CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

find-skills

Discover and install agent skills from the open ecosystem. Use when you encounter an unfamiliar domain, framework, or workflow that you lack specialized knowledge about, or when your coordinator suggests searching for skills before starting a task.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./manager/agent/openhuman-worker-agent/skills/find-skills/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 actionable and well organized, with executable commands and a clear four-step workflow. It is held back by redundant sections, missing validation checkpoints around install operations, and a suspicious unprompted safety guarantee ('Worker is completely isolated and cannot access any admin's personal sensitive data') that reads as an over-claim rather than procedural guidance.

Suggestions

Remove the 'Security Assurance' section and the duplicated script-path restatement in 'Skill Resources'; state the path once.

Add a validation checkpoint after install (e.g., verify the skill is listed/loads correctly) and confirm search results before running the install command.

Consolidate Step 2A and Step 4, which both describe the same install invocation.

DimensionReasoningScore

Conciseness

Command blocks are tight, but the 'Security Assurance' section adds no procedural value, the script path is stated twice (the variable and the 'Skill Resources' section), and Step 2A duplicates Step 4, so the body could be meaningfully tightened.

3 / 5

Actionability

Commands are executable with worked examples ('"${FIND_SKILLS_SCRIPT}" find react performance', 'npm install -g skills', the SKILLS_API_URL default), but install/check/update only appear as unexemplified invocations, leaving minor gaps.

4 / 5

Workflow Clarity

Steps 1-4 are clearly sequenced with a 'Critical' warning about exact install commands, but there is no verification of search results before install and no post-install validation; since installing skills is a mutating external operation, the rubric's validation cap applies.

3 / 5

Progressive Disclosure

Sections are well organized and the single bundle script (scripts/agentteams-find-skill.sh) is clearly signaled and consistently referenced, though the duplicated absolute-path treatment is minor clutter rather than a real gap.

4 / 5

Total

14

/

20

Passed

Description

62%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 answers both what the skill does and when to use it, with a clear niche and low conflict risk. Its weaknesses are limited action coverage (only discover/install) and trigger phrasing that describes scenarios rather than the natural terms users would say.

Suggestions

Enumerate the full set of concrete actions (e.g., 'search, install, update, and browse agent skills') to raise specificity beyond two verbs.

Add natural user trigger phrases such as 'find a skill for X', 'is there a skill for X', or 'install X skill from the market' to improve trigger term coverage.

Replace the vague 'open ecosystem' with a concrete identifier (e.g., the skills registry or skills.sh) to sharpen distinctiveness.

DimensionReasoningScore

Specificity

Names the domain ('agent skills from the open ecosystem') and two concrete actions ('Discover and install') but lists no further capabilities such as search, update, or browsing, so it is not comprehensive.

3 / 5

Completeness

It has both a clear 'what' ('Discover and install agent skills from the open ecosystem') and an explicit 'Use when...' clause, but the 'when' is scenario-based rather than concrete user trigger phrases, so it falls short of the anchor 5 example.

4 / 5

Trigger Term Quality

Triggers like 'unfamiliar domain, framework, or workflow' and 'searching for skills' are relevant, but common natural phrasings users would actually say ('find a skill for X', 'is there a skill for X', 'skill market') are missing.

3 / 5

Distinctiveness Conflict Risk

The skill-discovery/installation niche is clear with distinct triggers (e.g., 'when your coordinator suggests searching for skills'), but 'open ecosystem' is slightly vague and leaves minor overlap risk with general tooling/package-manager skills.

4 / 5

Total

14

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

agentscope-ai/AgentTeams

Path

manager/agent/openhuman-worker-agent/skills/find-skills/SKILL.md

Revision

8a661dd

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill