CtrlK
BlogDocsLog inGet started
Tessl Logo

invention-structuring

Structure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a patent-ready structure.

62

Quality

75%

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 ./skills/invention-structuring/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 content is a well-sequenced, actionable patent-structuring workflow with concrete templates, tables, and a validation checkpoint. Its weaknesses are moderate redundancy between the Key Rules and earlier steps, a refinement loop that is declared but not explicitly wired, and a shared-references link that points to a non-existent file.

Suggestions

Wire MAX_REFINEMENT_ROUNDS into an explicit loop: after Step 6's reviewer feedback, list which findings to revise and re-run validation until the reviewer approves or the round limit is hit.

Trim the Key Rules section to only constraints not already stated in Steps 1–2 (e.g., keep "Never invent embodiments..." and the codex-unavailable fallback), removing restatements of the Problem/Solution/core-concept rules.

Either create ../shared-references/patent-writing-principles.md or replace the dangling reference with an inline one-paragraph summary of the Problem-Solution-Advantage framework so the skill is self-contained.

DimensionReasoningScore

Conciseness

The body is information-dense and avoids explaining basic patent concepts, but the Key Rules section largely reiterates constraints already stated in Steps 1–2 and the output template repeats the Problem-Solution-Advantage structure, giving more than minor redundancy.

3 / 5

Actionability

It provides concrete, usable artifacts — a Problem-Solution-Advantage template with statement formats, claim-category and drawing-plan tables, an ASCII dependency map, a reviewer prompt, and a full output template — but these are skeletons with placeholders rather than fully worked examples, stopping short of the score-5 anchor.

4 / 5

Workflow Clarity

Seven steps are clearly sequenced with an explicit cross-model validation checkpoint (Step 6) and a fallback rule, but the MAX_REFINEMENT_ROUNDS constant is not wired into an explicit validate-fix-retry loop, leaving a minor feedback-loop gap below the score-5 anchor.

4 / 5

Progressive Disclosure

The body has clear section headers and signals one one-level-deep reference (../shared-references/patent-writing-principles.md), but no bundle files exist and that referenced file is absent on disk, a minor organization gap relative to the score-5 anchor.

4 / 5

Total

15

/

20

Passed

Description

82%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 strong: it explicitly covers both what the skill does and when to use it, with concrete bilingual trigger phrases and a clear, low-conflict niche. The main gap is specificity, since it restates a single core action rather than enumerating several distinct concrete actions.

DimensionReasoningScore

Specificity

"Structure a raw invention idea into a formal invention disclosure" names the domain and one concrete action (reiterated as "formalize a rough idea into a patent-ready structure"), but does not list several distinct concrete actions as the score-4 anchor requires.

3 / 5

Completeness

It clearly states what the skill does (structure an invention into a formal/patent-ready disclosure) and gives concrete "Use when..." trigger phrases, matching the anchor that explicitly answers both what and when.

5 / 5

Trigger Term Quality

Provides explicit natural trigger phrases including bilingual terms ("构建发明", "structure invention", "发明构建", "invention disclosure") plus a plain-language trigger, giving good keyword coverage though it lacks file extensions to reach the comprehensive score-5 anchor.

4 / 5

Distinctiveness Conflict Risk

The patent-invention-disclosure niche with bilingual, domain-specific triggers is clearly distinct from other skills and carries minimal conflict risk.

5 / 5

Total

17

/

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
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.