semantic-consistency-auditor

Use semantic consistency auditor for academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries.

Quality

52%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/semantic-consistency-auditor/SKILL.md

Quality

Content

65%

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

The content is highly actionable with concrete CLI/config/IO examples, but it is inflated with redundant cross-reference sections, concept re-explanations, and templated boilerplate, and its workflow steps are generic rather than tied to concrete validation checkpoints.

Suggestions

Remove the redundant pointer sections ('Example Usage', 'Implementation Details', 'Dependencies') that only say 'See ## X above', and collapse the duplicate 'Quick Check' and 'Audit-Ready Commands' compile-command blocks into one.

Move the Algorithms explainer, full Configuration YAML, and detailed Input/Output JSON schemas into reference files under references/, keeping SKILL.md a lean overview with one-level-deep links.

Replace the abstract 'Workflow' steps with a concrete evaluation sequence tied to the actual script (e.g. py_compile -> run main.py with validated inputs -> inspect results.json against thresholds -> on failure report the missing input and fallback).

Dimension	Reasoning	Score
Conciseness	The body contains real useful content but is padded with redundant cross-references ('See ## Usage above', 'See ## Workflow above'), duplicate compile-command sections, two '## References' sections, concept explanations of BERTScore/COMET Claude already knows, and templated boilerplate ('Evaluation Criteria', 'Output Requirements', 'Response Template').	2 / 3
Actionability	It provides concrete, copy-paste-ready CLI commands with real arguments, a full configuration YAML, Python API usage, and detailed input/output JSON schemas, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The 'Workflow' steps are abstract and templated ('Confirm the user objective', 'Validate that the request matches the documented scope') with no concrete validation checkpoint on the actual evaluation run, and the batch operation lacks an explicit validate-output feedback loop.	2 / 3
Progressive Disclosure	The bundle is real and one-level-deep (references/audit-reference.md is linked, scripts/main.py is referenced), but SKILL.md is a ~12KB monolith with Algorithms, Configuration, Usage, and I/O format details inline that could be split into reference files.	2 / 3
	Total	9 / 12 Passed

Description

40%

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 templated and circular: it names the skill and a generic academic-writing niche but never states the concrete capability (BERTScore/COMET-based semantic consistency evaluation of clinical notes) and leans on abstract qualities rather than natural trigger terms.

Suggestions

Replace the circular restatement of the skill name with the concrete capability, e.g. 'Evaluates semantic consistency between AI-generated clinical notes and expert gold standards using BERTScore and COMET.'

Add natural trigger terms users would actually say, such as 'clinical notes', 'semantic evaluation', 'BERTScore', 'COMET', or 'gold-standard comparison'.

Tie the 'when' clause to the real use case rather than generic academic-writing qualities, e.g. 'Use when comparing AI-generated clinical notes against gold standards for semantic entailment.'

Dimension	Reasoning	Score
Specificity	The description names a domain ('academic writing workflows') but lists only abstract qualities ('structured execution, explicit assumptions, and clear output boundaries') rather than any concrete actions, matching the 'vague or no actions; abstract language' anchor.	1 / 3
Completeness	A 'when' trigger is present ('for academic writing workflows that need...'), but the 'what' is circular — it merely restates the skill name ('semantic consistency auditor') without describing the actual capability, so it does not clearly answer both.	2 / 3
Trigger Term Quality	'academic writing' is a natural user term, but 'structured execution', 'explicit assumptions', and 'clear output boundaries' are not phrases users say, and the real use case (clinical-note semantic evaluation) is absent, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	'academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries' is generic enough to overlap many academic-writing skills and also misrepresents the skill's clinical-evaluation purpose, so conflict risk remains.	2 / 3
	Total	7 / 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
Path: scientific-skills/Academic Writing/semantic-consistency-auditor/SKILL.md
Commit: f5ef65b

Reviewed: 1 day 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.