CtrlK
BlogDocsLog inGet started
Tessl Logo

skillnet

Search, download, create, evaluate, and analyze reusable agent skills via SkillNet — the open skill supply chain for AI agents. Use when: (1) Before any multi-step task — search SkillNet for existing skills first, (2) User says "find a skill", "learn this repo/doc", "turn this into a skill", or mentions skillnet, (3) User provides a GitHub URL, PDF, DOCX, PPT, execution logs, or trajectory — create a skill from it, (4) After completing a complex task with non-obvious solutions — create a skill to preserve learnings, (5) User wants to evaluate skill quality, organize/analyze a local skill library, or orchestrate a supported scene. NOT for: single trivial operations (rename variable, fix typo), or tasks with no reusable knowledge.

73

Quality

92%

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

85%

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

The body is highly actionable, clearly sequenced with validation and safety checkpoints, and well-structured with real, properly signaled reference files. Its only weakness is conciseness: several key messages are repeated across sections and could be consolidated to reduce token cost.

Suggestions

Consolidate the repeated 'search before you build' guidance: state it once in the Core Principle and have Step 1 and the In-Task Triggers table reference it rather than restating it.

Merge the recurring 'confirm with the user before download/load/execute' rule into a single stated policy in the Security Essentials section, then point back to it from Step 2 and In-Task Triggers instead of repeating the full sentence.

Tighten the Capabilities section by moving the trigger→mode mapping table (which overlaps with the In-Task Triggers table) into the references or combining the two tables into one.

DimensionReasoningScore

Conciseness

The body is mostly actionable with little concept-explaining fluff, but the 'search before you build' and 'confirm with the user' messages recur across the Core Principle, Step 1, Apply, Security, and In-Task Triggers sections, so it could be tightened.

2 / 3

Actionability

Provides copy-paste-ready commands throughout (skillnet search/download/create/evaluate/analyze) plus concrete trigger→mode and decision tables, matching the score-3 anchor for fully executable guidance.

3 / 3

Workflow Clarity

The Search→Download→Load→Apply→Create→Evaluate→Maintain sequence is explicit with checkpoints (post-download review before loading, evaluate-after-create, dedup table), and destructive pruning is guarded by user confirmation and safe-removal-to-.trash rather than permanent deletion.

3 / 3

Progressive Disclosure

A 'Resource Navigation' table clearly signals one-level-deep references, and every referenced bundle file (api-reference.md, security-privacy.md, workflow-patterns.md, skillnet_create.py, skillnet_validate.py) exists on disk with no nested reference chains.

3 / 3

Total

11

/

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.

The description is strong across all dimensions: it lists concrete capabilities, provides natural trigger terms, explicitly covers both what and when, and carves out a distinctive niche with a negative-trigger exclusion. No first/second-person voice issues apply.

DimensionReasoningScore

Specificity

Names five concrete actions — 'Search, download, create, evaluate, and analyze reusable agent skills' — matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('Search, download, create, evaluate, and analyze...') and when (a numbered 'Use when: (1)...(5)...' clause), matching the score-3 anchor for clearly answering both.

3 / 3

Trigger Term Quality

Includes natural user phrasing ('find a skill', 'learn this repo/doc', 'turn this into a skill', 'skillnet') plus concrete artifacts (GitHub URL, PDF, DOCX, PPT, execution logs), giving broad coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (SkillNet skill supply chain) with distinct triggers and an explicit 'NOT for' exclusion clause, making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
zjunlp/SkillNet
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.