Build dependency network and critical path from a matter plan. Produce an interactive Gantt, flag near-critical tasks, and run what-if cascade scenarios when delays occur — showing programme impact and drafting communications. Produces filtered workstream or jurisdiction views for local counsel. Trigger on: 'build a timeline', 'Gantt chart', 'critical path', 'what if X is delayed', 'what moves if', 'schedule impact', 'how does this affect the programme', 'when do we finish', 'can we still close on time', 'if we miss this deadline', 'run a what-if', 'visualise the plan', 'Germany timeline', 'what does the Employment workstream look like', 'timeline for local counsel', 'just show me the [workstream] tasks'.
60
70%
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/timeline-generator/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 articulates specific capabilities (dependency networks, Gantt charts, what-if scenarios, filtered views), provides comprehensive trigger terms covering both technical and conversational language, and occupies a distinct niche in legal matter planning and programme management. The description is well-structured with a clear separation between capability description and trigger guidance, and uses appropriate third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: build dependency network, critical path analysis, produce interactive Gantt, flag near-critical tasks, run what-if cascade scenarios, show programme impact, draft communications, and produce filtered workstream/jurisdiction views. | 3 / 3 |
Completeness | Clearly answers both 'what does this do' (builds dependency networks, produces Gantt charts, runs what-if scenarios, drafts communications, produces filtered views) AND 'when should Claude use it' with an explicit 'Trigger on:' clause listing numerous natural trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say, including conversational phrases like 'what moves if', 'can we still close on time', 'if we miss this deadline', 'just show me the [workstream] tasks', as well as technical terms like 'Gantt chart', 'critical path', and 'schedule impact'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining legal matter planning, critical path analysis, Gantt charts, what-if delay scenarios, and jurisdiction-specific views for local counsel. The domain-specific terminology (workstream, programme, local counsel, jurisdiction views) makes it very unlikely to conflict with generic project management or document skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
39%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 in legal project management scheduling and provides a thorough, well-structured workflow with clear validation checkpoints and mode-based operation. However, it is severely over-length — much of the content is educational explanation of scheduling concepts Claude already understands, and the entire skill is crammed into a single file with no progressive disclosure. The lack of executable code for the core calculations (CPM algorithm, HTML Gantt rendering) limits actionability despite the detailed procedural descriptions.
Suggestions
Reduce content by 50-60%: remove the 'Key Concepts' and 'Common Scheduling Failures' sections entirely (Claude knows CPM), and trim the 'Legal Scheduling Patterns' section to a concise reference table of dependency type → legal pattern mappings.
Split into multiple files: move Output Format specifications to OUTPUT_FORMAT.md, domain knowledge to LEGAL_PATTERNS.md, cross-skill handoffs to HANDOFFS.md, and M365 integration to M365_MODE.md — reference each with one-line links from the main skill.
Add executable code: include a working Python implementation of the forward/backward pass algorithm and a complete HTML canvas Gantt template that Claude can adapt, rather than describing the algorithm in prose.
Deduplicate repeated content: the cascade impact table format, CP status values, and float inheritance warnings each appear 2-3 times — consolidate to single authoritative definitions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~4000+ words. Extensive sections explain concepts Claude already knows (what critical path analysis is, what float means, what FS/FF/SS dependencies are, why effort differs from duration). The 'Key Concepts' and 'Common Scheduling Failures' sections are largely pedagogical rather than instructional. Multiple points are restated across sections (e.g., cascade impact table format appears twice, float inheritance warning repeated). The legal domain knowledge sections, while potentially useful, read more like a textbook than actionable instructions. | 1 / 3 |
Actionability | The step-by-step process provides a clear algorithmic framework with specific formulas (ES, EF, LS, LF, float calculations) and dependency type handling. However, there is no executable code for the actual calculations, no working HTML canvas Gantt implementation, and the Mermaid example is a template rather than a complete executable example. The what-if cascade protocol is well-structured but remains procedural description rather than executable implementation. | 2 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced across 8 steps with explicit validation checkpoints ('If critical inputs are missing, stop and ask'), feedback loops (what-if → recalculate → validate → communicate), and clear mode-based branching. The 'Before Starting Any Mode' checklist enforces prerequisites. The what-if cascade protocol has explicit numbered steps with validation at each stage. Mode 3 versioning discipline and Mode 4 float inheritance warnings serve as important guardrails. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files and no references to external files for detailed content. The domain knowledge sections, common scheduling failures, legal scheduling patterns, and extensive output format specifications could all be split into separate reference files. Everything is inline in a single massive document, making it difficult to navigate and consuming enormous context window space on every invocation. | 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.