Always-on standing rules for every bot in Matthew's fleet. Each profile carries a ≤40-word core line pointing here; this file holds the full verbatim text.
mcorbett51090/RavenClaude
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 963
- GitHub stars
- 9
- GitHub forks
- 1
Install with an AI assistant
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/mcorbett51090/RavenClaude.Loading the repository README…
Skills in this repository
Showing 40 of 963 collected skills.
Onboards a non-Claude-Code coding agent (GitHub Copilot CLI / OpenAI Codex CLI / Cursor / Aider / Devin Desktop) to this repo at session start. Use when this repo will be operated on by an agent that does not natively read CLAUDE.md. Routes through AGENTS.md,…
Translate `.ravenclaude/comfort-posture.yaml` into `.claude/settings.json` permission rules. Owns the (category, level) → permission-rule emission table that the `/set-posture` slash command applies. Read this skill when authoring or reviewing the translation…
Look up any skill in the marketplace by name or topic, including a disabled one, and get its exact re-enable command. Reach for this when you suspect a skill exists for the current task but it is not in your listing.
Enforce the Structured Output Protocol — every sub-agent handoff ends with a `
Team Lead dispatch playbook. Pick the surface first (slash command vs skill vs specialist agent vs orchestration shape — Step 1.25), then whether to delegate (Step 1.5), then which agents and order. Load whenever choosing skill vs agent vs slash, weighing…
Turn raw notes into evidence-weighted, bias-checked, prioritized, decision-ready insight — affinity/thematic analysis, keeping observation ('6 of 8 abandoned at step 3') strictly separate from interpretation ('because the CTA is unclear'), weighting each…
WCAG 2.2-aligned accessibility audit — semantics, ARIA, keyboard navigation, color contrast, focus management, motion preferences. Severity guide + tooling notes. Used by `accessibility-auditor` (primary).
Audit existing site content — full inventory (URL × type × intent × last-updated × owner), scoring against business / user-need / SEO criteria, remediation queue (keep / consolidate / rewrite / retire), and the migration plan when re-platforming. Reach for…
Design site information architecture — sitemap, URL taxonomy, navigation patterns (primary / utility / footer / contextual), card-sort discipline, content model that the IA implies, and the URL-to-template mapping. On a portal or signed-in UX review, place…
The gated pipeline the web-design Team Lead runs on a new marketing site or storefront — and, for a pure web-app, as a thinner brand/UX/a11y/perf wrapper around frontend-engineering's build, not the app's build pipeline: nine fail-closed gates (discovery → IA…
Design an accessible-by-default component pattern, semantic HTML first and ARIA only where needed. Reach for this on a design-system or component question.
Design and implement an Intercom-style card / "tile" UI — discrete soft-shadowed rounded surfaces on a calm monochromatic canvas, in a multi-pane (navigation-rail + content) layout, with a single restrained accent used only as hairlines, outlines, and…
Audit a page set against a named WCAG version and level, classify issues by severity/level, and compute a weighted conformance score. Reach for this on a conformance question.
Verify keyboard operability and screen-reader parity hands-on with the assistive technology real users use. Reach for this on a parity question.
Frame a fuzzy research ask into a researchable question, run the research-theater gate (is this a real question or a decision already made?), select the method (generative/evaluative, qual/quant, attitudinal/behavioral, moderated/unmoderated) from the…
Make a website adapt correctly to desktop, laptop, phone (portrait and landscape), tablet, iPad windows and foldables like iPhone Duo, the way Apple prescribes — one document, content-driven breakpoints, dynamic viewport units, safe areas, touch and input…
Build or extend a website from a catalog of section blocks, so the agent writes a typed manifest instead of markup and the layout is pixel-perfect on every screen. Ships a starter kit (tokens, layout contract, block CSS, schemas, thirteen exemplar blocks, a…
Build a non-React static site: semantic HTML, token-driven CSS (custom properties, grid/flex, container queries, logical properties), and an SSG-first Astro/11ty/Hugo or plain HTML+CSS build with islands only where earned. Covers reflow to 320px, in-markup…
Version a component library like the public contract it is (semver + changesets), ship breaking changes with codemods and loud deprecation, and drive adoption with metrics. Traverses the versioning branch of the design-systems decision tree: semver mapping →…
