CtrlK
BlogDocsLog inGet started
Tessl Logo

patent-assistant

Assists R&D teams with patent technical disclosure drafting and patent/novelty search analysis; use when users ask to write a patent disclosure, structure an invention description, search related patents, or assess novelty.

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/patent-assistant/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 is well-structured and actionable, with executable search commands and a concrete disclosure template backed by real bundle scripts. The main weaknesses are mild verbosity from the long example and section overlap, and an unsurfaced bundle script plus a missing output-validation checkpoint.

Suggestions

Tighten conciseness by trimming the ~50-line full disclosure example to a condensed skeleton and removing the overlap between 'Key Features' and 'Implementation Details'.

Surface scripts/generate_disclosure.py with an executable usage example (as done for patent_search.py) so Claude knows the scripted disclosure-generation path exists.

Add an explicit validation/review checkpoint to the disclosure-generation workflow (e.g. 'review the generated disclosure against the information checklist before delivering') to lift workflow clarity.

DimensionReasoningScore

Conciseness

The body does not over-explain concepts Claude already knows and relies on actionable templates/commands, but the ~50-line full example disclosure and overlap between the 'Key Features' and 'Implementation Details' sections could be tightened; it sits above the verbose 2 anchor yet short of the lean 4.

3 / 5

Actionability

CLI examples are copy-paste ready and reference the real scripts/patent_search.py with concrete flags (--limit, -s all -p -a), and a full disclosure template is given; the gap keeping it from 5 is that scripts/generate_disclosure.py exists in the bundle but is never invoked or shown.

4 / 5

Workflow Clarity

Both the disclosure-generation and patent-search workflows are laid out as numbered sequences, and the disclosure workflow includes an 'ask if missing' information-collection checkpoint; it is not a 5 because there is no explicit validate-output checkpoint before delivering the generated disclosure.

4 / 5

Progressive Disclosure

Sections are well-organized with clear headers and the search script is properly referenced, but scripts/generate_disclosure.py is present in the bundle yet never surfaced or linked from the body, a minor organization gap that keeps it from 5.

4 / 5

Total

15

/

20

Passed

Description

87%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.

A strong, well-formed description: third-person voice, a clear statement of capability, and an explicit 'use when' clause with concrete natural triggers tied to a distinct patent niche. The only minor weakness is slightly narrower trigger-term/synonym coverage.

DimensionReasoningScore

Specificity

Names the patent domain and several concrete actions ('patent technical disclosure drafting', 'patent/novelty search analysis', 'write a patent disclosure', 'structure an invention description', 'search related patents', 'assess novelty'), with only minor coverage gaps; not a 5 because some actions are near-duplicates across the two clauses rather than a comprehensive, distinct set.

4 / 5

Completeness

It explicitly states what it does ('Assists R&D teams with patent technical disclosure drafting and patent/novelty search analysis') and when to use it with concrete trigger phrases, matching the 5 anchor that requires both an explicit 'what' and an explicit 'use when'.

5 / 5

Trigger Term Quality

The 'use when users ask to write a patent disclosure, structure an invention description, search related patents, or assess novelty' clause supplies natural phrases a user would actually say; a few common synonyms (e.g. 'invention disclosure', 'prior art search', 'patent application') are missing, so it falls short of the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Patent disclosure drafting and novelty search is a clear, narrow niche with triggers specific to patent work, giving minimal overlap risk with other skills; this fits the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
Reviewed

Table of Contents

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.