CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

patent-claim-mapper

Use when mapping patent claims to products, analyzing patent infringement, or preparing freedom-to-operate analyses. Compares patent claims against product features for biotech and pharmaceutical IP assessment.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/patent-claim-mapper/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%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 skill has a sound generic process skeleton (validate inputs, quick-check the script, fallback path) and a real, one-level-deep reference file, but the body is heavily padded with boilerplate and its centerpiece code/CLI examples do not match the actual bundled script, so a user following them would fail. Correcting the examples to the real PatentClaimMapper interface and cutting the duplicated template sections would raise it substantially.

Suggestions

Replace the Quick Start, Core Capabilities, and CLI Usage examples with the actual bundle interface: scripts/main.py defines PatentClaimMapper.analyze_infringement(patent_claims, product_description, ...) and CLI flags --patent-claims / --product-description / --output — remove all references to the nonexistent ClaimMapper class, scripts/claim_mapper.py, and the --patent/--product flags.

Cut the templated padding: drop the two verbatim repetitions of the frontmatter description in "When to Use" and "Key Features", merge the duplicate "Quick Check" and "Audit-Ready Commands" sections into one, and remove the self-referential "See ## Workflow above" line and the duplicated process guidance in "Implementation Details".

Move the generic process boilerplate (Output Requirements, Input Validation, Response Template, Error Handling) into references/ (e.g., alongside audit-reference.md) and keep SKILL.md focused on the domain workflow: parse claims → extract features → compare → interpret mapping statuses (fully/partially/not covered) → generate the report.

DimensionReasoningScore

Conciseness

The body is noticeably padded: the frontmatter description is repeated verbatim three times ("When to Use", "Key Features", and "Scope-focused workflow aligned to:"), the same two audit commands appear in both "Quick Check" and "Audit-Ready Commands", and generic template sections ("Implementation Details" opens with the self-referential "See ## Workflow above") restate the same process guidance. It is not a 1 because the domain material (mapping results taxonomy, CLI examples) does convey real, non-obvious information without explaining concepts Claude already knows.

2 / 5

Actionability

Concrete commands exist ("python -m py_compile scripts/main.py", "python scripts/main.py --help") and they work against the actual bundle, but the main code examples are non-executable: "from scripts.claim_mapper import ClaimMapper", "mapper.parse_claims(...)" / "identify_gaps(...)" reference a file and class that do not exist (scripts/ contains only main.py defining PatentClaimMapper with analyze_infringement), and the CLI example uses flags "--patent" / "--product" that do not match the script's actual "--patent-claims" / "--product-description". This is the anchor-3 pattern of concrete-looking guidance with missing key details; it is not a 2 because the verification commands are genuinely runnable and the correct entry point is named.

3 / 5

Workflow Clarity

The Workflow section has a sequenced five steps with an explicit fallback path ("If execution fails or inputs are incomplete, switch to the fallback path"), but the operational workflow a user actually needs — load claims, extract features, compare, generate report with the correct CLI flags — is never coherently laid out, and the conflicting CLI/Quick Start examples undermine the sequence. It is not a 4 because the checkpoints address generic request validation rather than the actual script execution, and the concrete run instructions conflict with the real script interface.

3 / 5

Progressive Disclosure

The reference structure that exists is good — references/audit-reference.md is real, clearly linked with a one-line description, and one level deep, and scripts/main.py matches the documented entry point. But the body also cites nonexistent paths (scripts/claim_mapper.py, scripts.claim_mapper module), which breaks navigation, and large amounts of template content (Output Requirements, Response Template, Input Validation, duplicated audit sections) are inlined in SKILL.md instead of being split out. It is not a 4 because broken file references are more than a minor organization gap.

3 / 5

Total

11

/

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 description that explicitly states both capability and trigger conditions in third person, with domain-specific, natural trigger phrases. Its only weakness is missing a few natural synonyms (FTO, claim chart) that would push trigger coverage to comprehensive.

DimensionReasoningScore

Specificity

The description lists several specific actions — "mapping patent claims to products", "analyzing patent infringement", "preparing freedom-to-operate analyses", "Compares patent claims against product features" — in third person. It falls short of a 5 because the actions are coarser-grained domain activities rather than fully comprehensive concrete operations (e.g., no mention of gap analysis, claim charts, or risk scoring).

4 / 5

Completeness

Both halves are explicit: what it does ("Compares patent claims against product features for biotech and pharmaceutical IP assessment") and when to use it ("Use when mapping patent claims to products, analyzing patent infringement, or preparing freedom-to-operate analyses"). The 'when' clause contains concrete trigger activities, matching the anchor-5 pattern; a 4 would require the 'when' to be less explicit or specific, which it is not.

5 / 5

Trigger Term Quality

Natural phrases users would say are present: "patent claims", "patent infringement", "freedom-to-operate", "biotech and pharmaceutical". It misses common synonyms and variations a user might naturally say — "FTO", "claim chart", "prior art", "design-around" — so it does not reach comprehensive synonym-level coverage.

4 / 5

Distinctiveness Conflict Risk

The niche is clear (patent claim-to-product mapping for biotech/pharma IP) with trigger terms that no other plausible skill would claim, giving minimal conflict risk. It is not a 4 because the domain scoping ("biotech and pharmaceutical IP assessment") plus the specific trigger activities leave essentially no overlap with generic document or analysis skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Evidence Insight/patent-claim-mapper/SKILL.md

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.