Design a game's menus and HUD so they read at a glance, navigate with a controller alone, and ship accessible. Decide what each HUD element is and whether it earns its place, build a universal Back with focus restoration, set accessibility presets over…
Use when designing, reviewing, or implementing Apple Wallet (.pkpass / PassKit) or Google Wallet passes — business cards, loyalty and membership cards, coupons, event tickets, save links — or a pass or contact-card builder, vCard export, or handing a card to…
Design or upgrade a tool that lets owners build their own forms — the definition model, field catalog, conditional logic and multi-step pages, versioning while responses exist, live preview, outputs (inbox, CSV, webhooks, email, CRM) and payment fields. Used…
Raise a page or app surface to the craft bar of Apple, Stripe, Cloudflare, Starlink, Tesla and recent game menus. Pick a craft register per surface, apply its sourced moves (glass with opaque fallbacks, static-first heroes, qualify-first CTAs, opt-in motion,…
Make a builder — form, contact card, Wallet pass, page or email — visually appealing and easy for owners. Covers editor layout, a live preview rendered by the same code as the output, insert and reorder without dragging, simple and advanced modes, undo and…
Oct 12 2026 direct-handoff rule. Use this when creating or refining a Grok Bot (CreateAgent/UpdateAgent): lean Goldilocks desc, ALWAYS/NEVER/NOT-MY-JOB, token-spend + CLI model (PE pack → specialist execute), talent→People Ops, fleet 3-model DONE, Matthew…
Oct 12 2026 direct-handoff rule. Use this on every user ask: direct bot-to-bot handoffs, CoS hub for results/decisions/failures; Matthew widgets recommended-first+primary (never bare menus); fleet 3-model DONE any iterative loop; talent→People Ops.
Oct 12 2026 direct-handoff rule. Use when optimizing Grok Bot fleet token spend or stamping personas. Fleet 3-model DONE; Matthew widgets recommended-first+primary; NEVER same-model sequential / bare menus. Advisory: skill ≠ meter.
Author Postgres Row Level Security policies (force-on, CI-deployed, denial-tested) for multi-tenant dashboards. Encodes the closeness-to-data invariant — tenant isolation at the closest-to-data layer the viewer's token cannot influence. Covers Postgres RLS +…
Roll up N entity trial balances (same period) into a group consolidation — reuses statement_engine per entity, then applies a BALANCED intercompany-elimination journal so IC receivable/payable and IC revenue/COGS net to zero, emits an entity-columns +…
Translate/remeasure ONE entity's functional-currency trial balance into a presentation-currency (USD) TB before consolidate.py, via scripts/remeasure.py. Current-rate method (A&L @ closing, P&L @ average, equity @ historical; plug = CTA to OCI/equity) or…
Turn per-entity close packages into a recurring, warehouse-backed, MULTI-TENANT controller dashboard where one controller sees only their PORTFOLIO of entities. Flattens close packages into fact/dim rows (scripts/close_package_to_rows.py, KPI parity with…
Hardened pac solution import plus explicit baseline-aware cloud-flow reactivation for SPN-driven CI/CD — preflight, baseline, import, reactivate, verify. Managed imports leave flows Draft when the importing identity lacks connection permission; this…
Report-wide referential-integrity validator for a PBIR Enhanced report's `definition/` tree. Deterministic, stdlib-only `check_refs.py` that catches DANGLING cross-file references — bookmarks pointing at deleted pages/visuals, `visualInteractions` naming…
Design a Power BI report/visualization in the Kurt-Buhler / Bas-Dohmen mold — a checklist-driven method: decide the question first, structure the page with the 3-30-300 information-seeking hierarchy, choose the visual by question-type, design headline KPIs…
Authors, validates and packages a claude.ai Organization Skill — the intake questions, the trigger and scope exercises, then lint, pack and verify against measured platform constraints. Reach for this when someone wants to publish a Skill to their…
Author a Vega-Lite / Deneb / SVG spec for a stated intent on any surface (web vega-embed, react-vega, Evidence, Observable, Power BI Deneb, Tableau extension/SVG, SVG-in-DAX). Six-step method: pick grammar → bind data → encode → wire interactivity → test…
Deterministic layout-arithmetic linter for dashboard/report page definitions. Runs seven checks — no-overlap (AABB), within-canvas, equal-gap, column-alignment, and three PBIR-specific invariants (no-empty-binding, bounded theme-override count,…
Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. Includes an inline substrate adapter that reads .ravenclaude/run-config.json once at startup; when enabled:false (the default) all agent()…
Iterate an artifact until it measurably passes a BOUNDED rubric — the Convergence Engine. Objective/deterministic gates run BEFORE any model judge, the judge is a DIFFERENT model than the author (never self-grade), the stop decision is a model-free predicate,…