CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paseo-plugin

Build and manage trusted local Paseo plugins. Use when the user asks to create, edit, install, reload, enable, disable, remove, or troubleshoot a Paseo plugin; add lifecycle hooks; transform agent configuration, environment, MCP servers, or workspace creation; automate permissions or turn follow-ups; add a screen, sidebar header or footer item, or workspace panel; add Command Center items or slash commands; add composer pills or attachment sources; transform, render, or append agent timeline items; contribute a theme; use Paseo from plugin code; or add plugin RPCs.

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 a maximally lean redirect stub that delegates all substance to a shared skill at an absolute external path. While token-efficient and unambiguous about its single action, it offers no in-bundle guidance or references, making the skill's usefulness entirely contingent on that external file being present. Self-containment or a bundled copy of the shared instructions would substantially improve it.

Suggestions

Bundle the essential instructions (or a copy of the shared skill) under references/ within the skill directory and point to that relative path, so the skill is self-contained instead of depending on ~/.agents/skills/paseo-plugin/SKILL.md.

Add a brief fallback line for when the shared skill path is missing (e.g., where to install it or what minimal steps to take), so the redirect does not dead-end.

If the two-line stub is intentional, add a one-line summary of the key entry points (e.g., 'See references/plugins.md for the plugin API') so the body carries minimal actionable orientation of its own.

DimensionReasoningScore

Conciseness

The body is two lines — a provenance comment and 'Load and follow the shared skill at `~/.agents/skills/paseo-plugin/SKILL.md`' — with zero padding or explanation of concepts Claude already knows; every token earns its place, matching the 'lean and efficient' anchor.

5 / 5

Actionability

The single directive is concrete (an exact path to load), but the file provides no executable guidance, commands, or examples for any of the tasks the description promises — everything is delegated to an external file. This lands at 'some concrete guidance but incomplete; missing key details' rather than score 4, which expects mostly executable in-file guidance.

3 / 5

Workflow Clarity

As a single-action stub, its one step ('Load and follow the shared skill at <path>') is unambiguous, which per the simple-skill exception merits a high score; however, no fallback or validation is given if the referenced shared skill is absent, leaving a minor gap that keeps it below 5.

4 / 5

Progressive Disclosure

The reference is clearly signaled and only one level deep, but it points to an absolute home path outside the skill bundle — no local references/, scripts/, or assets/ exist, and the target path is not part of the skill, so the structure depends entirely on an external, unverifiable location. This sits between 'references mostly clear' (4) and the disorganized/inline-content patterns (2-3), with the out-of-bundle dependency being more than a minor gap.

3 / 5

Total

15

/

20

Passed

Description

100%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.

An exemplary description: third-person voice, a crisp capability statement, an extensive enumeration of concrete actions, and an explicit 'Use when...' trigger clause covering natural user phrasings. It is highly specific, complete, and occupies a distinct niche with minimal conflict risk.

DimensionReasoningScore

Specificity

The description lists many concrete actions — 'create, edit, install, reload, enable, disable, remove, or troubleshoot a Paseo plugin; add lifecycle hooks; transform agent configuration, environment, MCP servers... add Command Center items or slash commands; add composer pills... contribute a theme; or add plugin RPCs' — giving comprehensive coverage of the domain's capabilities, matching the score-5 anchor rather than the 'minor gaps' of score 4.

5 / 5

Completeness

It explicitly answers both questions: 'what' ('Build and manage trusted local Paseo plugins' plus an enumerated capability list) and 'when' (an explicit 'Use when the user asks to...' clause with concrete triggers), exactly matching the score-5 anchor example pattern.

5 / 5

Trigger Term Quality

Trigger phrases mirror what a user would naturally say: 'install... a Paseo plugin', 'add... slash commands', 'contribute a theme', 'add a screen, sidebar header or footer item'. Coverage of natural action terms across the domain is comprehensive; it falls at the score-5 anchor rather than score 4's 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

The niche is clearly distinct — every trigger is scoped to 'Paseo plugin' and Paseo-specific surfaces (Command Center, composer pills, workspace panels), so conflict with generic skills is minimal; this matches the 'clear niche with distinct triggers' anchor rather than score 4's 'minor overlap risk'.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

phatblat/dotfiles

Path

.agents/harness/adapters/antigravity/skills/paseo-plugin/SKILL.md

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.