titan

Solid

Delivering working code fastest via build-first product delivery through minimum agent chains; S/M scopes skip planning and build immediately. Use when compressing time-to-first-PR.

AI & Automation 72 stars 14 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
62
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

<!-- CAPABILITIES_SUMMARY: - build_first_delivery: Turn product goals into working code via the smallest justified agent chain - scope_adaptive_minimal_chains: Select S/M/L/XL chains automatically based on file count and complexity - agent_justification_gate: Gate every agent deployment with three mandatory justification questions - anti_stall_recovery_cascade: Execute L1-L5 recovery ladder to guarantee forward progress - titan_state_persistence: Persist TITAN_STATE across sessions for resumable delivery - model_routing_cost_optimization: Route agent tasks to cheapest adequate model tier for up to 87% cost reduction - nexus_autorun_chain_orchestration: Issue and validate NEXUS_AUTORUN_FULL chains across all lifecycle phases ORCHESTRATION_PATTERNS: - Pattern A: Direct Build (Builder -> Radar) - Pattern B: Guided Build (Lens -> Sherpa -> Builder -> Radar) - Pattern C: Phased Delivery (justified phases and agents only) - Pattern D: Full Lifecycle (all 9 phases, Rally only when justified) COLLABORATION_PATTERNS: - Scribe[unified] -> Titan: Business-tech alignment context for scope classification - Magi -> Titan: MAGI_VERDICT for high-risk decisions - Nexus -> Titan: NEXUS_COMPLETE_[STATUS] chain results - Titan -> Nexus: NEXUS_AUTORUN_FULL chain execution requests - Titan -> Rally: Parallel Epic team launch for independent tasks - Titan -> Sherpa: Task decomposition requests for L/XL phases - Titan -> Magi: MAGI_REQUEST for medium/high-risk decisions BIDIRECTIONAL_PARTNERS: - ...

Details

Author
simota
Repository
simota/agent-skills
Created
7 months ago
Last Updated
today
Language
HTML
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category