CtrlK
BlogDocsLog inGet started
Tessl Logo

product-self-knowledge

Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming), and Claude.ai (Pro vs Team vs Enterprise plans, feature limits). Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons. Any time you would otherwise rely on memory for Anthropic product details, verify here instead — your training data may be outdated or wrong.

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/claude-science/product-self-knowledge/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

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

The body is well-structured, actionable, and appropriately scoped for a simple routing skill — concrete URLs, a clear response workflow, and one-level external references with no nested or missing files. Its main weakness is redundancy: the Core Principles and Quick Reference sections restate the workflow and repeat URLs, inflating token cost without adding guidance.

Suggestions

Remove the duplicated docs-map URLs from either Question Routing or the Quick Reference section, keeping each URL in one place, to cut roughly a quarter of the body's tokens.

Drop or fold the 'Core Principles' section into the Response Workflow, since bullets like 'Source everything' and 'Right resource first' restate workflow steps 3-4.

Add a brief error-recovery step to the workflow for when the docs page is unreachable or unclear (e.g., say so explicitly and suggest the user check the linked page) to strengthen workflow clarity.

DimensionReasoningScore

Conciseness

The 'Core Principles' section ('Accuracy over guessing', 'Source everything', 'Right resource first') largely restates the Response Workflow steps, and the Quick Reference block repeats the docs-map URLs already given in Question Routing ('https://docs.claude.com/en/docs_site_map.md' and 'claude_code_docs_map.md' each appear twice). Mostly efficient but with genuine redundancy to tighten, matching anchor 3 rather than 4's 'minor instances' bar.

3 / 5

Actionability

Concrete, executable guidance: exact per-product URLs, an explicit routing rule ('Check the docs maps first, then navigate to specific pages'), and a copy-ready fallback phrase ('For the most current information, see [URL]'). Minor gap — no instruction on how to actually fetch or search the doc pages — keeps it at anchor 4 rather than 5.

4 / 5

Workflow Clarity

A clear 5-step sequence (Identify product → Use the right resource → Verify details → Provide answer with source → If uncertain, direct to docs) with an uncertainty fallback checkpoint. Not 5 because there is no guidance for error recovery when docs are unreachable or contradictory; not 3 because the sequence and fallback are explicit and the skill involves no destructive or batch operations that would require validation caps.

4 / 5

Progressive Disclosure

No bundle files exist, and all references are external web URLs that are one level deep and clearly labeled per product, with well-organized sections and easy navigation. It falls short of anchor 5 because the body (~60 lines) slightly exceeds the simple-skill threshold and contains duplicated routing content (Quick Reference repeating Question Routing URLs) that indicates less-than-ideal organization.

4 / 5

Total

15

/

20

Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly defines both scope (three products with concrete topic coverage) and abundant trigger conditions, with natural keyword coverage including synonyms. Its only weaknesses are second-person phrasing and minor coverage gaps on a few product topics.

DimensionReasoningScore

Specificity

Enumerates many concrete coverage areas per product ('how to install, Node.js requirements, platform/OS support, MCP server integration, configuration'; 'function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming'; 'Pro vs Team vs Enterprise plans, feature limits') with only minor gaps (e.g., Console/billing, Claude.ai feature topics). It falls short of anchor 5's comprehensiveness and uses second-person phrasing ('whenever your response would include', 'your training data') rather than the preferred third-person voice.

4 / 5

Completeness

Explicitly answers both what ('Stop and consult this skill whenever your response would include specific facts about Anthropic's products') and when ('whenever your response would include specific facts', 'Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons', 'Any time you would otherwise rely on memory for Anthropic product details'). Clear anchor 5 match with concrete trigger phrases; not 4 because the 'when' is fully explicit, not merely adequate.

5 / 5

Trigger Term Quality

Comprehensive natural terms users would actually say: 'Claude Code', 'Claude API', 'Claude.ai', 'Anthropic SDK', 'pricing', 'rate limits', 'Pro vs Team vs Enterprise plans', 'LLM provider comparisons', 'Node.js', 'MCP server' — including synonym variants like 'Anthropic SDK' alongside 'Claude API'. Matches anchor 5's coverage of natural terms and synonyms.

5 / 5

Distinctiveness Conflict Risk

A clear niche (verifying Anthropic product facts) with distinct triggers (product facts, pricing, plan comparisons, SDK facts), but it shares domain territory with a closely related API-usage skill, creating minor overlap risk. Fits anchor 4 ('mostly distinct; minor overlap risk with closely related skills') rather than 5's minimal-conflict bar.

4 / 5

Total

18

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
UnicomAI/wanwu
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.