icd10-cpt-coding-assistant

Parse clinical notes and recommend ICD-10-CM diagnosis codes and CPT procedure codes with confidence scoring. Cross-references diagnoses with procedure codes, generates alternatives for medium-confidence matches, and produces structured coding reports with human-review flags.

Quality

74%

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/Other/icd10-cpt-coding-assistant/SKILL.md

Quality

Content

73%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 has a strong, checkpointed workflow and concrete executable commands, but is weighed down by generic boilerplate sections and a Parameters table that documents CLI flags absent from the actual script. Tightening boilerplate and reconciling the parameter list with scripts/main.py would raise the score.

Suggestions

Remove or condense the Risk Assessment, Security Checklist, Evaluation Criteria, and Lifecycle Status boilerplate, and delete the redundant 'Quick Check' section that duplicates 'Audit-Ready Commands'.

Reconcile the Parameters table with scripts/main.py: the script only exposes --input, --format, and --interactive, so --output, --confidence-threshold, and --include-alternatives should be implemented or removed.

Complete the References section to list all bundle files (add code_examples.md, common_mappings.json, cpt_guidelines.md, icd10_guidelines.md) and remove the reference to a non-existent requirements.txt.

Dimension	Reasoning	Score
Conciseness	Core sections (Workflow, Parameters, Output Format) are efficient, but several padded boilerplate sections — Risk Assessment table, Security Checklist, Evaluation Criteria/Test Cases, Lifecycle Status — add tokens without aiding execution, and 'Quick Check' duplicates 'Audit-Ready Commands'.	3 / 5
Actionability	Concrete copy-paste commands ('python -m py_compile scripts/main.py', 'python scripts/main.py --input ... --format json') and a matching programmatic CodingAssistant.analyze example are present, but the Parameters table documents --output, --confidence-threshold, and --include-alternatives flags that do not exist in scripts/main.py, a minor accuracy gap.	4 / 5
Workflow Clarity	The 5-step Workflow is explicitly sequenced with Input→Output annotations per step and an explicit validation checkpoint in step 4 ('⛔ Checkpoint: Present low-confidence codes (<0.7) to user for manual review; confirm all codes before output').	5 / 5
Progressive Disclosure	Structure is good: bulk logic lives in scripts/main.py and code tables in references/, with a References section signaling one-level-deep files; however the References section lists only 3 of the 7 actual reference files and omits code_examples.md, common_mappings.json, cpt_guidelines.md, and icd10_guidelines.md.	4 / 5
	Total	16 / 20 Passed

Description

75%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 and clearly occupies a distinct medical-coding niche, but it omits any explicit 'when to use' trigger guidance, which caps its completeness. Adding a 'Use when...' clause would lift the weakest dimension.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user needs ICD-10 or CPT codes from clinical notes, chart documentation, or billing-ready coding suggestions.'

Add common user synonyms like 'medical coding', 'billing codes', or 'diagnosis coding' to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Parse clinical notes and recommend ICD-10-CM diagnosis codes and CPT procedure codes', 'Cross-references diagnoses with procedure codes', 'generates alternatives for medium-confidence matches', 'produces structured coding reports with human-review flags' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	The 'what' is explicit and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms like 'ICD-10-CM diagnosis codes', 'CPT procedure codes', 'clinical notes', and 'confidence scoring' cover what a user would say, but common synonyms such as 'billing codes' or 'medical coding' are absent, so it stops short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	The medical-coding niche (ICD-10-CM diagnosis and CPT procedure codes with confidence scoring) is highly specific with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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/Other/icd10-cpt-coding-assistant/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.