keyword-velocity-tracker

Calculate literature growth velocity and acceleration to assess research.

Quality

53%

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/keyword-velocity-tracker/SKILL.md

Quality

Content

53%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 pairs a genuinely detailed analytic spec (functions, I/O schemas, algorithm formulas, executable commands) with a large volume of generic templated boilerplate that pads the context without adding skill-specific value. Structure and references are reasonable, but the workflow lacks integrated validation checkpoints.

Suggestions

Remove or collapse the generic boilerplate sections (When to Use, Key Features, Implementation Details, Output Requirements, Response Template, Input Validation, Error Handling) that restate process discipline Claude already applies, keeping only skill-specific content.

Integrate the validation commands directly into the Workflow steps as explicit checkpoints (e.g. 'Validate: python -m py_compile scripts/main.py; only proceed on success') instead of listing them in a separate section.

Move the detailed spec (Functions, Input/Output tables, Algorithm Description, Stage Judgment Criteria) into a dedicated reference file under references/ and have SKILL.md link to it, tightening the overview.

Dimension	Reasoning	Score
Conciseness	The body carries substantial templated boilerplate (When to Use restating the description, Key Features, Implementation Details, Output Requirements, Response Template, Input Validation, Error Handling) that explains process discipline Claude already knows, fitting the noticeably-verbose anchor below the midpoint.	2 / 5
Actionability	Concrete executable commands (py_compile, --help, --keyword --data-file), a Python API example, input/output JSON schemas, and algorithm formulas give mostly copy-paste-ready guidance, with only minor gaps such as the speculative import path 'skills.keyword_velocity_tracker.scripts.main' that is asserted without verification.	4 / 5
Workflow Clarity	The Workflow section is a generic five-step prose list (confirm, validate, run, return, fallback) with validation commands living in a separate Audit-Ready Commands section rather than integrated as explicit checkpoints with feedback loops, matching the steps-present-but-checkpoints-implicit anchor.	3 / 5
Progressive Disclosure	Section headers organize the content and a real one-level-deep reference (references/audit-reference.md, correctly linked) plus scripts/main.py exist, though a good deal of spec detail (functions, I/O tables, algorithms) is inlined in SKILL.md rather than split out, leaving minor organization gaps.	4 / 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 names a concrete domain and two analytic actions but reads as terse jargon with no explicit trigger guidance, leaving the "when to use" question unanswered. It is distinguishable from other skills yet lacks the natural user phrasing and Use-when clause that the top anchors require.

Suggestions

Add an explicit 'Use when...' clause naming the trigger situations, e.g. 'Use when analyzing how a research field's publication volume is growing or maturing over time.'

Include natural user-facing terms and synonyms such as 'keyword trends', 'publication growth', and 'field lifecycle' alongside the technical velocity/acceleration vocabulary.

Spell out the deliverable concretely (e.g. 'returns growth rate, acceleration, development stage, and trend predictions') so the 'what' is comprehensive rather than two verbs.

Dimension	Reasoning	Score
Specificity	Quotes "Calculate literature growth velocity and acceleration" name the domain plus two concrete analytic actions, but coverage stops there with no further specific operations, matching the score-3 anchor of domain plus 1-2 actions.	3 / 5
Completeness	The description states a clear "what" (calculate velocity and acceleration) but contains no "Use when..." clause or equivalent trigger guidance, so per the rubric cap completeness cannot exceed 3.	3 / 5
Trigger Term Quality	Terms like "literature growth velocity", "acceleration", and "assess research" are relevant but technical; common natural phrasings users would actually say (e.g. "keyword trends", "publication growth") are missing, matching the some-keywords-but-missing-synonyms anchor.	3 / 5
Distinctiveness Conflict Risk	The literature-velocity/acceleration analytic niche is fairly specific and unlikely to conflict with unrelated skills, though the broad "assess research" tail introduces minor overlap risk, fitting the mostly-distinct anchor above the midpoint.	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/keyword-velocity-tracker/SKILL.md
Commit: 63c61d3

Reviewed: 10 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.