skill-discovery

Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.

Quality

78%

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 ./openspace/host_skills/skill-discovery/SKILL.md

Quality

Content

100%

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

The content is concise, highly actionable with concrete tool invocations, and presents a clearly sequenced workflow with an error-recovery feedback loop. With no bundle files, its well-organized single-file structure earns full progressive-disclosure credit.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: tight parameter tables, copy-ready invocations, and a compact decision tree, with only minor justification prose ('Cloud skills have been evolved through real use') and no padding explaining concepts Claude already knows.	3 / 3
Actionability	Concrete executable invocations are given throughout — 'search_skills(query=...)' , 'cloud_auth_flow(action="bootstrap_agent_key", ...)' , and four 'cloud_browse_skills(action=...)' variants — plus a parameter table, making the guidance copy-paste ready.	3 / 3
Workflow Clarity	The process is clearly sequenced (when-to-use → local search → optional cloud auth → cloud browse → after-search decision tree), and the 'or a cloud operation reports a missing/invalid key, set up cloud access first' line provides an explicit feedback loop for error recovery.	3 / 3
Progressive Disclosure	No bundle files exist, and the body is organized into well-signaled sections (When to use, Cloud access, search_skills, cloud_browse_skills, After search, Notes) with no nested references, satisfying the simple-skill allowance for progressive disclosure.	3 / 3
	Total	12 / 12 Passed

Description

57%

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 clearly conveys a specific niche and concrete actions, but its trigger-term coverage is limited and it omits an explicit 'Use when...' clause, capping completeness at 2. The second-person 'your' also lowers specificity per the rubric.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrasings such as 'Use when the user asks what skills are available or whether a skill exists for a task.'

Replace second-person voice ('extends your capabilities') with third person ('extends capabilities') to satisfy the voice guideline and recover the specificity penalty.

Include common user phrasings (e.g., 'what skills are available', 'is there a skill for X') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'Search reusable OpenSpace skills locally, and browse cloud packages step by step' name multiple concrete actions (search + browse), which would be a 3, but 'extends your capabilities beyond built-in tools' uses second-person 'your', triggering the rubric's -1 specificity penalty.	2 / 3
Completeness	It states what the skill does ('Search reusable OpenSpace skills locally, and browse cloud packages step by step') and a partial when ('when a cloud skill may help'), but lacks an explicit 'Use when...' trigger clause, so completeness is capped at 2 per the guidelines.	2 / 3
Trigger Term Quality	Terms like 'skills' and 'cloud packages' are relevant, but common natural phrasings a user would actually say ('what skills are available', 'is there a skill for X') are absent from the description, leaving some common variations missing.	2 / 3
Distinctiveness Conflict Risk	'Search reusable OpenSpace skills locally, and browse cloud packages' carves a clear niche (skill discovery) with distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	9 / 12 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: HKUDS/OpenSpace
Path: openspace/host_skills/skill-discovery/SKILL.md
Commit: c5a9c4b

Reviewed: 2 days 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.