Skill Registry

Use when a task needs the judgment of an ambulance driver/attendant (non-EMT) — deciding emergency-vehicle driving mode, clearing an intersection under lights-and-siren, handling a scheduled inter-facility or discharge transport, securing and lifting a patient on a stretcher/gurney, or responding to time pressure from family or a sending facility to "run it hot."

Use when a task needs the judgment of an Architecture/Engineering firm or department manager — pricing a project fee (lump sum vs. hourly vs. % of construction cost), staffing a project against backlog, evaluating scope creep on a fixed-fee job, managing professional liability exposure, or deciding whether to pursue a project given current utilization.

Use when a task needs the judgment of an astronomer — calculating exposure time or signal-to-noise for a target, writing the feasibility math for a telescope-time proposal, reducing photometric or spectroscopic data, distinguishing a systematic error floor from statistical noise, or reviewing an observational result for calibration or upper-limit red flags.

Use when a task needs the judgment of an auto-body-repairer — deciding whether a damaged structural component gets pulled or replaced, reconciling an insurance estimate against actual teardown damage, writing a supplement, determining whether a repair triggers ADAS recalibration, or checking a proposed repair against an OEM position statement.

Use when a task needs the judgment of a radio broadcast announcer or on-air disc jockey — backtiming a live break against a hard network join or legal ID, deciding what to cut when a caller or breaking-news read runs long, judging FCC indecency/EAS exposure on live content, structuring a voice-tracked shift so it doesn't read as canned, or diagnosing why a daypart's PPM numbers are sliding.

Use when a task needs the judgment of a Derrick Operator (derrickhand) — running the monkeyboard during a pipe trip, reading trip-tank volume against calculated displacement for a swab or kick signature, calculating a barite weight-up in sacks, deciding whether a volume anomaly warrants stopping the trip for a flow check, or running the mud circulating system (shakers, desander, degasser) between trips.

Workflow for analyzing bug reports, tracing root causes, and generating structured bug-fix implementation plans with rollback strategies.

Language-agnostic workflow for code reviews and security audits against Clean Code/SOLID principles, generating formal refactoring plans.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Generates formal, structured, and executable implementation plan documents based on specifications.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Delegate one bounded child route through quest-passport law, local coding-agent execution defaults, hard gates for progression, self-agent, and stress posture, and governed return into reviewed closeout. Use when a parent route already has a real anchor and named outputs and the honest next move is a narrower child reviewer, evaluator, verifier, or leaf helper rather than a larger orchestration layer. Do not use when the route lacks an anchor, the outputs are unnamed, the work is `d3+` and still needs a split, or remote delegation is being used to bypass proof, approval, or closeout posture.

Fetch a web page (URL) and return clean Markdown via local trafilatura, with Exa MCP as a fallback for JS-rendered or anti-bot pages. Use when the user asks to read, fetch, scrape, summarize, or quote a URL — prefer this over the built-in WebFetch tool. Don't use for binary files (PDFs, images, archives) or for fetching API/JSON endpoints.

Hands-on playbook for macOS disk cleanup, dev-machine optimization, and proactive health alerting. Use when the Mac is full or slow, when a kernel panic / watchdog timeout / vm-compressor-space-shortage / Jetsam event happened, when the user asks to free disk space, audit storage, set up disk/memory alerts, or restore the same monitoring on a new Mac. Built around Mole (`mo` CLI) for safety guards plus a custom LaunchAgent-based alerter for active warnings. Covers Apple Silicon laptops with heavy AI/Docker workloads. Not for general macOS support, hardware diagnostics, networking issues, GUI / window-manager bugs, Time Machine recovery, broken app installs, or app-specific performance problems unrelated to disk or memory pressure.

Deep research over the Semantic Scholar Graph API. Covers endpoints missing from allenai's lookup skill — paper references (backward citations), recommendations, batch paper lookup (up to 500 IDs), snippet search, and multi-hop citation graph traversal (BFS forward/backward). Use when the user asks to build a citation graph, expand a literature seed, find related work, run a reference network traversal, explore what a paper cites or what cites it beyond simple lookup, or batch-resolve many DOI/arXiv/S2 IDs. For multi-step research questions, delegate to the deep-paper-researcher subagent to keep the main context clean. Not for single paper-by-ID lookups (use semantic-scholar-lookup) or topical discovery (use web_search_advanced_exa).

Orchestrate the a11y accessibility lifecycle: scout → plan → critique → [perspective audit] → test → critique. Dual-mode: full lifecycle automation or step-by-step dispatch. Spawns specialist agents at depth-1 from the main session.

Use when the user wants to record an architectural decision — drafting an Architecture Decision Record (ADR) or RFC, documenting a design choice and its trade-offs, or capturing why an approach was taken. Detects the repo's existing ADR location and template style (MADR or Nygard) and matches it; if none exists, sets one up. Writes the record; it does not change code.

Use when the user wants a commit message written for currently staged changes. Reads `git diff --cached`, recent log style, and CLAUDE.md, then outputs a conventional-commit-style message — type(scope) summary + why-focused body.

Use when the user wants prose, comments, docs, or a file's text to read like a human engineer wrote it instead of an AI. Strips AI tells (em-dashes, filler openers, chatbot scaffolding) by rewriting, then runs klaussy's deterministic scrubber as a guaranteed backstop. Never touches code.

Use when the user wants to run, start, or launch this project's app — to watch a change work end-to-end, reproduce behavior in the real app, or smoke-test locally. Finds the run command from CLAUDE.md and drives the app; it does not write features or fix bugs.

Use when the user explicitly wants to turn clean, human prose INTO maximal AI slop — as a joke, a demo of what AI tells look like, or to stress-test the humanize skill by feeding it the worst input imaginable. The evil twin of humanize — it adds every tell humanize strips. For laughs and demos only; never run it on a real deliverable.

Use when the user wants to record an architectural decision — drafting an Architecture Decision Record (ADR) or RFC, documenting a design choice and its trade-offs, or capturing why an approach was taken. Detects the repo's existing ADR location and template style (MADR or Nygard) and matches it; if none exists, sets one up. Writes the record; it does not change code.

Use when the user wants a commit message written for currently staged changes. Reads `git diff --cached`, recent log style, and CLAUDE.md, then outputs a conventional-commit-style message — type(scope) summary + why-focused body.

Use when the user wants prose, comments, docs, or a file's text to read like a human engineer wrote it instead of an AI. Strips AI tells (em-dashes, filler openers, chatbot scaffolding) by rewriting, then runs klaussy's deterministic scrubber as a guaranteed backstop. Never touches code.

Use when the user wants to run, start, or launch this project's app — to watch a change work end-to-end, reproduce behavior in the real app, or smoke-test locally. Finds the run command from CLAUDE.md and drives the app; it does not write features or fix bugs.