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

78%

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

Fix and improve this skill with Tessl

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

Quality

Content

75%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.

A well-structured, highly actionable single-file skill: exact commands, worked examples, and a properly referenced bundle script. Its main costs are a few padded sections that explain things Claude already knows and a missing post-install verification checkpoint.

Suggestions

Trim or remove the "What is the Skills CLI?" conceptual sentences, the "Security Assurance" paragraph, and "Step 1: Understand What They Need" — Claude can infer these, and they cost tokens without adding executable guidance.

State the fixed script path once (the code block near the top) and reference the variable elsewhere instead of repeating the full absolute path three times.

Add a brief post-install verification step (e.g., confirm the skill appears in the installed list or run a trivial usage check) to close the workflow's validation gap.

DimensionReasoningScore

Conciseness

The body is mostly efficient command documentation, but includes unnecessary padding Claude does not need: the conceptual explanation of what the Skills CLI is ("Skills are modular packages that extend agent capabilities with specialized knowledge, workflows, and tools"), the "Security Assurance" paragraph, and a "Step 1: Understand What They Need" section that coaches Claude on something it already does. This matches the level-3 anchor ("Mostly efficient but includes some unnecessary explanation or could be tightened"); it is not level 2 because the padding is limited to a few short sections and the bulk is lean, executable guidance.

3 / 5

Actionability

Guidance is fully executable and copy-paste ready: an exact pinned script path ("FIND_SKILLS_SCRIPT="$HOME/skills/find-skills/scripts/agentteams-find-skill.sh""), concrete find/install invocations with worked query examples ("find react performance", "find pr review"), an exact example response, and a no-results fallback script — the bundle script confirms `find` and `install` are its real subcommands.

5 / 5

Workflow Clarity

Steps 1 → 2 → 2A → 3 → 4 are clearly sequenced with a decision point for direct market imports and an explicit "copy exactly from search results" instruction. It falls short of level 5 because there is no post-install verification step (e.g., confirming the skill is now available) — a minor validation gap consistent with the level-4 anchor.

4 / 5

Progressive Disclosure

The single bundle file (scripts/agentteams-find-skill.sh) is real, referenced correctly via an absolute path rather than a cwd-relative one, and the ~170-line body uses clear sections (When to Use, commands, workflow, categories, tips, fallback). It does not reach level 5 because inline material like the Common Skill Categories table and Tips sections could live in a one-level-deep reference, and the script path instruction is repeated three times rather than stated once.

4 / 5

Total

16

/

20

Passed

Description

70%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 has a clear what/when structure and a distinct niche, but weakens itself with second-person trigger phrasing and a thin action vocabulary (only discover/install). It misses the most natural user phrasing ("find a skill"), which is the very behavior the skill name promises.

Suggestions

Rewrite the trigger clause in third person to avoid the specificity penalty, e.g. "Use when the user asks to find a skill, encounters an unfamiliar domain or framework, or asks to import a skill from the market."

Include the natural terms users actually say — "find a skill for X", "is there a skill for X", "install a skill from the market", "search the skills registry" — to broaden trigger coverage beyond "discover".

Add one or two more concrete actions (e.g., browse the registry at skills.sh, check for skill updates) to make the capability list more comprehensive.

DimensionReasoningScore

Specificity

"Discover and install agent skills from the open ecosystem" names the domain and two concrete actions, which matches the level-3 anchor ("Names domain and 1-2 concrete actions, but not comprehensive"). However, the trigger clause is written in second person ("when you encounter an unfamiliar domain... that you lack specialized knowledge about"), so the rubric's third-person-voice rule reduces specificity by 1.

2 / 5

Completeness

It clearly answers what ("Discover and install agent skills from the open ecosystem") and when with two explicit, concrete trigger conditions ("Use when you encounter an unfamiliar domain, framework, or workflow... or when your coordinator suggests searching for skills"), matching the level-5 anchor for explicit what-and-when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Phrases like "unfamiliar domain, framework, or workflow", "searching for skills", and "Discover and install agent skills" are relevant keywords, but common natural phrasings users actually say — "find a skill for X", "is there a skill for X", "install X from the market" — are absent, matching the level-3 anchor ("Some relevant keywords but missing common variations or synonyms").

3 / 5

Distinctiveness Conflict Risk

"Discover and install agent skills from the open ecosystem" carves out a clear niche (skill-registry discovery/installation) with distinct triggers, and is unlikely to fire for unrelated skills — matching the level-5 anchor ("Clear niche with distinct triggers; minimal conflict risk").

5 / 5

Total

15

/

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/worker-agent/skills/find-skills/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.