omni-github-skills

Search, score, scan, and import agent skills from GitHub repositories that contain SKILL.md, CLAUDE.md, .cursorrules, and similar agent skill files. Discover community skills across many tool and provider categories, evaluate relevance with heuristic scoring, check for malware or hardcoded secrets, and install into Hermes, Claude Code, Gemini CLI, or OpenCode agent directories.

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-github-skills/SKILL.md

Quality

Content

43%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 reads like an auto-generated API documentation stub rather than skill instructions: it reiterates the description and points to an OpenAPI spec, but provides no executable guidance or sequenced workflow for the skill's core task.

Suggestions

Replace the stub body with a concrete workflow — numbered steps for searching repositories, scoring relevance, running the malware/secret scan, and installing into the chosen agent directory — with validation checkpoints after the scan step.

Add executable examples or commands for each stage (e.g., the search/scoring call, the scan invocation, the install command) rather than only pointing to the OpenAPI spec.

Remove the empty 'No endpoints mapped for this area yet' placeholder and the verbatim description repetition, or move detail into a reference file with a clearly signaled one-level-deep link.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation, but the Overview repeats the frontmatter description verbatim and includes a non-informative 'No endpoints mapped for this area yet' stub that could be trimmed.	4 / 5
Actionability	Minimal concrete guidance for the skill's actual workflow — it only references API endpoints (`POST /api/auth/login`, `GET /api/openapi/spec`) and offers no executable commands or code for searching, scoring, scanning, or importing skills.	2 / 5
Workflow Clarity	The multi-step process (search → score → scan → import) is asserted as a flat list in the Overview with no sequenced steps and no validation checkpoints, despite malware/secret scanning being a validation-critical batch operation.	2 / 5
Progressive Disclosure	Section headers (Overview, Authentication, Endpoints, Payloads) provide some structure and it points to `docs/openapi.yaml` for detail, but the Endpoints section is an empty stub and there are no skill-specific reference files to navigate to.	3 / 5
	Total	11 / 20 Passed

Description

75%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.

The description is specific, action-rich, and distinct, clearly conveying what the skill does. Its main weakness is the absence of an explicit 'when to use' trigger clause, which limits completeness.

Suggestions

Append an explicit trigger clause such as 'Use when the user wants to find, evaluate, or import agent skills from GitHub, or mentions SKILL.md/CLAUDE.md/.cursorrules files.'

Add natural-sounding synonyms users might say ('find skills', 'browse community skills', 'install Claude Code skills') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Search, score, scan, and import', 'evaluate relevance with heuristic scoring', 'check for malware or hardcoded secrets', 'install into' named agent directories — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clearly and thoroughly answered, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Good natural coverage ('GitHub repositories', 'agent skills', 'SKILL.md', 'CLAUDE.md', 'Claude Code', 'Gemini CLI') but missing common variations like 'find skills' or 'browse skills' and the natural trigger phrasing users would say.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — discovering and importing agent skills from GitHub with malware/secret scanning — with specific named file types and target tools, minimizing conflict with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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: diegosouzapw/OmniRoute
Path: skills/omni-github-skills/SKILL.md
Commit: ea0cdc5

Reviewed: about 6 hours ago

Table of Contents

Discovery Implementation Validation

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.