sds-msds-risk-scanner

Extract hazard codes and safety info from chemical safety datasheets.

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/sds-msds-risk-scanner/SKILL.md

Quality

Content

48%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 has a clear, validated workflow and a genuine reference file, but it is padded with redundant command blocks and generic boilerplate, and the actual extraction usage is left implicit behind `--help`.

Suggestions

Consolidate the repeated `py_compile` / `--help` commands into a single validation section to remove duplication.

Add a concrete, copy-paste extraction example (e.g. `python scripts/main.py --input acetone_sds.pdf --chemical acetone`) instead of relying only on `--help`.

Move or remove generic boilerplate (Lifecycle Status, Evaluation Criteria, Risk Assessment, Response Template) that is not specific to SDS/MSDS extraction.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the same `python -m py_compile scripts/main.py` / `--help` commands appear in Example Usage, Quick Check, and Audit-Ready Commands, alongside generic boilerplate (Lifecycle Status, Evaluation Criteria, Response Template, Risk Assessment) that adds tokens without SDS-specific value.	2 / 5
Actionability	Concrete, executable commands and real parameters/returns are present, but the core extraction task is delegated to `scripts/main.py --help` rather than shown with a runnable extraction example, leaving key usage details implicit.	3 / 5
Workflow Clarity	The Workflow section gives a clear 5-step sequence with explicit validation (step 2 stop-early) and a fallback/error-recovery loop (step 5, Error Handling), with only minor gaps in checkpoint specificity.	4 / 5
Progressive Disclosure	There is a real one-level-deep reference (references/audit-reference.md) clearly signaled in a References section, but large amounts of generic template content are inlined in SKILL.md that would be better split out or removed.	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 is specific to a clear niche and states concrete actions, but it lacks an explicit "when to use" trigger clause and misses common SDS/MSDS synonyms that users would naturally say.

Suggestions

Add a "Use when..." clause naming concrete triggers, e.g. "Use when the user mentions SDS, MSDS, safety data sheets, hazard codes, or chemical safety information."

Include common synonyms and file extensions (SDS, MSDS, .pdf) to improve trigger-term coverage.

Enumerate a couple more concrete actions (e.g. "extract H-codes and P-codes, summarize PPE recommendations") to push specificity higher.

Dimension	Reasoning	Score
Specificity	Names the domain (chemical safety datasheets) and 1-2 concrete actions ("Extract hazard codes and safety info"), but does not enumerate several specific actions like filling forms or converting formats, so it is not comprehensive.	3 / 5
Completeness	Has a clear "what" (extract hazard codes and safety info) but no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes relevant keywords ("chemical safety datasheets", "hazard codes", "safety info") but omits the most common synonyms/acronyms users actually say (SDS, MSDS) and file extensions, so coverage is partial.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (chemical safety datasheets / hazard codes) with distinct triggers and minimal conflict risk, though the lack of an explicit use-when clause leaves minor overlap with general document 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/sds-msds-risk-scanner/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.