Block completion claims until verification evidence has been produced in the current message. Use before marking a task/slice/milestone complete, before creating a commit or PR, before saying "it works" or "tests pass", and any time you are about to claim work is done. The rule is: evidence before claims, always — running the verification must happen now, not "earlier in the session". Fresh output or no claim.

Package findings from a completed spike into a durable, project-local skill that auto-loads on future similar work. Reads the most recent `.gsd/workflows/spikes/` directory, interviews the user briefly on what's reusable, then writes `.claude/skills/<name>/SKILL.md`. Use when asked to "wrap up the spike", "package this as a skill", "make this reusable", "turn findings into a skill", or at the end of the synthesize phase of `/gsd start spike`. Closes the parity gap with GSD v1's `/gsd-spike-wrap-up`.

Produce 3+ radically different designs for a module, API, or interface, compare them in prose, and synthesize a recommendation. Use when asked to "design an interface", "shape this API", "design it twice", "explore module boundaries", or when planning a new deep module and the first idea is unlikely to be the best. Based on "Design It Twice" from A Philosophy of Software Design — the value is the contrast, not the first draft.

Design or review an HTTP/REST/GraphQL API for versioning, pagination, error shapes, idempotency, auth, and evolvability. Use when asked to "design an API", "shape the endpoints", "design the schema", "add a new endpoint", "review this API", or when building/modifying a public or internal HTTP surface. Complements `design-an-interface` (which is interface-agnostic) by covering HTTP-specific concerns like status codes, cache headers, and breaking-change management.

Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages. Use when docs have fallen behind code changes, after a batch of features lands, or when preparing a release. Trigger keywords - update docs, draft docs, docs from commits, sync docs, catch up docs, doc debt, docs behind, docs drift.

Manually dispatch and iterate on the Release Canary workflow that smoke-tests published OpenShell artifacts (install.sh on macOS/Ubuntu/Fedora, Helm chart on kind) after each Release Dev publish. Use when changing `.github/workflows/release-canary.yml`, validating a release before tagging, debugging a canary failure, or reproducing a canary job locally. Trigger keywords - release canary, release-canary, canary failed, canary dispatch, test release canary, post-release smoke, install.sh canary, helm chart canary, kind canary, dispatch canary.

Detect and fix drift across agent-first infrastructure files. Ensures skill inventories, workflow chains, architecture tables, issue/PR templates, and cross-references stay consistent when skills, crates, or workflows change. Run after adding, removing, or renaming skills or components. Trigger keywords - sync agent infra, sync skills, update agent docs, check agent consistency, agent infra drift, sync contributing, sync agents.

Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".

Works with OrchardCore multi-tenancy — shells, ShellSettings, creating/configuring tenants programmatically, running code in a tenant scope, feature profiles, and data isolation. Use when the user needs to create or manage tenants, run code inside a tenant, pre-configure tenants, or understand shell lifecycle.

Localizes OrchardCore apps — UI strings (IStringLocalizer/IViewLocalizer S, T, H), PO files and pluralization, content translation (LocalizationPart, culture picker), and supported-culture configuration. Use when the user needs to translate strings, add a culture, set up PO files, or make content items multilingual.

Controls how OrchardCore renders content — placement.json rules, display drivers, shapes, zones, alternates, and editor groupings (tabs/cards/columns). Use when the user needs to position or hide a part/field, move a shape to another zone, add alternates or wrappers, build admin editor layouts, or write a display driver.

Creates and updates OrchardCore data migrations (DataMigration classes with CreateAsync/UpdateFromX). Use when the user needs to alter content type definitions, create or change SQL index tables, patch existing content items, run a recipe migration, or version a module's schema.

Compare multiple sources on a topic and produce a grounded comparison matrix. Use when the user asks to compare papers, tools, approaches, frameworks, or claims across multiple sources.

Plan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.

Turn research findings into a polished paper-style draft with sections, equations, and citations. Use when the user asks to write a paper, draft a report, write up findings, or produce a technical document from collected research.

Inspect visible research run state, scheduled research follow-ups when available, and durable watch artifacts. Use when the user asks what's running for a research workflow or wants research-run status.

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

Contribute changes to the Feynman repository itself. Use when the task is to add features, fix bugs, update prompts or skills, change install or release behavior, improve docs, or prepare a focused PR against this repo.

Use Borzoi-style regulatory genomics models for sequence-to-expression or variant-effect analysis. Use when the task asks for noncoding variant impact, regulatory sequence design, or expression prediction.

Predict or audit protein structures with AlphaFold2-style workflows. Use when a research task needs monomer/multimer structure prediction, MSA/template handling, confidence metrics, or comparison against PDB/AlphaFold references.