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.

63

Quality

73%

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/copaw-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 with strong executable examples and clean single-file organization. The main weaknesses are minor redundancy with the description and a missing post-install verification checkpoint in the workflow.

Suggestions

Add a brief verification step after install (e.g., re-run find or check the installed skill is present) so the workflow has an explicit success checkpoint.

Trim the opening restatement and the "Skills are modular packages..." sentence to reduce overlap with the description and basic context Claude already knows.

Consider folding the "When to Use This Skill" bullet list into the description trigger guidance to avoid duplicating trigger conditions in two places.

DimensionReasoningScore

Conciseness

Mostly actionable and efficient, but repeats the description in the opening line, re-states trigger guidance in "When to Use This Skill", and includes light explanatory padding ("Skills are modular packages that extend agent capabilities...") that Claude does not need.

2 / 3

Actionability

Provides copy-paste-ready executable guidance: a concrete FIND_SKILLS_SCRIPT resolution loop, exact find/install commands, real example queries, and a sample output block.

3 / 3

Workflow Clarity

Steps are clearly sequenced (Step 1 → 2 → 2A → 3 → 4) with a script-not-found guard and a no-results fallback, but there is no validation checkpoint confirming a skill actually installed successfully before presenting it as ready.

2 / 3

Progressive Disclosure

The single bundle resource (agentteams-find-skill.sh) is clearly signaled and resolved one level deep via FIND_SKILLS_SCRIPT, and the body is organized into well-labeled sections that read as an overview with a single reference.

3 / 3

Total

10

/

12

Passed

Description

75%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 is well-formed with explicit what-and-when guidance and a clear, distinct niche. It is somewhat thin on action breadth and natural trigger variations, which keeps specificity and trigger quality at the mid level.

DimensionReasoningScore

Specificity

Names the domain ("agent skills") and two concrete actions ("Discover and install"), but stops there rather than listing multiple specific concrete actions like search, browse, or update.

2 / 3

Completeness

Clearly states both what ("Discover and install agent skills from the open ecosystem") and when ("Use when you encounter an unfamiliar domain, framework, or workflow...") with an explicit 'Use when' clause.

3 / 3

Trigger Term Quality

Includes relevant natural terms ("unfamiliar domain, framework, or workflow", "searching for skills") but omits common user phrasings such as "find a skill", "install from market", or "how do I do X".

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (skill discovery/install) with distinct triggers unlikely to fire for unrelated skills, written in proper third-person voice.

3 / 3

Total

10

/

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.