Stats
Actions
Tags
From taches-principled
Auto-selects improvement method (code exploration, workflow mapping, or waste identification) for a given target. Use when user says 'analyze this', 'look into this code', 'what's wrong here', or 'find the problem'.
How this skill is triggered — by the user, by Claude, or both
Slash command
/taches-principled:analyse [target description]When to use
Use when the user says "analyze this", "look into this code", "what's wrong here", or "find the problem". IMMEDIATELY when investigating code quality, process bottlenecks, or implementation gaps. Do NOT use when the problem is a specific incident (use analyse-problem instead), when code already exists and needs review (use code-review), or when complexity reduction is the goal (use code-simplify).
[target description]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
IF analyzing code implementation, exploring unfamiliar code, or checking documentation accuracy → use Gemba Walk (go see the actual code)
IF analyzing code implementation, exploring unfamiliar code, or checking documentation accuracy → use Gemba Walk (go see the actual code) IF analyzing workflows, processes, multi-stage pipelines, or bottlenecks → use Value Stream Mapping IF analyzing code quality, technical debt, over-engineering, or resource waste → use Muda (Waste Analysis) IF the method is already clear from context → apply it directly without auto-selection IF combining with structured problem documentation → produce findings for a downstream A3 analysis
Automatically selects and applies the most appropriate analysis technique for a given target. Three methods cover code exploration, process mapping, and waste identification.
Match the analysis method to the nature of the target. Code problems need code observation. Process problems need flow measurement. Quality problems need waste identification.
| If the target is... | Use... |
|---|---|
| Code implementation, legacy systems, gap between docs and reality | Gemba Walk |
| Workflows, CI/CD pipelines, team handoffs, cycle time | Value Stream Mapping |
| Code quality, technical debt, duplication, resource use | Muda Analysis |
Each method follows a distinct process:
Gemba Walk — Observe actual code:
Value Stream Mapping — Measure the flow:
Muda Analysis — Classify waste:
A structured analysis report with method rationale, observations, prioritized recommendations, and estimated improvement impact. Written to conversation — actionable for downstream improvement cycles.
Each method targets a distinct problem class. A single generic "analyze everything" approach would produce shallower results. The auto-selector removes decision overhead when the target type is clear.
Gemba Walk output is artifact-centric (surprises, gaps). VSM output is metric-centric (lead time, efficiency). Muda output is category-centric (waste type, impact). Forcing all three into one template would lose method-specific signal.
npx claudepluginhub git-fg/taches-principledProvides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.