CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skill-builder

Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A well-organized, actionable skill body that leads with prerequisites and an executable CLI fallback so the workflow never dead-ends when the MCP server is absent. Its consistent weakness is the missing middle-of-pipeline validation — scrape results are never verified before enhancement or packaging.

DimensionReasoningScore

Conciseness

The body is table-driven and lean with no concept over-explanation, but minor tokens could be trimmed: the '40 tools' count is trivia and the 'When to Use This Skill' section partially restates the frontmatter description.

4 / 5

Actionability

Provides copy-paste commands ('pip install "skill-seekers[mcp]"', 'claude mcp add skill-seekers -- python -m skill_seekers.mcp.server_fastmcp', 'skill-seekers create <source>') and an exact input-pattern-to-tool mapping table; minor gaps remain in that MCP tool arguments are never shown.

4 / 5

Workflow Clarity

The 7-step Recommended Workflow is clearly sequenced and includes an explicit failure checkpoint (tool-list check with CLI fallback) plus a post-run read-back, but validation is implicit in the middle of the pipeline — no scrape-output verification and 'validate_config' is listed as a tool yet absent from the workflow.

4 / 5

Progressive Disclosure

No bundle files exist, and the ~85-line body is well-sectioned with all content appropriately inline for an overview; the minor gap is that the full MCP tool catalog could move to a reference file to keep SKILL.md closer to a lean overview.

4 / 5

Total

16

/

20

Passed

Description

78%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 well-formed description that clearly states both capability and trigger conditions in third person with concrete source-type keywords. Its only weakness is moderate action specificity — it summarizes the pipeline at a high level rather than naming the scraping, enhancing, and packaging steps it actually performs.

Suggestions

Add 1-2 more concrete capability verbs (e.g. 'scrape sources, enhance, and package skills for Claude/Gemini/OpenAI') to raise specificity beyond the current two-action summary.

Include one or two natural trigger variations users actually say, such as 'SKILL.md', 'turn documentation into a skill', or '.pdf', to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain (skill building) and 1-2 concrete actions ('Automatically detect source types and build AI skills'), but stops short of the several specific actions (scrape, enhance, package, export) that would mark comprehensive coverage.

3 / 5

Completeness

Explicitly answers both what ('Automatically detect source types and build AI skills using Skill Seekers') and when ('Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources') with concrete trigger phrases, matching the top anchor's pattern.

5 / 5

Trigger Term Quality

Includes natural terms users would say ('create skills', 'documentation', 'repos', 'PDFs', 'videos') but misses common variations like 'scrape', 'SKILL.md', or file extensions such as '.pdf'.

4 / 5

Distinctiveness Conflict Risk

The skill-building-from-sources niche is mostly distinct with clear triggers, though mentions of 'PDFs' and 'videos' carry minor overlap risk with generic document/video-processing skills.

4 / 5

Total

16

/

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

yusufkaraaslan/Skill_Seekers

Path

distribution/claude-plugin/skills/skill-builder/SKILL.md

Revision

5b5d8df

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill