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.
66
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/patent-assistant/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description that clearly defines its domain (patent/R&D), provides explicit 'use when' triggers, and occupies a distinct niche. Its main weakness is that the capability descriptions are somewhat high-level—listing more granular actions (e.g., drafting claims, generating prior art summaries, structuring technical specifications) would improve specificity.
Suggestions
Add more granular concrete actions such as 'draft patent claims, generate prior art summaries, structure technical specifications, compare inventions against existing patents' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (patent/R&D) and some actions like 'patent technical disclosure drafting' and 'patent/novelty search analysis,' but it doesn't list multiple concrete granular actions (e.g., generating claims, drafting abstracts, comparing prior art). The actions are somewhat high-level. | 2 / 3 |
Completeness | Clearly answers both 'what' (assists with patent technical disclosure drafting and patent/novelty search analysis) and 'when' (explicit 'use when' clause listing four trigger scenarios: write a patent disclosure, structure an invention description, search related patents, or assess novelty). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'patent disclosure,' 'invention description,' 'search related patents,' 'assess novelty,' 'R&D teams,' 'novelty search.' These cover the main ways a user would phrase requests in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Patent disclosure drafting and novelty search analysis is a very specific niche. The trigger terms are highly domain-specific and unlikely to conflict with other skills unless there are multiple patent-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly verbose and monolithic, embedding a full example disclosure document and extensive implementation details that bloat the token budget significantly. While it provides some concrete CLI commands and a useful output template, the workflows lack validation checkpoints and the content organization would benefit greatly from splitting into referenced sub-files. The skill explains too many concepts Claude already understands and has significant redundancy between sections.
Suggestions
Move the full example disclosure template to a separate file (e.g., DISCLOSURE_TEMPLATE.md) and reference it from the main skill, keeping only a brief summary inline.
Eliminate redundancy between 'When to Use', 'Key Features', and 'Implementation Details' sections—consolidate into a single concise workflow section.
Add explicit validation checkpoints to workflows: e.g., 'Verify all 5 information-collection questions are answered before generating disclosure' and 'If search returns 0 results, broaden keywords and retry'.
Move the IPC reference table and detailed CLI platform options to a separate reference file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose. The massive example output (the full disclosure template) takes up enormous token space and could be referenced externally. The 'When to Use' and 'Key Features' sections heavily overlap. Explanations of patent concepts (what IPC is, what prior art means) are unnecessary for Claude. The dependency section hedges excessively with vague language. | 1 / 3 |
Actionability | The CLI commands for patent_search.py are concrete and executable, and the disclosure template provides a clear output format. However, the actual generation workflow is more descriptive than instructive—it describes what to do conceptually rather than giving Claude precise, executable steps. The script itself is referenced but its implementation is uncertain ('may vary depending on how scripts/patent_search.py is implemented'). | 2 / 3 |
Workflow Clarity | The disclosure generation workflow has clear numbered steps (information collection → synthesis → optimization), and the search workflow is sequenced. However, there are no validation checkpoints—no step to verify the disclosure is complete before presenting it, no error handling for failed searches, and no feedback loops for iterating on incomplete inventor input. | 2 / 3 |
Progressive Disclosure | Everything is crammed into a single monolithic file with no references to external files. The full example disclosure output (~60 lines of markdown) should be in a separate template file. The IPC table, CLI usage details, and implementation workflows could all be split out. The content is a wall of text with no navigation strategy. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
8277276
- 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.