CtrlK
BlogDocsLog inGet started
Tessl Logo

find-skills

Discover/install NEW agent skills from external sources (skills.sh). Use for capabilities you lack, e.g. "find a skill for X". Do NOT use to list skills you already have; see `<available_skills>`.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./core/python/long-horizon-harness/horizon/builtin_skills/find-skills/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable with concrete CLI commands and a clear six-step workflow plus user-confirmation and activation-verification checkpoints. It is concise and well-structured, lacking only an explicit error-recovery loop and carrying minor over-explanation.

DimensionReasoningScore

Conciseness

The body is mostly lean with executable commands and a useful examples table, but sentences like 'The leaderboard ranks by total installs, surfacing the most popular and battle-tested options' are minor over-explanation that could be trimmed; not a 5 because of these small padded passages.

4 / 5

Actionability

Provides copy-paste-ready commands throughout (npx skills find, skills add with @skill suffix, write/load_skill, which npx, skills init) plus a user-phrase-to-command mapping table, fully covering common cases as in the top anchor.

5 / 5

Workflow Clarity

Steps 1-6 are clearly sequenced with checkpoints (user confirmation before install, verify the skill appears in 'loaded' after reload); not a 5 because there is no explicit error-recovery feedback loop (e.g., what to do if reload does not list the skill or the directory name mismatches the name field).

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections with no nested or buried references and no content that clearly belongs in a separate file; not a 5 because the skill exceeds 50 lines and the simple-skill exception does not strictly apply, though structure is strong.

4 / 5

Total

17

/

20

Passed

Description

73%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 is strong: it states what and when with a concrete trigger phrase, uses third person, and includes excellent negative boundary guidance that lowers conflict risk. Its main limitation is single-example trigger coverage and only two named actions, which cap completeness and specificity just below the top anchor.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ('Discover/install NEW agent skills from external sources'), matching the anchor for 1-2 concrete actions without comprehensive coverage; it omits verification/presentation steps described in the body, so it is not a 4.

3 / 5

Completeness

Explicitly states both what ('Discover/install NEW agent skills from external sources (skills.sh)') and when ('Use for capabilities you lack, e.g. find a skill for X'), with a concrete trigger phrase; not a 5 because the 'when' offers a single example rather than the multiple concrete triggers seen in the 5 anchor.

4 / 5

Trigger Term Quality

Includes a natural user phrase ("find a skill for X") plus 'capabilities you lack', giving good keyword coverage; it falls short of 5 because only one example trigger is given rather than comprehensive synonyms or variations.

4 / 5

Distinctiveness Conflict Risk

Clear niche (external skill discovery/install) with explicit negative boundary guidance ('Do NOT use to list skills you already have; see <available_skills>') that minimizes conflict with existing-skill listing, matching the clear-niche/minimal-conflict anchor.

5 / 5

Total

16

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
google/adk-samples
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.