srinitude

Use when diagnosing Hermes state.db WAL advisories.

Use when tuning Honcho for a Hermes profile.

Use when managing crit reviews programmatically.

Use when reviewing code, plans, or live pages with crit.

Use when writing code or Markdown anywhere.

Use when preparing input for a standing Hermes goal.

Use when authoring or editing in-repo Hermes skills.

Use when managing user-local Hermes skill lifecycle.

How to drive Pi's `/until-done` autonomous goal loop — owning the contract, calling the four `until_done_*` tools, applying pi-config TDD discipline (ANALYSIS → BOOTSTRAP → RED → GREEN → REFACTOR), and respecting ask-before boundaries. Pi loads this skill on demand whenever a `/until-done` goal is active.

Generates one-of-a-kind websites, apps, images, SVGs, and videos with deterministic style resolution, multi-modal generation chains, pixel-level verification, and taste personalization via Mastra workflows. Use when asked to "design", "build a site", "landing page", "app screen", "generate image", "make video", "create SVG", "style transfer", "redesign", or any visual creative task. Supports interactive and headless (--print) execution modes. Not for backend code, databases, or non-visual work.

Produce unique designs that actually work — for websites, web apps, mobile apps (iOS/Android/visionOS), dashboards, marketing sites, brand identities, slides, posters, motion, or generative media. Use when the user wants to design, redesign, build, ship, fix, improve, refactor, polish, audit, critique, harden, brand, theme, animate, layout, type, color, accessibility, responsive, dark mode, glass, brutalist, minimalist, editorial, bento, dashboard, hero, landing, or component work — even if the user does not explicitly say "design". Also triggers on requests for premium feel, taste-driven UI, unique brand differentiation, extracting tokens from inspiration, building a design system, generating brand kits, evaluating screenshots or live URLs, producing a DESIGN.md spec, or making an existing design less generic. Do NOT use for pure backend, CLI, or non-visual work.

Build deterministic Agent Skills that weak models can execute without guessing. Use when the user says "build a deterministic skill", "make an agentskills.io-compliant skill", "validate a skill with skills-ref", "make the skill easy for dumb models", "write a skill generator", "add skill evals", or "make a skill the dumbest model can follow", even if they do not say "Agent Skills" explicitly. Do NOT use for ordinary prose editing, pure trigger-phrase tuning, non-skill prompt engineering, or generic documentation tasks.

Mastra memory provider for Hermes — observation log, semantic recall, working-memory mirror, and versioned identity-file storage (SOUL/MEMORY/USER/AGENTS) backed by @mastra/memory + @mastra/libsql.

Use when the user asks to analyze reference images, screenshots, moodboards, style frames, brand boards, cinematic stills, or product UI shots to infer a production-grade design system, design tokens, brand/art direction, cinematic language, worldbuilding, motion rules, or YAML style specification. Handles multimodal visual extraction into valid YAML for UI/UX, brand, motion, creative direction, AI generation, and design-engineering workflows. Not for generating images or ordinary frontend implementation unless visual references must be reverse-engineered first.

Use when an outcome is stated, inferred, or hidden.

Publish a local Hermes skill as a public GitHub repo, protect its main branch with required CI, version it, and reinstall it natively with hub provenance. Use when the user says "publish this skill to GitHub", "make a skill repo with CI", "add branch protection to a skill repo", "version a Hermes skill", "release a skill", "reinstall the skill from GitHub", or "turn this skill into an open-source repo", even if they do not say "Hermes" explicitly. Do NOT use for authoring skill content (use building-deterministic-skills), generic repo creation unrelated to skills (use github-repo-management), or installing third-party skills you did not author (use hermes-skill-operations).

Extend or override Hermes runtime behavior using the supported plugin, config, skill, and env layers in ~/.hermes — never by editing the Nous-deployed package. Use when the user says "extend Hermes", "add a Hermes plugin", "override Hermes behavior", "add a slash command", "add a hermes CLI subcommand", "hook a tool call", "customize Hermes without forking", or "change Hermes without touching the package", even if they do not say "plugin" explicitly. Do NOT use for claude-code (Anthropic's claude CLI delegation), hermes-config-management (pure config.yaml audits), hermes-skill-operations (installing/updating skill packages), or hermes-tui-customization (TUI chrome) tasks.

Generate isolated optimized Markdown goal prompts plus a paired ANALYSIS/BOOTSTRAP/RED/GREEN/REFACTOR TDD task list YAML that any coding agent can dynamically update through its building process. Use when a user asks to enhance, structure, validate, or save a goal prompt without executing it. Do NOT use as an automatic `/goal` preflight, slash-command interceptor, goal-loop hook, or to execute the generated goal or its task list; this skill only produces and validates the standalone prompt file and its companion task list YAML.

Use when reference images, screenshots, moodboards, or visual design-system YAML should become a complete deterministic YAML inventory of iOS design-system atoms. Handles iOS atomic tokens, primitive visual atoms, static values, dynamic adaptations, accessibility variants, SwiftUI/UIKit handoff fields, and strict no-null/no-empty/no-unknown validation.