strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Audit all system-level instructions embedded in this repository's Claude configuration, surface them as a structured inventory, and validate them for consistency, safety, and alignment with project goals.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Keep long-running agent tasks visibly alive by emitting periodic heartbeat status updates to stdout. Prevents silent timeouts and gives the operator confidence the task is still progressing.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Prevents scope creep by explicitly defining the boundaries of a task before implementation begins. Ensures the agent works on exactly what was asked — no more, no less.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Write or update tests before (or alongside) implementation. Ensures every code change is verifiably correct before merging.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Transform a GitHub issue (ticket) into a complete, merged pull request. End-to-end automation from reading the issue to pushing working, tested code.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Deep-dive diagnostics for tokenizer behavior in LLM training and inference. Tokenizer bugs are uniquely dangerous because they're silent — the model trains fine, but on subtly wrong data.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Monitor and diagnose LLM/ML training instability — loss spikes, exploding gradients, dead neurons, and learning rate mismatches. Surfaces actionable fixes before they derail a training run.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Session closing ritual with learning capture. Run at the end of every coding session. 5 steps: changes audit, quality check, learning capture, next session planning, summary.
strikersam/autonomous-ai-agency
Agent Claude Code
The Implementer agent receives a plan from the Planner and executes it step by step. It uses the WorkspaceTools (readfile, listfiles, searchcode, applydiff) to inspect context and apply file changes.