mouadja02

mouadja02/skills

Skill Claude CodeCodex

Use when designing scalable MCP tool routing, dynamic tool retrieval, agent-tool graphs, tool inventory indexing, or routing policies for agents with many available tools.

mouadja02/skills

Skill Claude CodeCodex

This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.

mouadja02/skills

Skill Claude CodeCodex

Use when building a Python terminal UI inspired by Claude Code with Rich. Translates a detailed TypeScript/Ink-style visual reference into a staged Python architecture for logo, message stream, streaming Markdown, tools, diffs, prompt, footer, spinners, permissions, transcript mode, themes, accessibility, and tests.…

mouadja02/skills

Skill Claude CodeCodex

Use when building Hugging Face smolagents, code-executing agents, Python-action agents, Hub-shared tools, or lightweight agent prototypes that need sandboxing and provider flexibility.

mouadja02/skills

Skill Claude CodeCodex

Use when designing defensive monitoring for agent systems whose risks accumulate across users, sessions, subagents, files, or tool calls. Adds online cross-context clustering with rare escalation, time-to-detect evaluation, provenance checks for control-like workspace content, and sanitized commits for persistent…

mouadja02/skills

Skill Claude CodeCodex

Turns a structured-autonomy PR plan (plans/{feature}/plan.md) into copy-paste-ready implementation documentation with complete code for every step, saved as implementation.md. Use after a plan exists and before implementation, when each step needs fully specified changes.

mouadja02/skills

Skill Claude CodeCodex

Use when executing a previously agreed autonomous agent plan — running the steps within declared boundaries, checkpointing progress, and escalating when a stop condition is hit.

mouadja02/skills

Skill Claude CodeCodex

Use when an autonomous agent run needs a plan before execution — decomposing the goal, setting explicit boundaries and stop conditions, and defining what the agent may decide alone versus escalate.

mouadja02/skills

Skill Claude CodeCodex

This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces.

mouadja02/skills

Skill Claude CodeCodex

Builds AI-powered trading and financial analysis agents with multi-agent LLM architectures: research pipelines, sentiment signals, portfolio optimization, backtesting, risk guardrails, and market monitoring. Use when designing or implementing an LLM-based trading or market-analysis system.

mouadja02/skills

Skill Claude CodeCodex

Use when diagnosing agent benchmarks or runtime failures from trajectories instead of aggregate pass rates. Builds shared action-observation decision landscapes, identifies productive cores and trap regions, profiles Access/Trap/Repair behavior, and designs conservative trap-triggered recovery experiments.

mouadja02/skills

Skill Claude CodeCodex

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: Implementing self-critique and reflection loops Building evaluator-optimizer pipelines for quality-critical generation Creating test-driven code refinement workflows Designing rubric-based or LLM-as-judge evaluation systems…

mouadja02/skills

Skill Claude CodeCodex

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to…

mouadja02/skills

Skill Claude CodeCodex

Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples. Use when the user runs /si:extract or asks to package a recurring solution from memory into a skill.

mouadja02/skills

Skill Claude CodeCodex

Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement. Use when the user runs /si:promote or asks to make a learned behavior permanent.

mouadja02/skills

Skill Claude CodeCodex

Saves an important piece of knowledge to auto-memory with a timestamp and context. Use when the user runs /si:remember or says to remember something, or when a hard-won debugging insight, project convention, tool gotcha, or architecture decision should not depend on automatic capture.

mouadja02/skills

Skill Claude CodeCodex

Analyzes auto-memory (MEMORY.md and topic files) for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use after a major feature or debugging session, when /si:status shows MEMORY.md over 150 lines, weekly during active development, or before a new project phase.

mouadja02/skills

Skill Claude CodeCodex

Shows a memory health dashboard: line counts, topic files, capacity, stale entries, and recommendations across all memory systems. Use when the user runs /si:status or asks how large or healthy the project's agent memory is.

mouadja02/skills

Skill Claude CodeCodex

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce…

mouadja02/skills

Skill Claude CodeCodex

Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling. Use when the user runs /ar:loop or wants an experiment to keep iterating on a schedule.

mouadja02/skills

Skill Claude CodeCodex

Resumes a paused or context-limited autoresearch experiment: checks out the experiment branch, reads the results history, and continues iterating. Use when the user runs /ar:resume or wants to pick up an experiment where it stopped.

mouadja02/skills

Skill Claude CodeCodex

Runs exactly one autoresearch experiment iteration: review history, choose a change, edit the target file, commit, evaluate, then keep or discard. Use when the user runs /ar:run or wants a single manual step instead of an autonomous loop.

mouadja02/skills

Skill Claude CodeCodex

Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator. Use when the user runs /ar:setup or asks to start optimizing a file with the autoresearch loop.

mouadja02/skills

Skill Claude CodeCodex

Runs an autonomous experiment loop on any programming task: you define the goal, metric, and eval command; the agent edits code, measures, and keeps or discards each change until interrupted. Use when optimizing a measurable target (speed, accuracy, size, score) by iteration.