Operational billing execution for legal matters. Monthly bill prep and billing instructions, LC invoice review and disbursement treatment, client billing query responses, cashflow modelling (LC payment obligations vs client receipts), and leverage and burn analysis (staffing mix, predicted total cost, margin trajectory). Trigger on: 'prepare the bill', 'billing instruction', 'end of month billing', 'LC invoice', 'local counsel invoice', 'pass through as disbursement', 'client querying the invoice', 'billing dispute', 'cashflow gap', 'when will we get paid', 'LC payment due', 'leverage analysis', 'staffing mix', 'predicted total cost', 'burn rate by grade', 'are we on track', 'what will this matter cost'.
61
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/billing-cycle-manager/SKILL.mdQuality
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 specific capabilities in legal billing operations, provides extensive natural trigger terms, and clearly delineates both what the skill does and when it should be activated. The description is well-structured with a clear separation between capability listing and trigger guidance, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple specific concrete actions: monthly bill prep, billing instructions, LC invoice review and disbursement treatment, client billing query responses, cashflow modelling with specific parameters, and leverage/burn analysis with detailed sub-components (staffing mix, predicted total cost, margin trajectory). | 3 / 3 |
Completeness | Clearly answers both 'what does this do' (operational billing execution covering bill prep, invoice review, query responses, cashflow modelling, leverage/burn analysis) AND 'when should Claude use it' with an explicit 'Trigger on:' clause listing numerous specific trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say, including variations like 'prepare the bill', 'end of month billing', 'LC invoice' / 'local counsel invoice', 'billing dispute', 'cashflow gap', 'when will we get paid', 'burn rate by grade', 'are we on track', and 'what will this matter cost'. These are realistic phrases a legal professional would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in legal matter billing operations. The combination of legal-specific terminology (LC invoices, disbursement treatment, matter cost) and billing-specific triggers makes it very unlikely to conflict with other skills. The domain is narrow and well-defined. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill demonstrates deep domain expertise and provides highly actionable, concrete outputs (templates, table formats, decision frameworks) that would genuinely guide billing execution. However, it is severely over-length, explaining foundational concepts at length rather than trusting Claude's intelligence, and packs all five modes' domain knowledge into a single monolithic file without any progressive disclosure structure. The workflow clarity is adequate but lacks the explicit validation-loop discipline expected for financial operations.
Suggestions
Reduce content by 50%+ by removing explanatory passages Claude doesn't need (e.g., 'Why leverage matters' preamble, the structural mismatch explanation, tone principles that restate Claude's default behavior). Keep only the decision rules, templates, and thresholds.
Split domain knowledge into separate referenced files per mode (e.g., LC_INVOICE_REVIEW.md, CASHFLOW_MODEL.md, LEVERAGE_ANALYSIS.md) and keep SKILL.md as a concise routing overview with mode triggers, identifier block, and links.
Add explicit numbered workflows with validation checkpoints within each mode — e.g., for Mode 1: '1. Confirm fee basis → 2. Review WIP by phase → 3. Apply write-down rules → 4. Validate: every line has authorised-by → 5. Produce billing instruction + CSV'.
Move the M365 Connected Mode and Cross-Skill Handoffs sections to a separate INTEGRATION.md file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines. It extensively explains concepts Claude already knows (what leverage is, why cashflow mismatches occur, what a billing query is, general professional tone guidance). Significant portions read like a training manual for a junior LPM rather than concise instructions for an AI. Many sections could be cut by 50-70% without losing actionable content. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific table formats for billing instructions, leverage tables, and cashflow models; a complete LC query letter template; explicit decision trees (three positions for client queries, three LC disbursement options); and clear criteria for write-down thresholds and approval requirements. Outputs are well-specified with exact column structures. | 3 / 3 |
Workflow Clarity | Each mode has clear inputs and outputs, and the 'Before Starting Any Mode' section provides a good validation checkpoint. However, the five modes lack explicit step-by-step sequencing with validation checkpoints within each mode. For example, Mode 1 bill prep doesn't have a numbered workflow with verify-before-proceeding gates. The LC invoice review has a three-point checklist but no explicit error recovery loop. For operations involving financial documents and write-downs, the absence of intra-mode validation steps is a gap. | 2 / 3 |
Progressive Disclosure | No bundle files are provided, yet the skill is monolithic — all domain knowledge for five distinct modes is inlined in a single massive file. The LC invoice review methodology, client billing query guidance, cashflow modelling domain knowledge, and leverage analysis could each be separate reference files linked from a concise overview. Cross-skill handoffs reference other skills but the skill's own content is a wall of text with no internal decomposition. | 1 / 3 |
Total | 7 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
dc6509d
Table of Contents
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.