Generate radically-different module or API contract designs in parallel, then compare on depth, simplicity, and ease-of-correct-use. Trigger when the user is shaping a new module surface, exploring contract options, comparing module shapes, or applying "design it twice" to a first-pass sketch.
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
Grill against the existing domain model. Stress-test a plan's terminology against CONTEXT.md and ADRs; update both inline as decisions crystallise. Trigger when user proposes a feature/refactor that touches business concepts and the project has documented domain language to honor — or when domain language is missing…
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
Mechanically tighten existing prose — restructure sections by dependency order, split or merge paragraphs, remove redundancy. Use to compress verbose plan files, READMEs, ADRs, and design docs. Does NOT change voice, register, tone, or any ODIN-mandated phrasing.
Polymorphic iterative repair loop — accept a verifier failure, structured findings (review/resolve/triage-issue), or a bug description; modify→verify→keep on green, auto-revert on guard regression, until clean or iteration cap. Use when the user says "fix", "make it pass", or "apply the findings", or hands an artifact…
Evidence-first generator for a personal -taste Claude Code skill. Mines local memories and agent histories for influences, slop bans, and overkill bans; asks compact confirmation forks; previews the synthesis; then writes a right-sized taste skill with exactly 5 anchors by default. Trigger with "generate my taste…
Personal taste skill — 5 evidence-derived anchors ({anchornames}) 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 "{triggerphrase}", "taste-test", "is this slop?", or "overkill?".
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize the failure, then plan and implement the fix after user approval. Use when the user asks to debug or fix failing PR CI on GitHub Actions; external checks (Buildkite, etc.) are reported as URLs only.
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…
Triage GitHub issues through a configurable label-based state machine. Use when user wants to triage incoming issues, prepare issues for an autonomous agent, or move an issue between workflow states. Repo inferred from git remote; all GitHub calls go through gh.
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
Surface deepening refactors that turn shallow modules into deep ones, informed by CONTEXT.md and docs/adr/. Use when the user asks to improve architecture, find refactor candidates, raise testability, or make a codebase more agent-navigable. Skip for single localized fixes.
Analyze a codebase and create or improve an AGENTS.md file for future agent instances. Use when onboarding to a repository and capturing hard-to-rediscover conventions, constraints, and rationale.
Restructure Web-UI / human-triggered tasks into CLI + file-output loops the LLM can iterate alone, with structured logs and addressable scratchpads. Apply trap-or-abandon: if a step cannot be looped, improve the harness rather than babysit. Trigger on iterative grunt-work, "push a button in a web UI to trigger this"…
Audit memory directory for structural issues (orphans, dangling refs, duplicates, missing sections, oversized entries) and staleness against session-history transcripts; report-first, fix-on-confirmation. Use when the user says "audit memory", "memory hygiene", or "find stale/duplicate memories".
Produce share-safe copies of memory files under /tmp with PII redacted (paths, emails, session IDs, dates) and credentials scanned (tokens, keys); never mutates originals. Use when the user says "sanitize memory for sharing", "redact memory PII", or "scan memory for credentials".
Scan agent's session-history transcripts for save-worthy signals (corrections, preferences, decisions, references), propose and write auto-memory files with valid frontmatter and MEMORY.md entry. Use when the user says "save this to memory", "remember that", or "scan this session for memories".
Decompose a task into independent concerns and execute them through broadly parallel, specialized agent groups. Use when a request involves multiple independent sub-tasks, research across separate domains, or work that can be parallelized across files or modules.
Hotspot detection and performance root-cause analysis: flamegraph interpretation, allocation tracking, latency profiling, regression measurement. Use when a workload misses its latency, throughput, or memory budget; when a benchmark regresses; or before optimizing any hot path (no optimization without a profile).