budget-and-fee-manager

Matter budgeting and ongoing WIP/variance monitoring. Build phase-based fee estimates at matter setup, run bottom-up budgets by jurisdiction or workstream, calculate contingency, and structure AFA arrangements (fixed fee, capped fee, phased fixed fees). Ongoing monitoring: WIP tracking against budget, proportionality assessment (spend vs progress), variance commentary with root cause analysis, forecast-to-complete, realisation monitoring, write-off analysis. Trigger on: 'build a budget', 'fee estimate', 'what will this cost', 'WIP review', 'budget vs actual', 'how are we tracking against budget', 'we're over budget', 'realisation is poor', 'what's our ETC', 'budget for the German workstream', 'model the financial impact of this scope change', 'draft a fee adjustment', 'write-off analysis', 'how much contingency', 'AFA structure', 'fixed fee estimate', 'budget update', 'forecast to complete'.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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 strong workflow sequencing and concrete templates across all five operating modes. Its main weakness is conciseness and the absence of a bundle structure that would let the large reference material live one level deep rather than inline.

Suggestions

Move the per-mode output templates (table headers, status enums, query-draft blocks, Mode 3 memo structure) into separate reference files (e.g. references/output-templates.md) and link them one level deep, keeping SKILL.md as an overview plus the core domain rules.

Tighten discursive justification paragraphs (e.g. repeated restatements of why proportionality matters, "The context window is a public good"-style rationale) to operating rules only, trimming tokens without losing guidance.

Consider a compact decision-tree or trigger->mode map near the top so the five operating modes and their inputs are navigable at a glance rather than discovered by scrolling.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of elementary-concept padding, but the body is large and contains discursive rationale ("The context window...", extended justification paragraphs, repeated restatements of the proportionality principle) that could be tightened without losing the operational guidance.	2 / 3
Actionability	Provides copy-paste-ready templates: exact table column headers, status value enums, a four-question variance framework, named contingency ranges, a full query-draft email block, and a Mode 3 memo structure with required rows — concrete and executable rather than abstract.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints (identifier block required before any output; financial disclosure sequencing gates; four-question framework; query/chase loop with draft-email-then-incorporate steps) and error-recovery feedback loops for risky outputs.	3 / 3
Progressive Disclosure	Content is well-sectioned but monolithic within SKILL.md with no references/, scripts/, or assets/ bundle files; the large domain-knowledge and per-mode template blocks could be split into one-level-deep reference files to improve navigability and token economy.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is specific, third-person, and explicitly pairs capabilities with an extensive, natural-language trigger list, covering both what and when. It is on the long side but every clause earns its place, and verbosity is not penalized under this rubric.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("build bottom-up budgets by jurisdiction or workstream", "calculate contingency", "structure AFA arrangements", "WIP tracking against budget", "variance commentary with root cause analysis", "forecast-to-complete", "write-off analysis") rather than vague domain references.	3 / 3
Completeness	It explicitly answers both what the skill does (budgeting, WIP/variance monitoring, AFA structuring) and when to use it, with a dedicated "Trigger on:" clause giving explicit trigger guidance.	3 / 3
Trigger Term Quality	The "Trigger on" clause supplies natural phrasings a user would actually say ("what will this cost", "how are we tracking against budget", "we're over budget", "how much contingency", "fixed fee estimate", "forecast to complete") with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The matter-budgeting/WIP niche and its specific trigger phrasings ("realisation is poor", "budget for the German workstream", "AFA structure") are clearly distinct from sibling skills and unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: legalopsconsulting/lpm-skills
Commit: 178ed52

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.