odin

ai-collab-protocols

Surface in-task AI collaboration protocols one tactic at a time, replacing ambiguous references with durable, recoverable handles.

API & Backend Solid

api-design

Guide stable API and interface design. Use when creating REST or GraphQL endpoints, defining type contracts, or establishing frontend/backend or module boundaries.

askme

Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via `/askme`.

ast-grep

Run code analysis and refactoring with ast-grep. Use when doing AST-based modifications, structural search, linting across code shape, or replacing regex-fragile transformations.

atomic-issues-prs

Publish a change-set as atomic GitHub issues or PRs. Use when the user says "atomic PRs" or wants one issue/PR per logical change.

autolearn

Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this".

Run a hands-off plan-to-ship pipeline by chaining existing skills. Use when the user says "autopilot", "take this from plan to shipped", "run the whole pipeline", "hands-off ship it", or "do the end-to-end build".

axiom-mode

Switch to ODIN's compact formal-logic English register using predicate claims and ASCII keywords. Use when the user requests "axiom", "axiom-mode", "axiom-compact", "formal-logic", or "compact form".

batch-ask-me

Use when the user wants to walk a complex design space round by round: map the decision tree, fire the current frontier as batched single-select questions, and loop until shared understanding is reached. Triggers: multi-fork decisions, ambiguous requirements, unresolved prerequisites, "batch ask me", "clarify the design space".

brainstorm

Explore vague or ambitious ideas into a right-sized requirements-only plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning, not for a decisive verdict on whether to adopt or switch to a specific external technology, library, or platform.

breaking-driven

Demolish bloated code and re-derive it clean, cutting every surface the rebuilt contract does not name. Use for a repo-wide bloat sweep, when patching a subsystem has stopped paying, or when the user says "this whole module is bloated", "rewrite this properly", or "break it and rebuild".

Testing & QA Solid

browser-testing

Test and debug browser code with Chrome DevTools MCP. Use when building or debugging browser UI, inspecting the DOM, capturing console errors, analyzing network requests, or verifying visual output.

Show all 55 bundled skills

can-i-help

Route contributors to data-backed contribution opportunities. Use when the user asks "where can I help", "what can I contribute", "find a good first issue", or "what should I work on".

cascade-dedup

Strip duplicate and conflicting directives across the system-prompt cascade family: the canonical baseline, the six output-style embeds, and the two external harness embeds.

caveman

Switch to a verbosity-reduction response register. Use when the user says "caveman", "compact mode", "less tokens", "be brief", or context-window pressure calls for shorter replies.

DevOps & Infrastructure Solid

ci-cd

Set up or modify CI/CD pipelines and deployment automation. Use when setting up build pipelines, automating quality gates, configuring test runners in CI, or establishing deployment strategies.

clarify

Scan a request, document, or conversation for ambiguities, undefined terms, implicit assumptions, and unstated boundaries, then surface them as a certainty-tiered findings report with recommended defaults. Use when the user says "clarify", "what is ambiguous here", "find the gaps in this spec", "what am I assuming", or when a prompt or spec reads as under-specified before planning.

cleanup-codebase

Reduce internal duplication, dead code, and ceremony. Use when you spot dead fields, redundant wrappers, or speculative abstractions in code you are already editing.

commit-push-current

Commit working-tree changes and push to the current branch: no branch creation, no branch switch, no PR. Use when asked to push to the branch you are already on, including the default branch.

commit-push-pr

Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.

commit-push

Use when asked to ship/publish commits without opening a PR.

commit

Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate, value-communicating message.

compound

Use when the user says "compound this", after a verified non-trivial outcome that should live in docs/solutions/ or CONCEPTS.md, or when a durable project term needs defining.

contexts

Use when the user says "get context on X", "how does X work", or wants architectural orientation before coding.

debug

Hypothesis-driven debugging. Use when a test fails, a crash or exception occurs, output is wrong, or an intermittent flake has no obvious cause.

dedup-skills

Ledger-first dedup of a skills/ or prompt-directory tree. Use when the user asks to dedup skills, find rules repeated across or within skill files, or check whether skills contradict each other.

deprecate-and-migrate

Use when removing old code, migrating users to a new implementation, or deciding whether to maintain or sunset something.

