frankxai

311 mods across 29 repositories, 81 stars between them.

org-role-design

169

frankxai/Starlight-Intelligence-System

Command Claude Code

Design or redesign a role with explicit decision rights, measurable accountabilities, success criteria, escalation path, interfaces with adjacent roles, and common failure modes. Refuses RACI-only outputs and vague accountabilities. Output anchors the role for hiring, performance, and succession downstream.

8 2d ago A 58 tokens original MIT

org-span

170

frankxai/Starlight-Intelligence-System

Command Claude Code

Span-of-control architecture audit and redesign. Audits per-manager spans against research bounds (5-9 for complex knowledge work; up to 15-20 for repetitive supervised). Surfaces pattern flags (top-heavy / middle-thin / over-spanned individual contributors), redesign recommendations with sequencing, and a transition…

8 2d ago A 74 tokens original MIT

org-succession

171

frankxai/Starlight-Intelligence-System

Command Claude Code

Succession planning with real readiness — not paper. Per critical role: identified successor, readiness gap, 6-12-month development plan, tested partial in-role, named timeline, transparent communication. Refuses paper-only succession plans. Surfaces single-points-of-failure, unprepared successors, and undisclosed…

8 2d ago A 77 tokens original MIT

frankxai/Starlight-Intelligence-System

Command Claude Code

Generate a 60-minute solution-focused + CBT-grounded coaching session script for a manager-as-coach engagement. Coaches use questions, not advice. Produces session structure (check-in → focus → scaling → exception-finding → small-step → close), follow-up prompts, and the manager-as-coach training notes that name the…

8 2d ago A 83 tokens original MIT

frankxai/Starlight-Intelligence-System

Command Claude Code

Psychologist-grade conflict mediation between two parties. Produces 90-minute mediation session structure — separate prep with each party (each three-conversations narrative collected privately) + joint session structure with psychological safety design + commitments + follow-up. Names what to escalate to professional…

8 2d ago A 95 tokens original MIT

frankxai/Starlight-Intelligence-System

Command Claude Code

Three-conversations framework rehearsal (Stone/Patton/Heen — Harvard Negotiation Project) for high-stakes conversations — termination, demotion, hard feedback, conflict surfacing. Produces three-conversations breakdown (what-happened / feelings / identity), conversation script with multiple opening choices, SCARF…

8 2d ago A 93 tokens original MIT

frankxai/Starlight-Intelligence-System

Command Claude Code

Rehearse a high-stakes feedback conversation before delivery. Takes an SBI sketch + recipient context, produces multiple openings, anticipated reactions with responses, SCARF-aware adjustments, and three branching paths the conversation could take with the manager's response to each. Saves to…

8 2d ago A 78 tokens original MIT

perf-review-redesign

176

frankxai/Starlight-Intelligence-System

Command Claude Code

Replace a broken annual performance ritual with a research-backed continuous + quarterly + annual-comp architecture. Produces redesigned cadence, manager scripts, employee-prep guide, calibration protocol, and a transition plan from old to new. Heavy disclaimer on legal/HRIS implications because changing comp linkage…

8 2d ago A 64 tokens original MIT

process-inbox

177

frankxai/Starlight-Intelligence-System

Command Claude Code

Process the .intake/ inbox in one shot. Catalogs each unprocessed file via subagent, applies operational-tier insights, archives originals, surfaces substrate-tier asks for /starlight-board, and surfaces cross-repo drops for Frank to action. Idempotent — safe to re-run.

8 2d ago A 65 tokens original MIT

reclaim-knowledge

178

frankxai/Starlight-Intelligence-System

Command Claude Code

Organize scattered professional material into a domain-based second-brain architecture. Maps existing sources (Canva, Drive, local folders, Notion, screenshots) to functional domains. Non-technical-friendly — produces folder structure + drag-and-drop instructions, not CLI commands.

8 2d ago A 58 tokens original MIT

sip-attest-audio

180

frankxai/Starlight-Intelligence-System

Command Claude Code

Attest an audio artifact (music track, voice-over, podcast, soundscape). Generates SIP attestation embedded in ID3 tags + sidecar .sip.json. Refuses decorative use. v7.5+ — scaffold present, full implementation pending.

8 2d ago A 57 tokens original MIT

frankxai/awesome-hermes-agent-skills

Skill Claude CodeCodex

Use when orchestrating multiple coding agent CLIs (Claude Code, Codex, OpenCode, Grok CLI, Antigravity). Discovery, comparison, structured prompting, and multi-agent handoff patterns. Portable free pack — no host-specific secrets.

5 2d ago A 56 tokens original MIT

todo-discipline

183

frankxai/awesome-hermes-agent-skills

Skill Claude CodeCodex

Use when starting any complex task (3+ steps) or before declaring work complete. Enforces todo/task state to match reality — merge updates + read verification. Prevents false completion.

5 2d ago A 41 tokens original MIT

arcanea-image-gen

184

frankxai/awesome-hermes-agents

Skill Claude CodeCodex

Purpose: Enable Hermes Agents to generate high-quality images, video, lipsync, and cinema content using Arcanea Studio's multi-model router (200+ models, provider-agnostic).

3 2d ago A 0 tokens original MIT

frankxai/affiliate-agent-skills

Instructions file CodexOpenCode

Instructions for frankxai/affiliate-agent-skills, covering repository instructions, classification, trinity branding & marketplace absorption (2026-07-14), agent rules and class-specific guidance.

2 1mo ago A 897 tokens original MIT

affiliate-audit

186

frankxai/affiliate-agent-skills

Skill Claude CodeCodex

Map which content mentions paying AI tools but lacks affiliate links, and which programs to join first. Use when monetizing AI-tool comparison content, choosing affiliate programs, or auditing a passive-income site's link coverage.

2 1mo ago A 45 tokens original MIT

agentic-income

187

frankxai/affiliate-agent-skills

Skill Claude CodeCodex

The operating brain for building income systems with AI agents. Use when planning, building, or scaling an affiliate/content/product income network — deciding what to build next, where money actually comes from, how to make it compound, and how the system improves itself. Composes affiliate-audit. Trigger phrases…

2 1mo ago A 98 tokens original MIT

affiliate-audit

188

frankxai/agentic-income-skills

Skill Claude CodeCodex

Map which content mentions paying AI tools but lacks affiliate links, and which programs to join first. Use when monetizing AI-tool comparison content, choosing affiliate programs, or auditing a passive-income site's link coverage.

2 5d ago A 45 tokens copy · 100% MIT

agentic-income

189

frankxai/agentic-income-skills

Skill Claude CodeCodex

Build and operate principal-owned AI income systems that perform accepted paid work. Use when discovering an agent service opportunity, validating demand, creating an Outcome Pack, implementing a vertical AI system, defining agent authority, evaluating delivery, exposing a Skill/MCP/A2A service, or proving net…

2 5d ago A 96 tokens original MIT