q-and-a-prep-partner

Predict challenging questions for presentations and prepare structured responses.

Quality

58%

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/q-and-a-prep-partner/SKILL.md

Quality

Content

50%

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 executable commands and a real script, but it is bloated with generic boilerplate, redundant command repetitions, and broken cross-references, and its workflow/references are only adequately structured.

Suggestions

Remove or relocate generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Test Cases, Lifecycle Status, Response Template) that adds no skill-specific value; keep only Q&A-specific guidance.

Fix the broken "See ## Prerequisites/Usage/Workflow above" references and deduplicate the repeated py_compile/--help commands into one validation section.

Move the "Next Review Date: 2026-03-06" and any version/date-sensitive content into a clearly labeled lifecycle/deprecated section, or remove it.

Tighten the Workflow with a concrete output-validation checkpoint (e.g., verify generated questions are topic-relevant before returning) and an explicit fix-and-retry loop.

Dimension	Reasoning	Score
Conciseness	The ~200-line body is padded with generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Test Cases, Lifecycle Status, Response Template) plus triplicated compile/help commands and broken "See ## ... above" cross-references; a time-sensitive "Next Review Date: 2026-03-06" sits outside any deprecated section, all of which is unnecessary context rather than lean guidance.	1 / 3
Actionability	Provides concrete, copy-paste-ready commands (py_compile, --help, and real --abstract/--topic/--field/--audience invocations) with a documented parameter list and a complete executable main.py, satisfying the fully-executable anchor.	3 / 3
Workflow Clarity	The Workflow lists a clear sequence with a stop-early scope check (step 2) and a fallback (step 5), but steps are generic boilerplate and there is no explicit validate->fix->retry feedback loop or output-verification checkpoint, fitting the checkpoints-implicit anchor.	2 / 3
Progressive Disclosure	The single reference (references/audit-reference.md) is real, one-level-deep, and well-signaled via a References link, but the SKILL.md itself is a monolithic body with large inline generic sections that should be split out or removed, matching the some-structure-but-inline-content anchor.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 concise, third-person, and states a clear niche with two concrete actions, but it lacks an explicit "Use when..." trigger clause and broader keyword variations, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. "Use when preparing for a presentation, talk, or defense Q&A, or when the user asks to anticipate audience questions."

Broaden trigger terms to include natural variations like "Q&A", "talk", "defense", "audience questions", and "slides".

Dimension	Reasoning	Score
Specificity	Names two concrete actions — "Predict challenging questions" and "prepare structured responses" — with a clear object (presentations), matching the multiple-specific-actions anchor rather than the single-domain score-2 example.	3 / 3
Completeness	Clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance, which the guidelines cap at 2; the "when" is only implied via "for presentations".	2 / 3
Trigger Term Quality	Includes relevant natural terms ("challenging questions", "presentations", "structured responses") but misses common variations a user might say ("Q&A", "talk", "defense", "audience questions", "slides"), so coverage is partial rather than broad.	2 / 3
Distinctiveness Conflict Risk	The presentation Q&A-prep niche is specific and distinct; "predict challenging questions for presentations" is unlikely to fire for unrelated skills, fitting the clear-niche anchor.	3 / 3
	Total	10 / 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.