subpoena-triage

Triage a subpoena served on the company — classify it, analyze scope/burden/privilege, cross-check the portfolio, and produce an objections framework, compliance plan, and deadline calendar. Use when the user says "we got a subpoena", "served with a subpoena", or shares a subpoena, CID, or third-party document request to evaluate.

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 well-structured, highly actionable legal workflow with strong validation gates and checklists. Its weaknesses are verbosity from repeated citation-attribution framing and a monolithic structure with a large inline output template that should be split into a reference file.

Suggestions

Consolidate the citation/source-attribution guidance, which is restated in Step 0 ('No silent supplement', 'Source attribution'), the triage template's 'Citation verification' section, and across `[SME VERIFY]` tags — state the rule once and reference it.

Move the ~115-line inline triage.md template (Step 8 output) into a `references/triage-template.md` file and link to it from the body, reducing the monolithic SKILL.md and improving progressive disclosure.

Tighten the 'Side context' and 'Jurisdiction assumption' prose to a few sentences each without losing the safety guidance about posture and rule-variant verification.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural guidance, but at ~280 lines it is padded with repeated citation/source-attribution framing (Step 0 'No silent supplement' and 'Source attribution', the template 'Citation verification' section, and `[SME VERIFY]` tags) plus lengthy 'Side context'/'Jurisdiction assumption' prose that could be tightened — matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Highly actionable for an instruction-only skill: a numbered Step 0–9 workflow, explicit fields to extract, named objection categories, a copy-paste triage.md template with placeholders, and concrete hand-off commands like '/legal-hold --issue' and '/matter-briefing [slug]'.	3 / 3
Workflow Clarity	A clearly sequenced Step 0–9 process with explicit validation checkpoints and feedback loops: the Step 0 'No silent supplement' stop-and-ask gate with an exact script, the Step 9 non-lawyer gate ('Do not proceed past this gate without an explicit yes'), and the [SME VERIFY] checklist rows — matching the top anchor.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a monolithic ~280-line SKILL.md; the large inline triage.md output template (~115 lines) is content that could be split into a separate reference, matching the 'some structure but content that should be separate is inline' anchor.	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, third-person description that names concrete actions and pairs them with natural, explicit 'Use when' triggers. It is concise, distinctive, and fully answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'classify it, analyze scope/burden/privilege, cross-check the portfolio, and produce an objections framework, compliance plan, and deadline calendar' — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly answers both what (triage/classify/analyze/produce) and when with an explicit 'Use when the user says...' trigger clause, matching the anchor that requires both with explicit triggers.	3 / 3
Trigger Term Quality	Gives natural phrases a user would actually say — 'we got a subpoena', 'served with a subpoena', 'shares a subpoena, CID, or third-party document request' — with good coverage of common variations, matching the top anchor.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (subpoena/CID triage) with distinct triggers unlikely to fire for other skills, matching the top anchor for a clear niche with distinct triggers.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-for-legal
Path: litigation-legal/skills/subpoena-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.