agentsclimarketplace
Sign in

Inception workflow planning

Skill yamatatsu/claude-aidlc/skills/inception-workflow-planning

Create execution plan determining which stages to run. Analyzes scope, impact, and risk to recommend optimal workflow.From its SKILL.md

Install
npx -y skills add yamatatsu/claude-aidlc --skill inception-workflow-planning

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.8 KB, as published. Nobody here has run it

AI-DLC: Workflow Planning (Inception)

ultrathink

Determine which stages to execute and create the comprehensive execution plan. This stage always executes.

Prerequisites Check

  1. Read aidlc-docs/aidlc-state.md — verify Requirements Analysis is complete
  2. Log stage start in aidlc-docs/audit.md

Execution

Follow workflow-planning-detail.md:

Analysis

  1. Load all prior context — reverse engineering, requirements, user stories (if any)
  2. Scope and impact analysis:
    • Transformation scope (brownfield: single component vs architectural)
    • Change impact (user-facing, structural, data, API, NFR)
    • Component relationships (brownfield)
    • Risk assessment (Low/Medium/High/Critical)

Determination

  1. Phase determination — for each conditional stage, evaluate EXECUTE vs SKIP with rationale:
    • Application Design, Units Generation
    • Functional Design, NFR Requirements, NFR Design, Infrastructure Design
  2. Note adaptive detail — all executed stages create ALL defined artifacts
  3. Multi-module coordination (brownfield: update sequence, dependencies)

Documentation

  1. Generate workflow visualization — Mermaid flowchart with styling per detail doc
  2. Create execution plan → aidlc-docs/inception/plans/execution-plan.md
  3. Update state — aidlc-state.md with execution plan summary

Completion

  1. Present plan to user with EXECUTE/SKIP rationale for each stage
  2. Emphasize user control: "You can override any recommendation"
  3. WAIT for user approval
  4. Log approval in audit.md
  5. Guide to next based on plan: first EXECUTE stage (typically /aidlc:inception-application-design or /aidlc:construction-functional-design)

Reference Files

Critical Rules

  • Always present EXECUTE/SKIP rationale for each conditional stage
  • User can override any recommendation
  • Validate Mermaid diagrams before writing
  • Include text alternative for workflow visualization
  • Append to audit.md — never overwrite

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.