CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

80%

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

78%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 tight, actionable skill body that maps inputs to concrete tools and supplies an executable CLI fallback, with clean section organization. It is kept off the top band by the absence of explicit validation checkpoints and a lack of example MCP tool invocations.

Suggestions

Add a one-line example invocation of a representative MCP tool (e.g., scrape_docs) so Claude sees exact argument shape, not just the tool name.

Add an explicit validation/checkpoint step in 'Recommended Workflow' (e.g., verify the generated SKILL.md exists and summarize its contents before declaring done).

Tighten the Prerequisites prose into a tighter checklist to reclaim a few tokens without losing the setup guidance.

DimensionReasoningScore

Conciseness

Lean, table- and command-driven body that assumes Claude's competence; only minor instances of prose (the prerequisites paragraph) that could be trimmed.

4 / 5

Actionability

Provides an executable input-to-tool detection table and a concrete CLI fallback with real commands; the small gap is that MCP tools are only named, not shown in an example invocation.

4 / 5

Workflow Clarity

The 'Recommended Workflow' is a clear 7-step sequence; operations are non-destructive so the validation cap does not apply, but explicit validation/checkpoint phrasing is absent, holding it below 5.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections with one-level structure and no inlined material that belongs in separate files; no bundle files exist, and the overview is self-contained and easy to navigate.

5 / 5

Total

17

/

20

Passed

Description

82%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-constructed description that pairs a concrete capability statement with an explicit, trigger-rich 'Use when' clause. It is narrowly held back from perfection only by slightly limited action enumeration and a few missing synonym triggers.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ('detect source types' and 'build AI skills') but does not enumerate the broader capability set; not comprehensive enough for a 4.

3 / 5

Completeness

Explicitly answers both 'what' (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) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Lists natural triggers ('documentation, repos, PDFs, videos, or other knowledge sources') that users would say, but omits common synonyms/extensions like 'scraping', 'packaging', or '.pdf'.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (skill-building from knowledge sources) with distinct triggers and minimal overlap risk with unrelated skills.

5 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
yusufkaraaslan/Skill_Seekers
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.