CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

recommendations

How to suggest options that fit the user and don't repeat earlier ones (meals, restaurants, trips, activities, gifts, books). Use before any open-ended recommendation.

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, well-structured instruction-only skill that names the exact tools to use for context gathering, live-fact verification, and recording suggestions, with an explicit anti-repeat rule. Minor gaps in call syntax and failure handling keep actionability and workflow clarity at 4; everything else is clean.

DimensionReasoningScore

Conciseness

Every line carries non-obvious, project-specific guidance (tool names like "search_web_grounded", "recall", and the AGENTS.md logging convention) with zero padding and no explanation of concepts Claude already knows. This matches "Lean and efficient; assumes Claude's competence; every token earns its place".

5 / 5

Actionability

Concrete tools are named for each step ("`list_threads` and `read_thread` on `voice_agent`", "`recall`", "`search_web_grounded` or `search_maps_grounded`") and the recording step is specific ("update `AGENTS.md` (e.g., 'Suggested so far')"), but no example call syntax or output handling is shown. Mostly executable guidance with minor gaps matches 4 rather than the copy-paste-ready 5.

4 / 5

Workflow Clarity

The three steps (check prior context → select options → record suggestions) are clearly sequenced, and "Verify live facts (hours, prices, availability)" acts as a checkpoint, plus an explicit rule for re-suggesting past favorites. However there is no guidance for what to do when a verification fails or sources conflict, matching "Clear sequence with most checkpoints present; minor validation gaps" rather than 5's explicit feedback loops.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references (no references/, scripts/, or assets/ files exist in the bundle), and is well-organized with numbered steps, bold labels, and sub-bullets. Per the simple-skill guideline, this organization earns 5.

5 / 5

Total

18

/

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 clearly communicates both what the skill does and when to use it, with an explicit "Use before" clause and a well-scoped, distinct niche. Its main weakness is specificity — the stated actions stay abstract and common natural trigger phrasings like "suggest" or "ideas" are missing.

Suggestions

List the concrete actions the skill performs (e.g., "check past threads for prior suggestions, filter out repeats, verify current hours and prices, log new suggestions") instead of the abstract "suggest options that fit the user" to raise specificity.

Sharpen the when-clause with natural user phrasings, e.g., "Use when the user asks for suggestions, ideas, or recommendations (e.g., 'where should we eat?', 'gift ideas')" instead of "any open-ended recommendation".

Consider adding a synonym for "recommendation" such as "suggestions" or "ideas" to the trigger terms so the description matches how users actually phrase the request.

DimensionReasoningScore

Specificity

"How to suggest options that fit the user and don't repeat earlier ones" names the domain and two behaviors, but they remain abstract — no concrete actions like checking past threads or verifying hours are listed. This matches the anchor "Names domain and 1-2 concrete actions, but not comprehensive"; it falls short of 4, which requires several specific listed actions.

3 / 5

Completeness

Both parts are present: what ("How to suggest options that fit the user and don't repeat earlier ones") and when ("Use before any open-ended recommendation"). The when-clause is explicit but leans on the abstract "open-ended" rather than concrete trigger phrases users would say, matching the 4 anchor ("'when' could be more explicit or specific") rather than 5.

4 / 5

Trigger Term Quality

"recommendation" plus the domain list "meals, restaurants, trips, activities, gifts, books" gives good natural keyword coverage, but common user phrasings like "suggest", "ideas", or "where should we eat" are absent. Good coverage with a few natural terms missing matches 4, short of the synonym-complete 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The fresh-recommendations niche is clearly scoped by the enumerated domains ("meals, restaurants, trips, activities, gifts, books") and a distinct trigger, giving minimal conflict risk with other skills. This matches the 5 anchor ("Clear niche with distinct triggers") and is more focused than the 4 anchor's broad "Works with PDF and Word document files".

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

google/adk-samples

Path

core/python/adk-voice-agent/sandbox/skills/recommendations/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.