep installation block from Step 1 — this is a one-time setup concern that should be in a separate setup/installation reference file, not executed on every docs query.

Move the Cross-Reference Guide and Key Commands Quick Reference into the referenced search-guide.md file to reduce the main SKILL.md to a concise workflow overview.

Eliminate redundant mentions of 'no search index' (stated 3 times) and the sync mechanism (described in Step 1, Keeping Docs Current, and Cross-Reference Guide).

DimensionReasoningScore

Conciseness

The skill is extremely verbose at ~200+ lines. It explains concepts Claude already knows (what grep does, how git pull works, what categories are), includes redundant sections (the sync workflow is repeated/referenced multiple times), and the domain concept map table explains things that could be conveyed in 2-3 lines. The ripgrep installation block and detailed file naming conventions add significant token overhead.

1 / 3

Actionability

The skill provides fully executable bash commands, concrete search tool usage patterns (Grep with output_mode options, Glob patterns), and a complete quick reference of copy-paste-ready commands. The Step 1 sync block is directly executable, and search workflows specify exact tool parameters.

3 / 3

Workflow Clarity

The 5-step workflow is clearly sequenced with explicit decision points (Step 4's same-category vs multi-category branching), validation (Step 1's mandatory sync with graceful degradation), and clear disambiguation rules. The cross-reference guide handles edge cases like ambiguous queries with specific actions.

3 / 3

Progressive Disclosure

The skill references two reference 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 to verify these references exist, and substantial content that could be in reference files (the full domain concept map, the cross-reference guide, the key commands quick reference) is inlined in the main SKILL.md, making it bloated.

2 / 3

Total

9

/

12

Passed

Description

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 (natural language queries, content search, topic lookup), and provides an explicit and comprehensive trigger clause covering many relevant terms. The description is well-structured, uses third person voice, and would be easily distinguishable from other skills in a large skill set.

DimensionReasoningScore

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

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
seanGSISG/claude-depot
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.