oc-status

Generate weekly status-request email drafts to outside counsel across the active portfolio — markdown per matter, plus Gmail drafts when the MCP is available. Use when the user asks for OC status requests, weekly outside counsel check-ins, or wants per-matter status emails drafted from the portfolio log.

Quality

83%

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

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.

Highly actionable with a clear, validated workflow and concrete templates. It loses points for conciseness (repeated long paths and redundant caveats) and for progressive disclosure, since everything lives inline in one file with no references to offload detail.

Suggestions

De-duplicate the long `~/.claude/plugins/config/claude-for-legal/litigation-legal/...` paths — define the base path once and reference it relatively afterward to cut tokens.

Move the Gmail-MCP fallback and scheduling caveats into a single section instead of restating them in Purpose, the step list, Output, and Scheduling.

Consider extracting the email skeleton and run-summary templates into a reference file to add a progressive-disclosure layer and slim the main body.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the body repeats long config paths verbatim many times and re-explains the Gmail/scheduling caveats in multiple sections, which could be tightened.	2 / 3
Actionability	Provides a fully concrete email skeleton, exact output file paths, explicit filter rules, flag semantics, and markdown formatting templates — copy-paste-ready actionable guidance throughout.	3 / 3
Workflow Clarity	Clear numbered 7-step sequence with explicit validation/skip gates (email null check, Gmail MCP fallback) and a send-gate review checkpoint plus run summary; the batch/destructive-adjacent operations have feedback loops as the rubric rewards.	3 / 3
Progressive Disclosure	Well-organized into sections but it is a monolithic single-file skill with no bundle references to split detail into; per the rubric's bundle-structure guidance for skills without external references, structure is good but there is no progressive disclosure layering.	2 / 3
	Total	10 / 12 Passed

Description

90%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, specific description with concrete actions and explicit 'Use when...' triggers in proper third-person voice. Minor conflict risk with generic status/check-in skills keeps it just shy of perfect distinctiveness.

Suggestions

Add a domain qualifier to the trigger clause (e.g., 'litigation outside-counsel status requests') to further reduce overlap with generic check-in/status skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Generate weekly status-request email drafts', 'markdown per matter', 'plus Gmail drafts when the MCP is available' — matching the rubric's highest anchor for listing specific concrete actions.	3 / 3
Completeness	Clearly states both what it does (draft status-request emails per matter, markdown + Gmail drafts) and when to use it via an explicit 'Use when...' clause with multiple triggers; third-person voice is maintained throughout.	3 / 3
Trigger Term Quality	Covers natural user phrasings — 'OC status requests', 'weekly outside counsel check-ins', 'per-matter status emails drafted from the portfolio log' — good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The niche is fairly distinct (outside-counsel status emails from a litigation portfolio log) but the 'weekly check-ins / status requests' framing could overlap with other status/communication skills, so it is not maximally distinct.	2 / 3
	Total	11 / 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/oc-status/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.