presentation-hook

Creates engaging opening statements and powerful closings for medical.

Quality

42%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/presentation-hook/SKILL.md

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body contains genuine skill-specific content (parameters, output format, a working script) but is heavily padded with generic template sections and suffers from mismatches between documented and actual script behavior. It is more verbose than this simple skill warrants.

Suggestions

Remove the generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) that are not specific to hook generation.

Make the documented commands match the script: either add argparse so '--help' and CLI inputs work, or correct the examples and drop references to the nonexistent CONFIG block.

Replace the awkward 'See ## X above' cross-references and the hardcoded dates with concise, skill-specific guidance.

Dimension	Reasoning	Score
Conciseness	The ~190-line body for a simple single-task skill is padded with generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template), awkward cross-references ('See ## Features above'), and hardcoded time-sensitive dates, explaining process concepts Claude already knows.	1 / 3
Actionability	A real executable script, an input-parameters table, and an output-format spec provide concrete guidance, but documented usage does not match the actual script (it references '--help' and a 'CONFIG block' that do not exist and main() uses hardcoded inputs rather than a CLI).	2 / 3
Workflow Clarity	A numbered Workflow, a py_compile Quick Check, and an Error Handling fallback are present, but the core workflow steps are generic process boilerplate unrelated to generating a hook and there is no validation that the generated output is correct.	2 / 3
Progressive Disclosure	References to references/ and scripts/main.py are signaled and one level deep, but references/guidelines.md is near-empty (three bullet topics) and the body keeps heavy generic content inline rather than splitting it out.	2 / 3
	Total	7 / 12 Passed

Description

50%

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 conveys a recognizable purpose but is mediocre across the board: it lacks an explicit use-when trigger, relies on vague qualifiers, and omits natural trigger-term variations. It is distinguishable but not sharply so.

Suggestions

Add an explicit trigger clause, e.g. 'Use when preparing opening or closing remarks for a medical presentation or speech.'

Replace fluffy qualifiers ('engaging', 'powerful') with concrete capabilities and add natural terms users would say (presentation, speech, talk, opening, closing).

Tighten the domain phrasing so 'for medical' becomes a natural trigger such as 'for medical presentations and healthcare talks'.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('opening statements' and 'closings' for medical), but the qualifiers 'engaging' and 'powerful' are vague and it does not enumerate a comprehensive set of actions.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' clause or equivalent trigger, so the 'when' is missing; per the rubric a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	'opening statements' and 'closings' are relevant keywords, but common natural variations ('presentation', 'speech', 'talk', 'opening', 'closing') are missing and the phrase 'for medical' reads as awkward rather than a user-spoken trigger.	2 / 3
Distinctiveness Conflict Risk	The medical-presentation niche gives it some specificity, but the generic phrasing and absence of explicit triggers means it could still overlap with general writing or speaking skills.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Commit: 7cc5680

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.