Build and sharpen a project's ubiquitous language as you design: challenge terms against the glossary, sharpen fuzzy ones, and write CONTEXT.md the moment a term resolves. Use when pinning down domain terminology or maintaining the domain model. Not the contexts skill, which routes pre-implementation context gathering.
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.
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. For doc-vs-code drift inside a specific diff, use sync-docs.
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.
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…
Use when a concept needs making clear rather than practising: build the intuition, explain why it exists and what it replaced, trace where it came from, draw it, or contrast it against what it gets confused with. For exercises and grading, use drill.
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".
Rebuild code from its performance floor: split hot paths from cold, demolish and re-derive the hot ones first, then grill every remaining inefficiency in the cold ones. Use for a subsystem-wide or repo-wide performance campaign, when another round of patching has stopped paying, or when the user says "make this as…
Strip the leading framing from a question, put the bare version to several fresh zero-context reads, and report where they diverge before reporting where they agree. Use when one read might be an artifact of how the question was asked, or the user says "check this from scratch", "fan this out", or "is this just my…
Press a decision you just made until you can explain it plainly to a skeptic, or until the gap you cannot explain is named out loud. Use right after committing to a design or an approach, or when the user says "feynman this", "explain this like I am new", or "do you actually understand this". It tests your own grasp…
Surface in-task-collaboration protocols when the user describes an AI workflow informally — URL-as-entity-reference, PR-comment threads as session memory. Trigger when the user names entities by colloquial label instead of stable URL, asks "how should I structure this for Claude", or describes a multi-step Claude…
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
Run the atomic-commit workflow on the current changes, then publish the resulting commits to the remote. Use whenever the user says "commit and push", "ship these changes", "atomic commit and push", "publish my work", or wants atomic commits delivered to origin in one step. Prefers git submit (git-branchless); falls…
Review staged + unstaged changes and split them into one commit per logical change. Use whenever the user says "atomic commit", "commit my changes", "split this into commits", or has multiple unrelated edits sitting in the working tree — even if they don't say "atomic". Runs repo-native type-checker and linter before…
ODIN's compact-form conversation skill -- formal-logic English register with predicate claims, Hoare-triple framing, and ASCII shortened-English keywords. Trigger when user requests "axiom", "axiom-mode", "axiom-compact", or "compact form".
Verbosity-reduction response register. Drops redundant clauses, narrative hedging, and ceremony while preserving articles, grammar, and decision-oriented register. Trigger on "caveman", "compact mode", "less tokens", "be brief", or context-window pressure in long sessions.
Reduce concepts, duplication, and ceremony in internal code while touching nearby code. Use when working an existing path and you spot dead fields, redundant wrappers, or speculative abstractions; distinct from refactor-break-bw-compat (internal hygiene, not public API removal).
Auto-router for context gathering. Detects whether the task needs codebase exploration or external knowledge research and dispatches accordingly. Trigger on "get context", "background on X", "context on X", "how does X work", architectural orientation, or any setup-before-coding request.
Hypothesis-driven defect isolation — stack-trace forensics, breakpoint strategy, state inspection, and root-cause confirmation via minimal repro. Use when a defect surfaces (test failure, crash, exception, wrong output, intermittent flake) and the cause is not immediately obvious from the change set.
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…