CtrlK
BlogDocsLog inGet started
Tessl Logo

matter-drill-down

Produces an LPM working view on a single matter — a focused zoom-in for the LPM's own operational use, not for distribution. Structured around deliverables (what is due, when, to whom), issues (current problems requiring action), and risks (plausible future problems requiring monitoring). Use when the user asks "drill into [matter]", "brief me on [matter]", "focus on [matter]", "zoom into [matter]", "prep me for [partner] call on [matter]", "I'm handing [matter] to [name]", "leave cover on [matter]", "taking over [matter]", or pastes single-matter correspondence asking for a working view. Four modes: standard drill-down, decision-first, partner prep, handoff briefing. Not for status reports for distribution (use status-report-drafter) or portfolio views across multiple matters (use daily-briefing). Produces a .docx working view saved to the matter folder.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

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

Highly actionable, well-sequenced content with concrete templates and explicit gates, but it is a long monolithic file with repeated anti-drift phrasing and no progressive disclosure to reference files despite its length.

Suggestions

Move the four mode template variations into separate reference files (e.g. references/mode-templates.md) and link from SKILL.md to reduce inline length and enable one-level-deep progressive disclosure.

State the anti-drift rule ('Produce the document, not a chat answer') once in the Output Format section and reference it from each mode, instead of restating it verbatim across Modes 2, 3, and the routing step.

Tighten the Step 3 audience gate to the exact refusal pattern plus one framing sentence; the current extended explanation of the failure mode repeats the boundary already stated in the Boundary section.

DimensionReasoningScore

Conciseness

Dense and domain-specific with no padding of concepts Claude already knows, but ~475 lines with repeated anti-drift phrasing ('Do not produce conversational prose', 'Produce the document, not a chat answer') restated across modes that could be tightened.

3 / 5

Actionability

Fully executable guidance: exact section-ordered templates with table schemas, concrete M365 tool calls (outlook_email_search, outlook_calendar_search), and specific elicitation prompts — copy-paste ready across all four modes.

5 / 5

Workflow Clarity

Clear sequenced workflow (Input Classification Steps 1–4 → Before Starting → mode routing → template) with explicit validation gates (matter-identifier hard gate, audience refusal gate) and feedback loops (route-and-stop on audience mismatch).

5 / 5

Progressive Disclosure

Well-sectioned single file, but all four full templates and domain knowledge are inlined in SKILL.md with no reference bundle files; the mode template variations could be split into one-level-deep reference files.

3 / 5

Total

16

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 concretely states capabilities, comprehensive natural triggers, and explicit boundaries against adjacent skills. Both 'what' and 'when' are answered with specific trigger phrases.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Produces an LPM working view', structured around deliverables/issues/risks, four named modes, and '.docx working view saved to the matter folder' — with comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what (working view on deliverables/issues/risks, four modes, .docx output) and when (concrete 'Use when the user asks...' trigger phrases), with explicit not-for boundary.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say ('drill into', 'brief me on', 'focus on', 'zoom into', 'prep me for [partner] call', 'leave cover', 'taking over') plus the pasted-correspondence pattern.

5 / 5

Distinctiveness Conflict Risk

Clear niche (single-matter LPM working view) with explicit routing away from status-report-drafter and daily-briefing, minimizing wrong-skill triggers.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
legalopsconsulting/lpm-skills
Reviewed

Table of Contents

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.