scope-change-controller
Scope management for legal matters — baseline capture, in-flight change control, OOS documentation, and scope retrospective. Use when asked to review scoping assumptions, assess whether work is in or out of scope, draft a scope change notice, track scope changes, prepare an OOS justification, run an OOS report, prepare a scope call agenda, or review what changed on a matter. Trigger on: 'scope change', 'out of scope', 'OOS', 'scope creep', 'is this in scope', 'the client wants us to also', 'additional work', 'scope review', 'what changed from the original scope', 'we need to revisit the quote', 'the budget assumed', 'OOS report', 'scope call with the client', 'run a scope report'.
71
63%
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/scope-change-controller/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 clearly defines its domain (legal matter scope management), lists specific concrete actions, provides explicit 'Use when' guidance, and includes a rich set of natural trigger terms covering both formal terminology and conversational phrases. It uses proper third-person voice throughout and is highly distinctive in its niche.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: baseline capture, in-flight change control, OOS documentation, scope retrospective, reviewing scoping assumptions, drafting scope change notices, tracking scope changes, preparing OOS justifications, running OOS reports, preparing scope call agendas. | 3 / 3 |
Completeness | Clearly answers both 'what' (scope management for legal matters with specific sub-capabilities) and 'when' (explicit 'Use when...' clause listing specific scenarios, plus a 'Trigger on' section with natural language phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including abbreviations ('OOS'), full phrases ('out of scope', 'scope creep'), conversational phrases ('the client wants us to also', 'we need to revisit the quote', 'the budget assumed'), and task-oriented terms ('run a scope report', 'scope call with the client'). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to legal matter scope management, which is a clear niche. The combination of legal domain + scope management + specific triggers like 'OOS', 'scope creep', and 'the client wants us to also' makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill contains genuinely valuable domain knowledge about legal scope management, with useful templates and communication examples. However, it is severely over-length, mixing philosophical rationale, operational context, and actionable instructions into a single monolithic document. The extensive explanations of why scope management matters and how it fails are unnecessary for Claude and consume significant token budget that competes with conversation context.
Suggestions
Cut the content by 50-60%: remove the 'Core design philosophy' section, 'Why scope management fails', 'Scope creep vs scope change' definitions, and repeated justifications — Claude understands these concepts and the user doesn't need them explained in the skill.
Split into multiple files: keep SKILL.md as a concise overview with the step-by-step process and Standard templates, then create separate files for Extended mode (EXTENDED.md), M365 Connected Mode (CONNECTED.md), and operational knowledge/patterns (PATTERNS.md) with clear one-level-deep references.
Add explicit validation gates in the workflow: e.g., 'Confirm baseline extraction with the LPM before proceeding to Step 4' and 'Verify OOS entry accuracy with source document before drafting client communication.'
Tighten the output templates into copy-paste-ready markdown blocks with placeholder syntax (e.g., {{matter_name}}, {{entity_count}}) rather than embedding them within paragraphs of explanatory text.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~3500+ words. Extensive philosophical discussion about why scope management fails, design philosophy, 'buying work' patterns, and operational knowledge that Claude already understands. Much of this is explanatory context rather than actionable instruction — e.g., the entire 'Core design philosophy' section, 'Why scope management fails' section, and repeated justifications for the approach. | 1 / 3 |
Actionability | Provides concrete table templates, example communications, and structured field definitions which are useful. However, there's no executable code, no specific tool commands, and many instructions remain at the level of guidance rather than copy-paste-ready artifacts. The Excel workbook structure is described but not generated with specific formulas or scripts. | 2 / 3 |
Workflow Clarity | Steps 1-5 provide a clear sequence, and the Standard vs Extended tiering is well-structured. However, there are no explicit validation checkpoints or feedback loops for error recovery. The process describes what to produce but doesn't include verification steps (e.g., 'confirm baseline with partner before proceeding' as a gate). The workflow is more of a decision tree than a validated sequence. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content — from quick-start scope summaries to extended Excel workbook structures to M365 connected mode details — is inline in a single massive document. The Standard vs Extended split could easily be separate files, and the operational knowledge, cross-skill handoffs, and M365 sections should be broken out. | 1 / 3 |
Total | 6 / 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
1eb58a1
- 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.