fto-triage

Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent counsel review. This skill never concludes a product is clear to launch.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A substantive, highly actionable legal-triage skill with a clear sequenced workflow and strong guardrail checkpoints. Its weaknesses are token-efficiency (a repeated disclaimer and a long inline output template) and the absence of any progressive disclosure — everything sits in one large file.

Suggestions

Consolidate the "this is not a freedom-to-operate opinion" disclaimer to a single prominent statement; restating it 5+ times across the opening, dedicated section, output template, and closing sections inflates the body without adding clarity.

Move the ~100-line output-format template and the verbatim intake/fallback scripts into a reference file (e.g. references/output-template.md) and link to it from SKILL.md, giving a large skill genuine progressive disclosure and a leaner main file.

Trim the recurring willfulness/strict-liability explanations that reappear in the search, claim-chart, next-steps, and willfulness-note sections; state them once and reference back.

Dimension	Reasoning	Score
Conciseness	The body is high-signal and does not explain basic concepts Claude already knows, but it restates the "this is not an FTO opinion" guardrail five or more times (opening, dedicated section, output template, "What this skill does not do", tone) and carries a ~100-line output template inline. Mostly efficient but padded with repeated disclaimers; not lean enough for the top anchor.	2 / 3
Actionability	Provides copy-paste-ready, executable guidance: verbatim intake questions, an exact fallback statement to "Write this exact statement in the output," a full output-format template with table schemas, a concrete claim-chart table structure, and exact output file paths. Fully actionable for an instruction-only skill.	3 / 3
Workflow Clarity	A clearly sequenced workflow (intake → search → per-patent capture → claim-chart → open questions → next steps → output → non-lawyer gate → output location) with explicit checkpoints: stop if the profile contains [PLACEHOLDER], push once on vague intake, fallback statement when no database, citation verification ("Do not cite a result you cannot open"), and a non-lawyer gate before issuing output.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the entire ~527-line skill lives inline in SKILL.md. Sections are well-organized, but content that could be split — the long output template, verbatim intake scripts, and the dedicated guardrail block — is inline with no one-level-deep references, fitting the middle anchor for a skill of this size.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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-crafted description: concrete actions, explicit "Use when" triggers, natural user phrasing, and a clear anti-overclaim boundary that distinguishes it from a full FTO opinion. Every dimension lands at the top of the scale.

Dimension	Reasoning	Score
Specificity	Names concrete actions — "a structured first look at potentially blocking patents" and "build a claim-chart first pass against the most plausible patents before patent counsel review" — rather than vague language. It lists multiple specific concrete actions, matching the top anchor; it is not abstract like "Helps with documents."	3 / 3
Completeness	Explicitly answers both what ("a structured first look at potentially blocking patents, not an FTO opinion... build a claim-chart first pass") and when (an explicit "Use when..." clause with multiple triggers). Both halves are present and explicit, satisfying the top anchor.	3 / 3
Trigger Term Quality	Includes natural phrasings a user would actually say — "when asked whether anything stops a launch" and "evaluated for blocking patents" — alongside domain terms (FTO, claim-chart). Good coverage of natural trigger terms; not just jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (patent FTO triage) with distinct triggers and an explicit boundary — "This skill never concludes a product is clear to launch" — that separates it from a full FTO-opinion skill. Unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (538 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: anthropics/claude-for-legal
Path: ip-legal/skills/fto-triage/SKILL.md
Commit: 4a6c651

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.