Skill Claude CodeCodex
Operate on @draft facts — collaboratively refine them into precise, actionable @spec facts. Resolve ambiguities, fill gaps, eliminate contradictions, and sharpen labels until every fact is ready to implement. Use when asked to refine facts, clarify the spec, review facts for quality, or "work on facts" with the user.
Skill Claude CodeCodex
Manage .facts files — atomic, validatable truth statements about a project. Install, check, list, add, edit, remove, and lint facts via the CLI. ALWAYS read this skill when the user mentions facts in any capacity.
Skill Claude CodeCodex
Timeboxed ideation on a topic using propose-and-critique subagent pairs. Use when the user wants to brainstorm, explore ideas, discover features, generate options, or think through possibilities for a specified duration. Triggers on requests like "brainstorm X for 30 minutes", "ideate on X", "spend an hour thinking…
Skill Claude CodeCodex
Use when the user specifies a task and a duration, and the work should be done iteratively by subagents over that time period.
Instructions file CodexOpenCode
AGENTS.md instructions for av/mi, covering mi — agent instructions, architecture, running locally, tests and checks and editing index.mjs.
Instructions file
Claude Code instructions for av/mi, a project described as: self-extending sandboxed agentic harness. a loop, two tools and an llm.
Skill Claude CodeCodex
Fix bugs, crashes, errors, or failing tests. Use when "it's broken", "getting an error", "test is failing", or the cause isn't obvious.
Skill Claude CodeCodex
Run parallel or isolated subagents for independent subtasks (research, parallel analysis, one-shot transforms) to avoid bloating the main context.
Skill Claude CodeCodex
Answer "how does X work", "where is X defined", or "trace through Y" questions about a codebase using parallel subagent searches with cited summaries.
Skill Claude CodeCodex
Write a new SKILL.md to teach yourself a procedure for a recurring task. Use when asked to "write a skill", "create a skill", "add a skill", "remember how to X", "make a procedure for X", or when you notice a task pattern worth recalling in future sessions.
Skill Claude CodeCodex
Write a strategy doc before starting multi-step, multi-file, or unclear work. Use when asked to "plan out", "figure out the approach", or before any task needing more than one step.
Skill Claude CodeCodex
Restructure code without changing behavior. Triggers: "rename X to Y", "move X to Y", "extract X into Y", "clean up / split / deduplicate code" — one transformation at a time, tests kept green.
Skill Claude CodeCodex
Review code, a PR, branch, or staged diff. Use when asked to "review", "give feedback", "check this PR", or "what's wrong with this diff".
Skill Claude CodeCodex
Answer questions about how 'mi' works, write new tools, or modify the harness. Use for "how do you work", "write a tool", "add a tool", "create a tool", "extend yourself", "edit yourself", "what tools do you have", or any introspection/modification of the running agent.
Skill Claude CodeCodex
Track a numbered list of steps to completion. Use when the user gives explicit numbered steps ("1) do X 2) do Y"), says "I need to do N things", or when a multi-step job needs a checklist. Distinct from plan (strategy): tasks tracks what's done/pending during execution.
Skill Claude CodeCodex
Add new behavior test-first (write failing test → make it pass → refactor). Use when asked to "add a test for", "implement X with tests", or extending a codebase that already has a test suite.
Skill Claude CodeCodex
Run lint, typecheck, tests, or build — and fix any failures found. Use when asked "does it build", "run the tests", "check for lint errors", "find and fix lint errors", or after making code changes.
Skill Claude CodeCodex
Use when the user requests integration testing, feature validation, or test plan execution.
Skill Claude CodeCodex
Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other LLM-introduced architectural decay — over a specified duration.
Skill Claude CodeCodex
Produce a researched long-form article from a topic prompt via an orchestrated pipeline - research agent (first-person sources, working-definition gate), narrative-architecture outline, writer/cold-reviewer loop with an explicit ACCEPT/REVISE verdict contract, then a catalog-deslop pass with a regression gate. The…
Skill Claude CodeCodex
Runs autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style of karpathy/autoresearch. Use when the user says "autoresearch" (optionally with a focus, e.g. "autoresearch the optimizer"), asks to run experiments on a repo overnight, to hill-climb or optimize a…
Skill Claude CodeCodex
Create custom modules for Harbor Boost, an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or…
Skill Claude CodeCodex
Systematically explore and test any software project (CLI, API, Backend, Library, etc.) to find bugs, usability issues, and edge cases. Produces a structured report with full reproduction evidence (exact commands, inputs, logs, and tracebacks) for every issue.
Skill Claude CodeCodex
Fully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage each finding, fix confirmed issues with subagents, then audit all fixes against repo constraints and target platforms. Runs end-to-end without user interaction.