investigation-add

Add data to an open investigation — documents, interview notes, or observations. Processes batches against the documented pull criteria, surfaces significant items, and logs everything reviewed for coverage verification. Use when new evidence, interview notes, or document productions come in for an open investigation.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%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 lean, well-structured instruction skill that delegates detail to a clearly signaled reference skill. Its main weakness is the batch-processing workflow, which lacks an explicit validation/coverage checkpoint before reporting results.

Suggestions

Add a verification checkpoint before reporting surfaced items — e.g., step 3.5: confirm every batch item was reviewed and reconcile the coverage log against the sources checklist before showing the surface ratio.

Make the coverage gate explicit in the workflow: only prompt to update the sources checklist after confirming the batch was fully processed with no ingestion or parse errors.

Specify what to do on a failed/partial batch (retry, flag, log a gap) so the batch operation has a feedback loop rather than a single forward pass.

Dimension	Reasoning	Score
Conciseness	Lean body (~25 lines) with no concept-explanation padding; it assumes Claude's competence and points to detail elsewhere. The opening sentence lightly restates the description, but overall every section earns its place. Not a 2 because there is no unnecessary explanation beyond that minor restate.	3 / 3
Actionability	Instructions name exact, executable targets — the path '~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md', 'the internal-investigation reference skill and run Mode 2 (Add data)', and concrete outputs (surface ratio, surfaced items, sources checklist). For an instruction-only skill this is specific and actionable.	3 / 3
Workflow Clarity	Steps 1–4 are clearly sequenced, but this is a batch operation ('Processes document batches') with no validation/verification checkpoint before reporting surfaced items; the rubric caps batch workflows at 2 when feedback loops are missing. Not a 3 because there is no explicit validate-then-proceed step; not a 1 because the sequence itself is present.	2 / 3
Progressive Disclosure	Clear overview with a single, well-signaled one-level-deep reference — the blockquote states the detailed needle-finding process, log format, surface-ratio rules, and checklist tracking 'live in the internal-investigation reference skill — load it before doing substantive work'. Content is appropriately split and easy to navigate.	3 / 3
	Total	11 / 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 states concrete capabilities and an explicit Use-when trigger with domain-natural keywords. It is concise without padding and clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Processes batches against the documented pull criteria, surfaces significant items, and logs everything reviewed' — matching the top anchor for multiple specific actions rather than a single domain/action.	3 / 3
Completeness	Answers both halves: what ('Processes batches…surfaces significant items, and logs everything reviewed') and an explicit when clause ('Use when new evidence, interview notes, or document productions come in for an open investigation').	3 / 3
Trigger Term Quality	Covers natural terms a user would actually say in this domain — 'documents, interview notes, or observations', 'new evidence, interview notes, or document productions', 'open investigation' — rather than jargon or generic phrasing.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (open legal investigation with pull criteria, surface ratio, coverage verification) with distinct triggers unlikely to collide with other skills. Not a 2 because the scoped domain ('open investigation', 'document productions') is unmistakable.	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: employment-legal/skills/investigation-add/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.