poi-discovery-briefing

Extracts specific local activity recommendations and sentiment from travel vlogs into a shareable HTML BD report.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./python/agents/youtube-analyst/youtube_analyst/skills/poi-discovery-briefing/SKILL.md

Quality

Content

57%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 skill is a well-structured, single-purpose workflow that names concrete tools, but it lacks executable code examples for most steps and any validation before its outward-facing publish step, capping actionability and workflow clarity at 3.

Suggestions

Add a short executable HTML template and an example publish_file call so the report step is copy-paste ready.

Insert a validation checkpoint before publishing (e.g. confirm the HTML renders and the returned URL is reachable) to lift workflow clarity above the batch/destructive cap.

Trim explanatory narration (e.g. 'Travel vloggers often list 10+ activities...', 'to make it visually appealing') to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient prose with concrete tool names, but includes unnecessary narration like 'Travel vloggers often list 10+ activities in a single video' and 'to make it visually appealing', fitting the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean level-4 example.	3 / 5
Actionability	Names the exact tool to use at each step and gives one concrete call (publish_file with content= and filename=), but most steps are 'Use X to do Y' without call syntax or an HTML template, fitting 'some concrete guidance but incomplete; missing key details'; not 4 because the bulk lacks executable examples.	3 / 5
Workflow Clarity	Six steps are clearly sequenced, but the workflow is a batch operation (2-3 vlogs, multiple comments) ending in an outward-facing publish with no validation checkpoint (e.g. verify HTML before publishing, confirm the returned URL), so per the rubric it is capped at 3.	3 / 5
Progressive Disclosure	The body is under 50 lines, single-purpose, with no need for external references, and is organized into a clear Objective plus numbered Execution Steps with bold labels, qualifying for 5 under the simple-skill exception.	5 / 5
	Total	14 / 20 Passed

Description

58%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 states what the skill does with concrete, domain-specific actions, but omits any 'Use when...' trigger guidance, capping completeness and trigger-term quality. It is distinctive but would benefit from explicit trigger phrases.

Suggestions

Add an explicit trigger clause, e.g. 'Use when researching local activities around a POI from travel vlogs, or when the user asks for things to do near a destination.'

Include common natural synonyms users say ('things to do', 'vlog', 'points of interest') to broaden trigger coverage.

Optionally surface the HTML report / publish deliverable more explicitly as a 'when' cue (e.g. 'Use when an OTA BD team needs a shareable activity briefing').

Dimension	Reasoning	Score
Specificity	Names the domain (travel vlogs/POI) and several concrete actions — 'Extracts specific local activity recommendations and sentiment' and packaging 'into a shareable HTML BD report' — matching the 'lists several specific actions; minor gaps' anchor; not 5 because coverage is narrow relative to the full workflow.	4 / 5
Completeness	Has a clear 'what' (extract recommendations and sentiment into an HTML BD report) but no 'Use when...' or equivalent trigger clause; per the rubric a missing trigger clause caps completeness at 3, matching the 'clear what but when missing or only weakly implied' anchor.	3 / 5
Trigger Term Quality	Contains relevant natural terms ('travel vlogs', 'local activity recommendations', 'sentiment') but misses common variations users would say ('things to do', 'vlog', 'POI', 'points of interest'), fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The niche (travel-vlog POI activity extraction for BD) is distinctive and unlikely to trigger for unrelated skills, matching 'mostly distinct; minor overlap risk'; not 5 because the absence of explicit triggers leaves slight overlap with general travel-research skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: python/agents/youtube-analyst/youtube_analyst/skills/poi-discovery-briefing/SKILL.md
Commit: 2d0c272

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.