target-novelty-scorer

Score the novelty of biological targets through literature mining and.

Quality

51%

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/Evidence Insight/target-novelty-scorer/SKILL.md

Quality

Content

50%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 body is actionable with concrete commands, examples, and a parameter table, but it is bloated with redundant cross-references and generic boilerplate, and its workflow validation checkpoints are implicit. Tightening and moving peripheral material to reference files would materially improve it.

Suggestions

Remove the redundant 'See ## X above for related details' pointers and the duplicated Description block; consolidate to one statement of each idea.

Replace the hardcoded '/Users/z04030865/.openclaw/workspace/...' path in Basic Usage with a portable relative path so examples run as written.

Move the Risk Assessment, Security Checklist, Lifecycle, and Evaluation Criteria boilerplate into a reference file and weave explicit validation checkpoints (e.g. py_compile then --help) directly into the Workflow steps.

Dimension	Reasoning	Score
Conciseness	The ~270-line body is noticeably verbose with padded sections (repeated 'See ## X above for related details' pointers, a duplicated Description block, and generic Risk/Security/Lifecycle boilerplate) that do not earn their tokens.	2 / 5
Actionability	Concrete executable commands ('python -m py_compile scripts/main.py', 'python scripts/main.py --target "PD-L1"'), a full parameter table, and a JSON output example give mostly copy-paste-ready guidance, with the hardcoded '/Users/z04030865/...' path as a minor gap.	4 / 5
Workflow Clarity	A 5-step Workflow and an Example run plan provide a sequence and a fallback path, but the workflow steps are abstract and validation checkpoints are implicit rather than woven into the sequence.	3 / 5
Progressive Disclosure	Structure exists with clear section headers and a one-level-deep, signaled References link to references/audit-reference.md, but large amounts of content (scoring criteria, output format, risk/security checklists) that could live in separate files are inlined in SKILL.md.	3 / 5
	Total	12 / 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 identifies a specific niche and one concrete action but is truncated and lacks any explicit 'when to use' trigger guidance. It is usable but incomplete and would benefit from completion and a trigger clause.

Suggestions

Finish the truncated sentence so the description is grammatically complete and lists the full set of concrete actions.

Add an explicit 'Use when ...' clause naming natural trigger phrases a user would say (e.g. 'Use when assessing how novel a biological target is, or when ranking targets by research novelty').

Include common synonyms or file/format cues (e.g. PubMed, PMC, gene symbol) to strengthen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('biological targets') and one concrete action ('Score the novelty ... through literature mining'), matching the anchor for naming a domain plus 1-2 actions, though it stops at that single action.	3 / 5
Completeness	A 'what' is identifiable (score novelty via literature mining) but it is truncated mid-sentence ('...mining and.') and there is no 'Use when...' clause, so completeness is capped at 3 per the missing-trigger guidance.	3 / 5
Trigger Term Quality	Terms like 'biological targets', 'literature mining', and 'novelty' are domain-relevant but lean toward technical jargon with missing natural variations a user would actually say.	3 / 5
Distinctiveness Conflict Risk	'Score the novelty of biological targets through literature mining' carves a clear niche with limited overlap risk, though distinct trigger phrases are absent.	4 / 5
	Total	13 / 20 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/Evidence Insight/target-novelty-scorer/SKILL.md
Commit: 63c61d3

Reviewed: 5 hours 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.