LIBRARY-FIRST PROTOCOL (MANDATORY)
Before writing ANY code, you MUST check:
Step 1: Library Catalog
- Location:
.claude/library/catalog.json
- If match >70%: REUSE or ADAPT
Step 2: Patterns Guide
- Location:
.claude/docs/inventories/LIBRARY-PATTERNS-GUIDE.md
- If pattern exists: FOLLOW documented approach
Step 3: Existing Projects
- Location:
D:\Projects\*
- If found: EXTRACT and adapt
Decision Matrix
| Match | Action |
|---|
| Library >90% | REUSE directly |
| Library 70-90% | ADAPT minimally |
| Pattern exists | FOLLOW pattern |
| In project | EXTRACT |
| No match | BUILD (add to library after) |
STANDARD OPERATING PROCEDURE
Purpose
Plan and execute product launches with aligned objectives, cross-functional readiness, and clear contingency paths.
Trigger Conditions
- Positive: Product or feature launch planning; Cross-functional launch readiness; Need launch communications and risk plan
- Negative: Pure engineering release with no GTM (route to github-release-management); Ongoing incident handling (route to cicd-intelligent-recovery); Ops maturity review without launch (route to production-readiness)
Guardrails
- Structure-first: keep SKILL.md aligned with examples/, tests/, and any resources/references so downstream agents always have scaffolding.
- Adversarial validation is mandatory: cover boundary cases, failure paths, and rollback drills before declaring the SOP complete.
- Prompt hygiene: separate hard vs. soft vs. inferred constraints and confirm inferred constraints before acting.
- Explicit confidence ceilings: format as 'Confidence: X.XX (ceiling: TYPE Y.YY)' and never exceed the ceiling for the claim type.
- MCP traceability: tag sessions WHO=operations-{name}-{session_id}, WHY=skill-execution, and capture evidence links in outputs.
- Avoid anti-patterns: undocumented changes, missing rollback paths, skipped tests, or unbounded automation without approvals.
Required Artifacts
- SKILL.md (this SOP)
- metadata.json
- Add examples/tests/resources during execution if missing
Execution Phases
-
Align goals and constraints
- Capture launch objectives, audiences, and success metrics
- List dependencies (product, marketing, support, ops)
- Confirm budget, channels, and timelines
-
Plan the launch
- Design run sheet with milestones, owners, and approvals
- Prepare assets, messaging, and instrumentation
- Define risk matrix with triggers and contingency actions
-
Rehearse and harden
- Run dry runs or canaries
- Validate support/readiness (runbooks, on-call, comms)
- Lock fallback and rollback procedures
-
Execute and review
- Launch with live monitoring and comms cadence
- Capture metrics vs. targets
- Run post-launch review and assign follow-ups
Output Format
- Launch brief with objectives, metrics, and audiences
- Run sheet with milestones, owners, and approvals
- Communications and asset checklist
- Risk and contingency plan with triggers
- Post-launch report with metrics and follow-ups
Validation Checklist
- Owners and approvals assigned for each milestone
- Contingency/rollback communications ready
- Monitoring and support coverage confirmed
- Launch metrics and success criteria defined
- Confidence ceiling stated for launch go/no-go
Confidence: 0.70 (ceiling: inference 0.70) - Launch SOP mirrors skill-forge structure with rehearsals and fallbacks