reagent-substitute-scout

Find validated alternative reagents based on literature citation data.

Quality

55%

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/reagent-substitute-scout/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 content is highly actionable with concrete commands, examples, and a validated workflow, but it is weighed down by redundant and templated boilerplate that inflates the body. Progressive disclosure is adequate yet leaves reference-worthy detail inlined rather than split out.

Suggestions

Remove the redundant Description/Features/Key Features overlap and the generic Lifecycle/Evaluation-Criteria/Security-Checklist/Response-Template boilerplate that does not advance the skill's actual operation.

Move the full Configuration JSON, Output Format examples, and Scoring Algorithm into a reference file, keeping SKILL.md a lean overview that links to them.

Reconcile the inconsistent command paths (skills/reagent-substitute-scout/scripts/main.py vs scripts/main.py vs the cd "20260318/…" path) into one consistent invocation form.

Dimension	Reasoning	Score
Conciseness	The 363-line body is noticeably verbose: redundant When-to-Use/Description/Features sections, generic templated Lifecycle/Evaluation-Criteria/Security-Checklist/Response-Template boilerplate, and odd "See `## X` above" cross-references add padding without actionable value.	2 / 5
Actionability	Provides concrete executable commands (py_compile, --help, --reagent/--cas/--formula/--format/--limit/--verbose), a full config JSON, output-format examples, and the scoring formula, with only minor path inconsistencies (skills/… vs scripts/main.py vs cd "20260318/…").	4 / 5
Workflow Clarity	The 5-step Workflow sequences scope confirmation, validation/stop-early, packaged execution, structured return, and a fallback path, plus a py_compile pre-check; it lacks an explicit validate→fix→retry feedback loop on script output.	4 / 5
Progressive Disclosure	Real one-level-deep references (audit-reference.md, scripts/main.py) are clearly signaled and linked, but substantial detail (full configuration JSON, output-format examples, scoring algorithm, data sources) is inlined in SKILL.md and the single reference file is thin.	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 clear, specific purpose but omits any explicit "when to use" trigger guidance and relies on a single action verb, leaving it competent yet incomplete. Trigger terms are domain-appropriate but lack natural synonyms a researcher would actually say.

Suggestions

Add an explicit 'Use when…' clause naming concrete trigger phrases (e.g., reagent discontinued, out-of-stock reagent, need a substitute reagent).

Expand beyond the single 'Find' action to list the concrete capabilities (parse reagent identifiers, score alternatives by citation data, generate a substitute report).

Include natural synonyms such as 'substitute reagent', 'replace reagent', and 'reagent alternative' alongside 'alternative reagents'.

Dimension	Reasoning	Score
Specificity	Names the domain (alternative reagents) and one concrete action ("Find validated alternative reagents based on literature citation data"), but lists only that single action rather than multiple specific capabilities.	3 / 5
Completeness	The description gives a clear "what" but provides no "Use when…" trigger guidance, so per the rubric cap completeness cannot exceed 3.	3 / 5
Trigger Term Quality	Relevant keywords like "reagent", "alternative reagents", and "literature citation data" are present, but common natural synonyms users would say (substitute, replace, out-of-stock, swap) are missing.	3 / 5
Distinctiveness Conflict Risk	The reagent-substitution niche is specific and unlikely to trigger unrelated skills, but the phrasing is narrowly academic with minor overlap risk against other literature-analysis skills.	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/reagent-substitute-scout/SKILL.md
Commit: 63c61d3

Reviewed: 8 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.