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.
52
58%
Does it follow best practices?
Impact
—
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 well-constructed skill description with a clear 'use when' clause and strong trigger terms that cover the main user intents in the patent domain. Its main weakness is that the capability description could be more granular—listing specific concrete actions like claim drafting, prior art analysis, or abstract generation rather than high-level categories. Overall, it performs well for skill selection purposes.
Suggestions
Expand the capability list with more specific concrete actions, e.g., 'draft patent claims, generate invention abstracts, compare prior art, structure technical specifications' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (patent/R&D) and some actions like 'patent technical disclosure drafting' and 'patent/novelty search analysis,' but doesn't list multiple concrete granular actions (e.g., claim drafting, prior art comparison, abstract generation). 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,' 'write a patent disclosure,' 'structure an invention description.' These cover the main ways users 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 like 'patent disclosure,' 'novelty,' and 'invention description' are highly distinctive and unlikely to conflict with other 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 overly verbose and monolithic, explaining many concepts Claude already understands while cramming all content into a single large file. The CLI examples and disclosure template provide some actionable guidance, but the lack of validation steps, missing bundle files for referenced scripts, and absence of progressive disclosure significantly weaken the skill. The content reads more like product documentation than a concise, actionable skill instruction.
Suggestions
Cut the content by at least 50%: remove the 'Key Features' marketing section, trim the full example disclosure to just the section headers with one filled-in section as illustration, and drop the dependency hedging language.
Add validation checkpoints to both workflows: e.g., 'Verify all 5 information-collection questions are answered before proceeding to synthesis' and 'If search returns 0 results, broaden keywords and retry'.
Split into multiple files: move the full disclosure template example to TEMPLATE.md, the IPC reference table to IPC_REFERENCE.md, and the CLI usage details to SEARCH_CLI.md, with clear one-level references from SKILL.md.
Include the actual patent_search.py script in the bundle or clarify that it must be implemented by the user, since referencing a non-existent script undermines actionability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~200+ lines. It explains concepts Claude already knows (what patent sections are, what IPC codes mean), includes a massive example output that could be summarized, lists obvious dependency information with hedging language, and repeats workflow information that's already demonstrated in the examples. The 'Key Features' section is pure marketing copy that adds no actionable value. | 1 / 3 |
Actionability | The CLI commands for patent_search.py are concrete and copy-paste ready, and the disclosure template example is detailed. However, the search script is referenced without any bundle files to confirm it exists, the output is described as 'conceptual' rather than concrete, and the disclosure generation workflow is more of a checklist description than executable guidance. Dependencies are hedged with 'may vary' language. | 2 / 3 |
Workflow Clarity | The disclosure generation workflow has clear steps (information collection → synthesis → optimization), and the search workflow is sequenced. However, there are no validation checkpoints—no step to verify the generated disclosure is complete, no error handling for failed searches, and no feedback loop for iterating on missing information. For a multi-step document generation process, this is a notable gap. | 2 / 3 |
Progressive Disclosure | Everything is crammed into a single monolithic file with no references to external files for detailed content. The IPC table, the full example output, the implementation details, and the CLI reference could all be split into separate files. No bundle files exist to support progressive disclosure, and the skill references scripts/patent_search.py without any supporting documentation or bundle. | 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
d3c2c0f
- 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.