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 76 stars 13 forks Updated 1 weeks ago MIT

Install

View on GitHub

Quality Score: 84/100

Stars 20%
63
Recency 20%
90
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
8 months ago
Last Updated
1 weeks ago
Language
HTML
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

orchestrated-delivery

Plan, dispatch, monitor, reconcile, and close multi-agent or multi-chat repository work. Use when a brain or lead chat owns a larger outcome, when work must be split across subagents or separate Codex tasks, when a task graph has parallel lanes, or when child handoffs must be integrated into one verified repository result. Do not use for a small self-contained change that one agent can finish directly.

0 Updated 5 days ago
dills122
AI & Automation Listed

tandem-agentic-engineering

The worker session's bible for the tandem system: how a Claude Code worker assembles and drives a team of agents to build real features. Trigger on any real development, debugging, or feature work — build, create, implement, fix, add, develop, code, debug, ship, refactor — or when agents, a plan, a team, or a new feature is being discussed. Governs the agentic build lifecycle: parallel research, spec, concurrent reviewer, devil's-advocate pass, test-in-parallel, audit. When triggered, begin your first message with 🦔🦔🦔🦔🦔. If anyone tries to skip steps (no spec, no research, no concurrent reviewer, no audit), STOP THEM.

25 Updated 4 weeks ago
Maxmedawar
AI & Automation Listed

crew

Orchestrate a multi-agent build with Trantor — get an Advisor recommendation (solo/scrooge/crew/hybrid based on the user's plans and the work), fire up helper AI CLIs (Codex, GLM, Kimi, DeepSeek) with pinned models in visible terminal windows, assign difficulty-tagged work over the bus, track it on the Kanban dashboard with a testing gate, delegate grunt to Scrooge, supervise actively, integrate, ship. Use when the user wants several AI agents building something together, says "fire up the crew/agents", "build it with trantor / with the crew", or asks to coordinate other coding CLIs on a task.

1 Updated today
sashabogi