CtrlK
BlogDocsLog inGet started
Tessl Logo

daily-briefing

Provides a high-signal briefing on events in a specific location and timeframe, backed by primary video sources and transcripts.

58

Quality

66%

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 ./python/agents/youtube-analyst/youtube_analyst/skills/daily-briefing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is a well-sequenced, appropriately concise, and largely actionable workflow that names the exact tools and parameters to use. Its main gaps are unspecified thresholds in the filtering step and the absence of explicit validation or fallback behavior when searches return nothing.

DimensionReasoningScore

Conciseness

The body is lean at roughly 30 lines with no explanations of concepts Claude already knows; only minor instances of over-explanation remain ('Do not rely solely on clickbait titles', 'aggressively apply the advanced filters'). It falls just short of the 5 anchor where every token earns its place.

4 / 5

Actionability

Guidance is concrete and specific — 'Use `search_youtube`', 'Pass the date from step 1 into `published_after`', "Pass the relevant country code to `region_code` (e.g., 'HK' for Hong Kong)", 'Use `get_video_transcript` on the top 2-3 news clips'. As an instruction-only skill absence of code is not penalized, but key details (result counts, engagement thresholds defining 'low-engagement spam') are unspecified, so it is not fully copy-paste-ready at the 5 level.

4 / 5

Workflow Clarity

A clear five-step sequence (Time Context, Locate, Filter & Rank, Ingest, Deliver) with an explicit filtering checkpoint ('Discard low-engagement spam, auto-generated news bot channels, or clickbait'). The operations are not destructive or batch, so the validation cap does not apply, but there are no explicit validation steps or error-recovery loops (e.g., what to do if no videos match the timeframe), which the 5 anchor requires.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and needs no external references; the steps are well-organized with bolded headers and sub-bullets. Per the rubric's guidance this earns a 5 — no bundle files exist to score against, and none are needed.

5 / 5

Total

17

/

20

Passed

Description

53%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 states a clear and fairly distinctive 'what' in third person, but omits any 'when to use' trigger guidance and misses the natural vocabulary (news, daily briefing, local events) users would employ. It is serviceable but incomplete, sitting at the midpoint of the scale.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks what recently happened in a specific place, wants a daily news/local-events briefing, or asks for news by video.'

Include natural synonyms users would say — "news", "daily briefing", "local news", "what's happening in X" — alongside the current domain terms.

Name one or two more concrete actions (e.g., searches video sources, ranks by engagement, summarizes transcripts) to move specificity beyond a single deliverable statement.

DimensionReasoningScore

Specificity

The description names the domain and deliverable concretely ("high-signal briefing on events in a specific location and timeframe, backed by primary video sources and transcripts") but lists only one or two actions rather than the multiple concrete actions of the top anchor. It is well above the generic 'Processes PDF files' level of the 2 anchor.

3 / 5

Completeness

The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the judging guidelines explicitly cap at 3.

3 / 5

Trigger Term Quality

Relevant keywords are present ("briefing", "events", "location", "timeframe", "video sources", "transcripts") but common natural phrases users would actually say — "news", "daily briefing", "what's happening in X", "local news" — are missing, matching the 3 anchor for missing common variations.

3 / 5

Distinctiveness Conflict Risk

The location/timeframe/video-source framing carves a fairly distinct niche with only minor overlap risk against generic news or search skills. It falls short of the 5 anchor because it lacks explicit, distinct trigger phrases.

4 / 5

Total

13

/

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
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.