document-approval-tracker
Approval cascade definition and tracking for multi-stakeholder document workflows. Internal review sequences, client approval workflows, regulatory review, overdue chasing with escalation logic, version control coordination, and cross-jurisdiction document dependencies. Use when defining who reviews a document and in what order, tracking where a document is stuck in the approval chain, chasing an overdue reviewer, preventing reviewers working on superseded drafts, or mapping dependencies between documents across jurisdictions. Trigger on: 'who needs to approve this', 'document approval', 'review sequence', 'stuck in review', 'overdue approval', 'who has the document', 'version control', 'wrong version', 'document dependency', 'NL SPA waiting on German opinion', 'approval cascade', 'review chain', 'document circulation', 'chasing the partner', 'client approval process', 'where is the document'.
82
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/document-approval-tracker/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, provides rich natural-language trigger terms, and clearly delineates both what the skill does and when it should be used. The inclusion of realistic user phrases ('chasing the partner', 'NL SPA waiting on German opinion') demonstrates strong understanding of how users would invoke this skill. The description is well-structured and occupies a distinct niche unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: approval cascade definition, tracking, internal review sequences, client approval workflows, regulatory review, overdue chasing with escalation logic, version control coordination, and cross-jurisdiction document dependencies. | 3 / 3 |
Completeness | Clearly answers both 'what' (approval cascade definition and tracking for multi-stakeholder document workflows with specific sub-capabilities) and 'when' (explicit 'Use when' clause with five distinct scenarios plus a comprehensive 'Trigger on' list). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including conversational phrases users would actually say like 'who needs to approve this', 'stuck in review', 'chasing the partner', 'where is the document', and domain-specific examples like 'NL SPA waiting on German opinion'. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around document approval workflows and cascades, distinct from general document editing, version control (git), or project management skills. The legal/multi-jurisdictional framing and specific trigger terms like 'approval cascade' and 'review chain' make it highly distinguishable. | 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.
The skill excels in actionability and workflow clarity — every mode produces concrete, structured outputs with clear sequencing, validation gates, and escalation logic. However, it is severely undermined by its length and monolithic structure: domain knowledge explanations, M365 integration details, and cross-skill handoff descriptions bloat the content well beyond what's needed for Claude to execute the skill effectively. Splitting content into referenced files and cutting explanatory prose would dramatically improve token efficiency.
Suggestions
Move the 'Domain Knowledge — Why Document Approval Fails' section to a separate DOMAIN_CONTEXT.md file and reference it — Claude doesn't need five paragraphs explaining common failure modes inline to execute the workflows.
Extract the 'M365 Connected Mode and DMS Integration' section into a separate DMS_INTEGRATION.md reference file — it's detailed implementation context that doesn't need to load on every invocation.
Move 'Cross-Skill Handoffs' to a separate HANDOFFS.md file with a one-line summary in the main skill ('See HANDOFFS.md for integration with other LPM skills').
Cut explanatory prose throughout — e.g., the second and third paragraphs of the introduction explain why document approval matters, which Claude doesn't need to be told; the 'When to use this skill' section largely duplicates the frontmatter trigger list.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It includes extensive domain knowledge sections explaining why document approval fails (concepts Claude can infer), lengthy explanations of LPM vs attorney boundaries, and substantial prose context that could be dramatically compressed. The 'Domain Knowledge' section and much of the M365 integration section explain concepts rather than instruct. | 1 / 3 |
Actionability | The skill provides fully executable templates for every mode: complete cascade design skeletons with table structures, position tracker tables, escalation email templates at each stage with specific language, version status tables, and recall/clarification emails. All outputs are copy-paste ready with clear placeholders. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints. The input classification runs first, the identifier block is a hard gate before proceeding, Mode 3 escalation stages are calculated from days overdue with clear thresholds, the 80% SLA flag threshold is explicit, and the Mode 2/3 hybrid rule ensures position tracking precedes chasing. Feedback loops are present (flag gaps, re-validate versions). | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. The M365 integration section, domain knowledge section, cross-skill handoffs, and time-sensitive assumptions could all be split into separate reference files. Everything is inline, making the skill extremely long and difficult to navigate quickly. | 1 / 3 |
Total | 8 / 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.
- Repository
- legalopsconsulting/lpm-skills
- Commit
8f9093f
- 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.