local-counsel-manager

End-to-end external local counsel lifecycle management for multi-jurisdiction legal matters. LC selection criteria and capability assessment, engagement setup and instruction design, performance monitoring and check-in cadence, scope enforcement, and relationship escalation. Use when selecting local counsel for a jurisdiction, designing LC instructions, managing the LC check-in rhythm, enforcing scope boundaries when LC signals overreach, or escalating a performance or relationship issue beyond the matter team. Trigger on: 'which LC should we use', 'LC instruction', 'brief the local counsel', 'LC hasn't responded', 'LC is going off scope', 'LC scope dispute', 'confirm scope with LC', 'LC check-in', 'LC is slow', 'monitor the LC network', 'LC engagement letter', 'LC selection', 'what should we tell the local counsel', 'LC onboarding', 'LC performance issue', 'LC relationship problem'.

Quality

77%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/local-counsel-manager/SKILL.md

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that thoroughly covers all evaluation dimensions. It provides specific concrete actions across the full LC lifecycle, includes a comprehensive set of natural trigger terms that users would realistically say, and clearly delineates both what the skill does and when it should be used. The domain is highly specific and distinctive, minimizing conflict risk with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: LC selection criteria and capability assessment, engagement setup and instruction design, performance monitoring and check-in cadence, scope enforcement, and relationship escalation. These are clearly defined lifecycle stages.	3 / 3
Completeness	Clearly answers both 'what' (end-to-end LC lifecycle management with specific stages listed) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios, plus a dedicated 'Trigger on' list). Both dimensions are thoroughly addressed.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would actually say, including variations like 'which LC should we use', 'LC hasn't responded', 'LC is going off scope', 'LC check-in', 'LC is slow', 'LC engagement letter', 'LC onboarding', and 'LC performance issue'. These cover a wide range of realistic user queries.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche focused specifically on external local counsel management in multi-jurisdiction legal matters. The 'LC' terminology and specific lifecycle stages (scope enforcement, engagement letters, check-in cadence) make it very unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

55%

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

This skill is exceptionally well-designed in terms of actionability and workflow clarity — the document templates, escalation paths, and validation gates are production-ready and precisely structured. However, it is severely undermined by its length and monolithic structure; at 400+ lines with no bundle files, it consumes enormous context window space and includes substantial narrative explanation (failure mode philosophy, domain knowledge, M365 integration details) that should be split into referenced files or trimmed entirely.

Suggestions

Extract 'Domain Knowledge — LC Network Management', 'M365 Connected Mode', 'Cross-Skill Handoffs', and 'Time-Sensitive Assumptions' into separate referenced files (e.g., LC_DOMAIN.md, M365_INTEGRATION.md, HANDOFFS.md) to reduce the main skill to its core operational modes.

Remove philosophical/explanatory passages like 'Managing local counsel is a coordination discipline, not a legal one' and 'The most common failure modes on LC networks are not capability failures — they are instruction failures' — these explain concepts Claude can infer from the operational instructions themselves.

Consolidate the repeated 'produce the output, do not ask' directives into a single output behavior rule at the top rather than restating it in each mode and in the output format section.

Trim the input classification section which appears both at the top and is restated in Mode 4's signal detection — deduplicate to a single authoritative location.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. Extensive explanations of coordination philosophy, failure mode narratives, and domain knowledge that Claude can infer. Sections like 'The instruction failure pattern' and 'LC response quality signals' explain concepts an LPM-trained model would already understand. The repeated emphasis on 'produce the output, don't ask' appears multiple times. The M365 section and cross-skill handoffs add significant length for optional/contextual content that could be in separate files.	1 / 3
Actionability	Highly actionable with complete, copy-paste-ready document skeletons (instruction letter template, scope response letter template), specific escalation timelines with day-numbered actions, concrete email subject line formats, and structured action tables. The selection criteria are prioritized, the check-in cadences are specific, and the scope response letter includes three position options with exact language.	3 / 3
Workflow Clarity	Excellent multi-step workflows with explicit validation checkpoints throughout. The input classification runs as a mandatory first step before mode selection. The escalation path has a clear day-numbered sequence with ownership and feedback loops (Day 5 includes internal flag, Day 7 reassessment). The instruction letter requires acknowledgment within 2 business days with follow-up if not received. The identifier hard gate is a clear validation checkpoint before document production.	3 / 3
Progressive Disclosure	Monolithic wall of text with no bundle files to offload content. The domain knowledge section, M365 connected mode, cross-skill handoffs, and time-sensitive assumptions could all be separate referenced files. Everything is inline in a single massive document, making it expensive to load for simple tasks. No external references or file structure to navigate to advanced content.	1 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: legalopsconsulting/lpm-skills
Commit: dc6509d

Reviewed: 19 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.