daily-briefing

Produces a portfolio-level morning briefing for an LPM running two or more active matters. Reads email, call notes and matter state across the portfolio and produces a triage surface structured around meetings (today and this week), deliverables (what is due, when, to whom), issues (current problems requiring action), and risks (plausible future problems requiring monitoring). Also reads Outlook Calendar to surface upcoming matter-relevant meetings and to flag past meetings where no follow-up correspondence has been identified. Use when the user asks "run my daily briefing", "portfolio briefing", "what do I need to know today", "what's landed overnight", "Monday sweep", "pre-09:00 briefing", "weekend catchup", or pastes correspondence spanning two or more matters. Not for single-matter briefings (use matter-drill-down) or for audience-facing status reports (use status-report-drafter). Produces a .docx working surface for the LPM's own consumption, not distribution.

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 1-5

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

The body is highly actionable with a precise, sequenced workflow and strong validation gates, but it carries notable repetition of the single-matter rule and over-explains some domain concepts. As a long monolithic skill it also misses opportunities to split detailed material into referenced files.

Suggestions

Consolidate the single-matter routing rule into one authoritative statement (Boundary) and reference it elsewhere rather than restating it five times, to recover token budget.

Move the full Standard Template spec, the Domain Knowledge taxonomy, and the M365 Connected Mode guide into separate reference files (e.g. TEMPLATE.md, DOMAIN.md, M365.md) and link to them from SKILL.md so the overview stays lean.

Tighten the Domain Knowledge section by pruning explanations of general concepts (e.g. RAG as a trailing indicator, the issues-vs-risks taxonomy) down to the LPM-specific decision rules Claude would not already infer.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific guidance, but the single-matter routing rule is restated roughly five times (Boundary, Input Classification Step 1, Mode 2, Output Format anti-pattern, LPM vs Attorney) and the Domain Knowledge section explains general concepts (RAG semantics, issues-vs-risks taxonomy, past-meeting judgment) at length that could be tightened.	3 / 5
Actionability	Fully concrete and actionable — a complete output template with exact tables and section order, a verbatim routing response to copy, specific connector calls ('outlook_calendar_search'), and explicit placeholder conventions ('[LPM NAME]', '[M-NUMBER]') covering the common cases; the absence of code is appropriate for this instruction-only skill.	5 / 5
Workflow Clarity	Clear sequenced workflow — Input Classification (Steps 1–4) → pre-mode checks → mode selection → template production — with explicit validation gates (the single-matter hard gate, 'Do not proceed without a roster', silence detection) and feedback loops (route-and-stop, cross-document silence consistency check).	5 / 5
Progressive Disclosure	Well organized into clearly headed sections, but it is a ~375-line monolith with no bundle files and no external references — content that would benefit from being split out (the full template spec, the domain-knowledge taxonomy, the M365 connector guide) is all inlined.	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.

The description is exemplary: third-person voice, comprehensive concrete actions, natural trigger phrases covering synonyms and invocation styles, and explicit what/when plus a not-for boundary. It is dense but every clause earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Reads email, call notes and matter state', 'reads Outlook Calendar to surface upcoming matter-relevant meetings and to flag past meetings where no follow-up correspondence has been identified', 'produces a triage surface structured around meetings, deliverables, issues, and risks', 'Produces a .docx working surface' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (reads email/call notes/matter state/calendar, produces a four-element triage surface as .docx) and 'when' (a dedicated 'Use when the user asks...' clause with concrete trigger phrases), with an explicit 'Not for...' boundary clause.	5 / 5
Trigger Term Quality	Includes natural verbatim phrases a user would actually say — 'run my daily briefing', 'what do I need to know today', 'what's landed overnight', 'Monday sweep', 'pre-09:00 briefing', 'weekend catchup', and 'pastes correspondence spanning two or more matters' — covering synonyms and invocation styles comprehensively.	5 / 5
Distinctiveness Conflict Risk	A clear niche — portfolio-level, two-or-more active matters, LPM consumption — with explicit de-confliction: 'Not for single-matter briefings (use matter-drill-down) or for audience-facing status reports (use status-report-drafter)', minimizing wrong-skill triggering.	5 / 5
	Total	20 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: legalopsconsulting/lpm-skills
Path: skills/daily-briefing/SKILL.md
Commit: 178ed52

Reviewed: 4 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.