deps-upgrade

Dependency-upgrade campaign. Use when CVEs require remediation, a major upstream version lands, stack compatibility forces a sweep, on a scheduled hygiene cadence, or for a lockfile audit before a release.

design

Use when starting UI work, defining palettes or design tokens, or when output looks AI-generic, vibe-coded, or default-framework sloppy.

deslop

Certainty-graded cleanup of code debris. Use when the user says "deslop", "remove debug code", "find placeholders or stub code", or "remove dead code", or when the slop skill routes code findings here.

doc-review

Use when the user asks to review or critique a prose planning document — a plan, spec, PRD, requirements doc, or design doc.

docs-and-adrs

Document decisions, not just code. Use when making architectural decisions, changing public APIs, shipping features, or capturing context for future engineers and agents.

doubt-driven

Doubt-driven adversarial review. Use when correctness matters more than speed, the code is unfamiliar, stakes are high, a claim can't be checked by the type system or compiler, or verifying now is cheaper than debugging later.

drift-detect

Use when the user says "plan drift", asks whether the roadmap, plans, or docs still match the code, or is deciding what to rebuild when restarting a stalled project.

duet

Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.

enhance

Audit and tighten agent/plugin surfaces. Use when the user asks to enhance a plugin config, agent definition, skill, or CLAUDE.md.

exhaustive

Prove a decision space, state space, requirement set, or behavior surface is fully covered by enumerating every cell and classifying each as covered, gap, or deferred with an executed check. Use when the user says "exhaustive", "prove coverage", "did I miss any case", "enumerate the state space", or when a refactor or feature needs a completeness audit before it is called done.

explore

Explore the codebase to map structure, symbols, and dependencies. Use when the user says "explore", "find where X is", "how does X work in the code", or "map the codebase".

fix

Use when the user says "fix", "make it pass", or "apply the findings", or hands a verifier failure or bug description.

Web & Frontend Solid

frontend-ui

Build user-facing interfaces. Use when creating or modifying components, implementing layouts, managing state, or when the output must look hand-crafted rather than AI-generated.

generate-my-taste

Generate a personal taste skill from local evidence and confirmation forks.

skill_name

Personal taste skill — 5 evidence-derived anchors ({anchor_names}) for prose, code, design, and decisions. Two modes: audit judges an artifact against the two-sided charter; anchor loads the taste register before producing. Trigger with "{trigger_phrase}", "taste-test", "is this slop?", or "overkill?".

gh-fix-ci

Use when the user asks to debug or fix failing CI checks on a GitHub pull request.

Code & Development Solid

git-branchless

Use when doing multi-commit work, stack edits, rebases, fixups, stacked-PR publishing, or when the user mentions branchless, smartlog, git move, or git undo.

github-solution-research

Find open-source solutions on GitHub. Use when facing a bug, integration failure, dependency issue, unclear API usage, implementation blocker, or tool capability need.

github-triage

Triage GitHub issues. Use when the user wants to triage incoming issues, prepare issues for an autonomous agent, or move an issue between workflow states.

handoff

Snapshot the current session into a resumable handoff artifact so a cold session, agent, or person continues without replaying context. Use when the user says "write a handoff", "hand off", "snapshot this session", "I'm running low on context", "pause and pack this up for the next session", or "resume this later".

ideate

Generate grounded, divergent ideas from the codebase. Use when the user says "let's brainstorm", "what should we build", or "any ideas for".

improve-architecture

Surface deepening refactors that turn shallow modules into deep ones. Use when the user asks to improve architecture, find refactor candidates, raise testability, or make a codebase more agent-navigable.

incremental

Use when a change spans multiple files, or you're about to write a lot of code at once.

inits

Creates or improves an AGENTS.md file. Use when onboarding to a repo, or capturing conventions, constraints, and rationale that are expensive to rediscover.

llm-self-loop

Restructures human-gated workflows into autonomous LLM loops with file-based outputs. Use when a task needs a button click, dashboard check, or human verdict inside its iteration loop.

loop-me

Use when the user wants to design a recurring personal or team workflow: capture loops, write specs in workflows/*.md, and run a stateful askme session until the spec is implementer-ready. Triggers: "loop me", "design a workflow", "automate this recurring task", morning routine, inbox processing.