target-novelty-scorer

Score the novelty of biological targets through literature mining and.

Quality

63%

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

Quality

Content

56%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 delivers genuinely actionable core content — a runnable script with concrete CLI examples, a full parameter table, explicit scoring criteria, and a realistic output format — wrapped in a heavily padded, duplicated document. Boilerplate meta-sections and broken/hardcoded paths dilute token efficiency, and most detail that belongs in references is inlined in SKILL.md.

Suggestions

Cut the generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) or move them into a reference file; also merge the duplicated Installation/Prerequisites and remove the body "## Description" that repeats the frontmatter.

Fix the broken paths: replace the personal absolute path (`cd /Users/z04030865/...`) and the nonsensical `cd "20260318/scientific-skills/..."` with a portable relative path like `cd <skill-dir>`, and correct the misdirected cross-references ("See `## Usage` above" points to a section below).

Consolidate the five overlapping process sections (Example run plan, Implementation Details, Workflow, Output Requirements, Response Template) into the single Workflow section so the execution sequence and its validation checkpoints are followed in one place.

Dimension	Reasoning	Score
Conciseness	Many padded boilerplate sections unrelated to the task knowledge ("## Risk Assessment", "## Security Checklist", "## Evaluation Criteria", "## Lifecycle Status", "## Output Requirements", "## Response Template") plus duplication ("## Description" repeats the frontmatter; "## Installation" and "## Prerequisites" both say `pip install -r requirements.txt`) — anchor 2. Not 1 because the core sections (Scoring Criteria, Parameters, Output Format) are genuine task content with no explanation of concepts Claude already knows.	2 / 5
Actionability	Concrete executable guidance is present: `python scripts/main.py --target "PD-L1"`, a full parameter table, a realistic JSON output example, and `python -m py_compile scripts/main.py`. Not 5 because Usage hardcodes a personal absolute path (`cd /Users/z04030865/.openclaw/...`) and a nonsensical relative cd (`cd "20260318/scientific-skills/..."`), and the run plan hedges ("Edit the in-file CONFIG block or documented parameters if the script uses fixed settings").	4 / 5
Workflow Clarity	The "## Workflow" section gives a clear 5-step sequence with explicit stop-early validation, a "Quick Check" (py_compile), a fallback step, and dedicated "## Error Handling" guidance — anchor 4. Not 5 because the sequence is fragmented across redundant overlapping sections (Example run plan, Implementation Details, Output Requirements, Response Template) and cross-references point the wrong way ("See `## Usage` above" when Usage is below); not 3 because validation checkpoints and error-recovery feedback are genuinely present.	4 / 5
Progressive Disclosure	`references/audit-reference.md` is a real, clearly signaled, one-level-deep reference and `scripts/main.py` exists, but the ~277-line body inlines substantial content that belongs in separate reference files (security checklist, risk assessment, evaluation criteria, lifecycle metadata) — anchor 3 ("content that should be separate is inline"). Not 4 given the monolithic inline bulk relative to the thin single reference.	3 / 5
	Total	13 / 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 states a concrete, fairly distinctive purpose but is truncated mid-sentence ("...literature mining and."), which cuts off whatever actions or trigger clauses followed, and it entirely lacks a "Use when..." trigger. It communicates the core capability but fails as a complete, self-contained trigger description.

Suggestions

Fix the truncated sentence: complete the description, e.g. "Score the novelty of biological targets through literature mining of PubMed and PubMed Central. Use when the user asks to assess a drug target's research popularity, uniqueness, or innovation potential."

Add natural trigger terms and synonyms users would say, such as "PubMed", "drug target", "target assessment", and "novelty score", so the skill triggers on common phrasings.

State the concrete actions the skill performs (retrieve literature, compute a 0-100 novelty score, analyze temporal trends, generate a report) to raise specificity from a single action to comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Score the novelty of biological targets" and "through literature mining" name the domain and one concrete action, but the sentence is truncated mid-clause ("...mining and."), so action coverage is visibly incomplete — anchor 3, not 4, which requires several listed actions with only minor gaps.	3 / 5
Completeness	A clear "what" is present ("Score the novelty of biological targets through literature mining") but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines. Not 2 because the "what" is concrete rather than vague.	3 / 5
Trigger Term Quality	"novelty", "biological targets", and "literature mining" are relevant keywords, but common variations users would naturally say (PubMed, drug target, target evaluation, research assessment) are missing and the truncation may have cut off additional trigger phrases — anchor 3.	3 / 5
Distinctiveness Conflict Risk	"Score the novelty of biological targets" carves a fairly distinct niche with only minor overlap risk against general literature-review or bibliometric skills — anchor 4 rather than 5 because the truncated description lacks the explicit trigger phrases that would fully distinguish it.	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: 686e09d

Reviewed: 13 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.