strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Route prompts to a locally running Ollama instance instead of cloud AI APIs. Use this for privacy-sensitive tasks, offline work, or cost reduction. Pairs with the Docker stack in docker/local-ai-stack/.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Advise on learning rate schedules for transformer/LLM training. One of the most under-documented aspects of building LLMs from scratch — the schedule matters as much as the peak LR value.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Review codebase or design for modularity problems and produce actionable improvement recommendations. Also guides design of new modular boundaries from functional requirements. Inspired by Vlad Khononov's balanced-coupling model and golden-age-of-modularity principles. NOTE: Full upstream plugin at…
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Decompose a large task into N independent subtasks and dispatch them as parallel subagents, then aggregate results. Inspired by the Modal + OpenAI Agents SDK pattern of spawning multiple coding agents simultaneously — each working in its own sandbox — to discover solutions faster through parallelism.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Git worktree setup for zero dead time. Work on multiple branches simultaneously without switching branches or stashing. Ideal for running tests on main while implementing on a feature branch.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Core AI coding workflow. Orchestrates 8 patterns: Scout → Plan → Implement → Review, with smart commits, session rituals, and continuous learning capture. This is the master skill — invoke it at the start of any non-trivial task.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Maintain a structured, versioned library of the prompts and behavioral templates used by agents in this repository. Inspired by CL4R1T4S's approach of collecting and publishing AI system prompts for community benefit.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Inspired by the CL4R1T4S project (github.com/elder-plinius/CL4R1T4S), this skill audits and surfaces all implicit behavioral instructions, system prompts, and agent directives embedded in this repository. It generates a human-readable transparency report so anyone can understand exactly how the AI agents in this repo…
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Gate check before tagging and releasing a new version. Run this skill before any git tag vX.Y.Z operation.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Surface relevant past patterns before starting work. Read the learnings file and extract rules that apply to the current task. Prevents repeating past mistakes.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Keep AGENTS.md files and .Codex/state/ in sync with the current repo reality. Use after significant structural changes, after adding risky modules, or when AGENTS.md feels stale.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Implements codebase intelligence layers similar to repowise-dev/repowise. Provides dependency graph, git history, auto-generated documentation, and architectural decisions intelligence for AI agents.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Conduct structured, systematic research on any topic — synthesizing sources, extracting key findings, identifying gaps, and producing a clear research brief. Designed for both technical and non-technical research tasks.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Track, display, and summarise all resources consumed or produced during an agent session: files read/written, URLs fetched, tools called, tokens used, and external dependencies touched.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Mandatory deep review for changes to security-sensitive modules: adminauth.py, keystore.py, agent/tools.py, and any auth/session/key path. Do not skip this for any change to these files.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Run shell commands or code snippets in an isolated subprocess environment, preventing side effects from leaking into the host workspace. Mirrors the "Modal Sandbox" pattern described in the OpenAI Agents SDK blog post — give an agent a safe "home computer" to work on.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Detect and prevent scope creep during implementation. Keeps Claude focused on the original task and flags when it's about to do more than asked.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Enables the agent to analyze its own skill library, identify gaps or weaknesses, and propose or implement improvements to existing skills or new skill definitions.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Write structured resume documentation for the next session. Captures state, context, and next actions so any AI or developer can continue without archaeology.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Enables the agent to combine multiple existing skills into a coordinated workflow for complex tasks that no single skill covers. Acts as an orchestration layer over the skill library.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Quality gates + conventional commits. Run tests, lint, and typecheck before committing. Format the commit message as a conventional commit. Blocks on failure.