// Defines rules for skill activation, including input requirements, output contracts, conflict lists, and performance costs. Enforces Lean Execution mode by default.
[HINT] Download the complete skill directory including SKILL.md and all related files
| name | skill-activation-policy |
| description | Defines rules for skill activation, including input requirements, output contracts, conflict lists, and performance costs. Enforces Lean Execution mode by default. |
"Efficiency is intelligent laziness."
meta-governor is always active and cannot be disabled.indonesian-communicator is always active. All user-facing output in Bahasa Indonesia.output-discipline is always active. Professional formatting enforced.hallucination-guard is always active. Verification before generation.| Category | Skills | Behavior |
|---|---|---|
| Always-On | meta-governor, indonesian-communicator, output-discipline, hallucination-guard | Every request. Cannot disable. |
| Conditional | context-memory (long chat), task-orchestrator (multi-step only), clarification-enforcer (ambiguity >40%), constraint-enforcer (code output only) | When condition met. |
| On-Demand | All other skills | Trigger word or escalation. |
| Skill | Scope | Does NOT |
|---|---|---|
meta-governor | Skill lifecycle & selection | Plan tasks, Solve problems |
task-orchestrator | Multi-step task decomposition | Select skills, Reason logic |
structured-reasoning | Complex problem solving | Plan tasks, Select skills |
Overlap → lower-cost skill runs. Higher-cost needs explicit escalation.
| Tier | Skills | Auto? |
|---|---|---|
| Low | output-discipline, indonesian-communicator, constraint-enforcer, hallucination-guard, error-taxonomy, i18n-localizer, stakeholder-translator | ✅ |
| Medium | structured-reasoning, debug-protocol, refactor-code, migration-planner | ✅ |
| High | deep-audit, advanced-architecture, optimize-perf, security-scan | ❌ |
| Conflict | Winner | Reason |
|---|---|---|
clarification-enforcer vs task-orchestrator | clarification-enforcer | Clarify before planning |
constraint-enforcer vs refactor-code | constraint-enforcer | Contract lock |
hallucination-guard vs output-discipline | hallucination-guard | Correctness > brevity |
debug-protocol vs optimize-perf | debug-protocol | Fix first, optimize later |
security-scan vs optimize-perf | security-scan | Security > performance |
migration-planner vs refactor-code | migration-planner | Data safety > code cleanliness |
indonesian-communicator vs output-discipline | indonesian-communicator | Language rule overrides format |
Only User or meta-governor may escalate to High-tier.
Auto-escalate ONLY if: Security risk, Data loss risk, or Architecture violation.
Max 2 Evaluators/cycle. Self-Critique 1x. Ambiguity >40%. Refinement 1x. Shortest Correct Path.
Trigger: "deep review", "enterprise audit", "full analysis". Max 4 Evaluators. Critique 2x. High-tier auto-allowed. Auto-revert after task.
Plan selected → No re-evaluation unless user introduces new variable.
Lean Mode default. No redundant layers. No governance stacking.
To ensure no skill is wasted, the following chains are MANDATORY for complex tasks:
refactor-code -> doc-architect (Update README/ADR) -> ux-polish.security-scan (Secret check) -> output-discipline.optimize-perf (Query check) -> devops-architect (Config check).| Skill | Keywords |
|---|---|
deep-audit | "audit", "review architecture", "check layers" |
security-scan | "security check", "vulnerability" |
optimize-perf | "slow", "optimize", "performance" |
advanced-architecture | "DDD", "Event Sourcing", "Enterprise" |
| Deep-Cycle Mode | "deep review", "enterprise audit", "full analysis" |