strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Build and run a structured agent harness — an outer loop that gives an LLM a defined set of tools (capabilities) and drives it to task completion. Based on the architecture from the OpenAI Agents SDK blog post: an Agent is a for-loop with an LLM running tools until done.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Automatically detect and fix linting, formatting, and type errors across the codebase. Acts as a one-shot "clean up everything" command before committing or opening a PR.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Convert a chaotic list of scattered ideas, notes, or thoughts into a structured, prioritized action plan. Transforms raw cognitive output into organized tasks with clear next steps.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Ensure every meaningful change has a proper docs/changelog.md entry. Use before every commit that changes behaviour, adds features, or fixes bugs.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Design and validate checkpointing strategies for LLM training runs. One of the most painful lessons from building LLMs from scratch: losing 12 hours of compute to a spike you can't roll back from.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Prime Claude with deep repository context before starting any significant task. Ensures Claude has a full mental model of the codebase architecture, conventions, and constraints before writing a single line of code.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Resume an interrupted AI coding session after token exhaustion, rate limiting, or process restart. Use when a session was interrupted mid-task.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Multi-perspective code review before merging. Simulates a council of reviewers (security, correctness, performance, maintainability) independently evaluating a change. Use before any PR merge or for significant changes.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Audit training data and tokenizer pipelines for quality issues that silently degrade LLM training. Data problems are the #1 underdiagnosed cause of poor model performance — most tutorials skip this entirely.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Systematically trace and resolve bugs using hypothesis-driven debugging. Prevents random trial-and-error and ensures the root cause is found, not just the symptom.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Review, validate, and update Python dependencies safely. Use when adding a new package, upgrading an existing one, or reviewing the dependency surface.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Remove AI code slop before committing. Review AI-generated code for unnecessary verbosity, redundant comments, over-engineering, and low-signal patterns that degrade codebase quality over time.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Keep documentation in sync after code changes. Run after any change that alters module behaviour, APIs, env vars, or architecture.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Clone an existing plan, task thread, or agent session so you can explore an alternative approach without losing the original. Analogous to "duplicate thread" in Copilot's mission control.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Rapidly process a backlog of emails by categorizing, prioritizing, and drafting responses or actions. Reduces inbox overwhelm and ensures nothing important is missed.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Implements a Fabric-like reusable prompt pattern system. Allows storing, retrieving, and composing prompt patterns for consistent AI interactions.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Implement new features behind feature flags to enable safe, gradual rollouts and easy rollbacks without code deployments.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Ensures the repository's git history, branch state, and commit messages are clean, meaningful, and follow project conventions before pushing or merging.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Converts this codebase into a queryable knowledge graph so AI sessions query graph.json (71.5x fewer tokens) instead of reading raw source files. Integrates with Claude Code and Codex via repo hooks that auto-refresh on session start and after turns.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Plan a multi-file or multi-step implementation before writing any code. Use before any change touching more than two files, adding a new feature, or changing a module interface.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Analytics, heatmaps, and trends from session history. Analyze checkpoint logs, learnings, and git history to surface patterns: which files change most, which steps fail most often, and where to invest in tooling or tests.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Provides a structured, repeatable process for resolving GitHub issues from start to finish — reading the issue, planning a solution, implementing it, testing it, and closing it with a proper commit and changelog entry.
strikersam/autonomous-ai-agency
Skill Claude CodeCodex
Persist corrections and patterns to long-term memory. When a mistake is made or a rule is learned, write it to .claude/state/learnings.md so it's never repeated.