CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

68%

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

72%Weight 40%Scale 1-3

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 and well-structured with a clean one-level script reference, but it carries some redundant explanatory prose and lacks any verification step in its install workflow. Trimming the background sections and adding a confirm/verify checkpoint would tighten it further.

Suggestions

Cut or shrink the "What is the Skills CLI?" and "Security Assurance" sections to only what Claude cannot infer, recovering token budget.

Add a lightweight verification step after install (e.g. run a command to confirm the skill is present/usable before reporting success) to give the workflow a feedback checkpoint.

De-duplicate the "When to Use This Skill" list against the description's trigger clause so the same guidance is not stated twice.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the "What is the Skills CLI?" prose and the "Security Assurance" paragraph explain concepts Claude already knows and add padding without earning their tokens.

2 / 3

Actionability

It provides concrete, copy-paste-ready commands with a fixed script path and worked query examples (e.g. "${FIND_SKILLS_SCRIPT} find react performance"), which is fully executable guidance.

3 / 3

Workflow Clarity

Steps 1 through 4 are clearly sequenced with a "Critical" guardrail, but there is no validation or feedback checkpoint (e.g. confirm a skill exists before installing, verify install succeeded), so it stops at the 2-anchor.

2 / 3

Progressive Disclosure

Content is organized into well-signaled sections with a single one-level-deep reference (the scripts/agentteams-find-skill.sh path invoked explicitly), so navigation is easy and nothing is nested.

3 / 3

Total

10

/

12

Passed

Description

65%Weight 40%Scale 1-3

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 cleanly answers both what and when with a distinct meta-purpose, but its action list is thin and the trigger phrasing relies on "you encounter" (second person) rather than natural user phrasings. Rewording to third person and adding common user terms would raise specificity and trigger quality.

Suggestions

Rewrite "Use when you encounter..." in third person (e.g. "Use when the user faces an unfamiliar domain..." or "Use when working with an unfamiliar framework") to avoid the second-person voice penalty.

Expand the action list beyond "discover and install" to more concrete operations (e.g. "search, compare, and install agent skills") to lift specificity toward the 3-anchor.

Add natural trigger phrasings users actually say, such as "find a skill for X" or "is there a skill for X", to improve trigger-term coverage.

DimensionReasoningScore

Specificity

"Discover and install agent skills" lists only two actions (discover, install) and is not a comprehensive list, which is a baseline 2; the clause "Use when you encounter" is second-person voice, so per the rubric guideline the specificity score is reduced by 1.

1 / 3

Completeness

It states both what it does ("Discover and install agent skills from the open ecosystem") and an explicit when ("Use when you encounter an unfamiliar domain...").

3 / 3

Trigger Term Quality

Terms like "unfamiliar domain, framework, or workflow" and "searching for skills" are relevant, but common natural phrasings a user would actually say (e.g. "find a skill for X", "is there a skill for X") are missing.

2 / 3

Distinctiveness Conflict Risk

The meta-niche of discovering/installing skills, combined with triggers like "coordinator suggests searching for skills", is distinct and unlikely to fire for unrelated skills.

3 / 3

Total

9

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentscope-ai/AgentTeams
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.