helioy-plugins

Orchestrate a helioy-bus warroom: tmux agents doing parallel work under one orchestrator. Use for warroom, mixture of experts, MoE review, peer consensus, sign-off, brainstorm, spec-writing, scout, reuse audit, code-review, engineering, slice-build-loop, or any request that dispatches work to parallel agents.

Use for any helioy-bus mail operation: checking your inbox, sending messages to other agents, broadcasting to all agents, or responding to a "you have mail!" nudge. Use at the start of any task to check for directives from peer agents. Also use when the user says things like "reply to that agent", "tell nancy I'm done", "who's on the bus?", "who else is online?", "check for messages", "check for directives", or "send a message to X". Any inter-agent communication goes through this skill.

Improve codebase health through careful decomposition, consolidation, boundary repair, and developer experience cleanup. Use when the user asks for code hygiene, code-hygene, LOC reduction, refactoring, decomposing large files or functions, finding natural seams, reducing duplication, reorganizing modules, improving maintainability, or taking a craftsmanship pass across Rust, Python, TypeScript, JavaScript, Go, or any other language.

Generate accurate codebase onboarding maps and architecture diagrams. Use when the user asks for a codebase map, repo map, architecture map, onboarding map, dependency map, MAP.md, or a diagram that helps agents understand a codebase. For fmm indexed repos, use fmm MCP tools extensively and validate diagrams.

Claim a crates.io package name by checking availability and publishing a placeholder. Use when the user says "crate claim", "cargo claim", "reserve crate name", or wants to check if a crates.io name is available. Takes a crate name as an argument. Note: crates.io publishes are permanent (yank only, no unpublish).

Kubernetes fundamentals taught from first principles (kubernetes-the-hard-way backbone). Use BEFORE reasoning from scratch about any Kubernetes internals: cluster bootstrap, the control plane (apiserver / controller-manager / scheduler), etcd, the PKI/TLS cert mesh and CN/O-to-RBAC mapping, kubeconfigs, kubelet / containerd / CRI, pod networking and CNI, kube-proxy, encryption at rest, the Node Authorizer, or CRDs and the Helioy v2 K8s-shaped endgame. Routes you into the verified curriculum at ~/.mdx/knowledge/kubernetes/. Trigger when: explaining or debugging Kubernetes internals, designing K8s-shaped infrastructure, reviewing cluster config, or onboarding to how the core components fit together.

Use when planning, reviewing, or routing Linear work for Nancy or other autonomous agents. Covers issue capture, triage, planning gates, agent issue review, execution readiness, and Linear as the source of truth for autonomous work.

Check a package name across npm, PyPI, and crates.io, then scaffold a 0.0.1 placeholder for every available registry into one shared directory. Prints three copy-pasteable publish commands at the end so the user can run all three publishes themselves in their own terminal. Use when the user says "name claim", "claim X", "reserve name", or wants to lock a name across all three registries with a single command. Takes a name as an argument. Crates.io publishes are permanent (yank only, no unpublish).

Claim an npm package name by checking availability and publishing a placeholder. Use when the user says "claim", "npm claim", "reserve package name", or wants to check if an npm package name is available. Takes a package name as an argument.

Claim a PyPI package name by checking availability and publishing a placeholder. Use when the user says "pypi claim", "reserve pypi name", or wants to check if a PyPI package name is available. Takes a package name as an argument.

List the user's documented workflows in ~/.mdx/workflows/. Use when the user asks "what workflows do I have?", "list my workflows", "show workflows", "/workflows", or otherwise wants to see what reusable orchestration patterns are on disk.

Use when the user invokes /imagegen, asks for a Helioy visual style, wants a banner or image prompt shaped by a named design style, or needs available design styles listed before choosing one.

Use when planning, reviewing, or routing Linear work for Nancy or other autonomous agents. Applies to issue hierarchy, planning gates, agent issue review, execution readiness, and Linear as the source of truth for autonomous work.

Create pull requests with conventional commit titles for squash merge. Use when creating PRs, preparing branches for merge, or when the user says "create a PR", "open a PR", "prepare for merge", or "push this".

Turn a topic into a published blog post. Runs a structured interview for net-new posts, accepts delegated drafting when the session already carries context (github reviews, cm decisions, research artifacts), resumes in-flight drafts, and promotes already-published posts. Hands prose drafting to my-voice, persists markdown to ~/.mdx/blog/ before review, and orchestrates the Substack paste flow. Use when the user wants to write a post, draft an essay, resume a draft, promote a published post, or convert just-completed research into a teardown or deep-dive. Owns blog state in cm (blog-draft-open, blog-published) and triggers the social-loop cascade on publish.

Smart router for content work. Reads cm state, scans session-fresh research artifacts, summarizes what is open across blogs, social, and DMs, suggests one to three next actions with reasoning, and dispatches to blog-architect or social-loop. Use when the user types /content, asks "what should I post next", "what's open", "what's in flight", "what should I work on", "I just finished a repo review", or any variant of "help me decide what to write today". This skill never drafts. It only orchestrates.

Storage policy for the cm context store. Use when deciding whether to persist a fact, decision, or lesson via cx_store/cx_deposit. The cm MCP server documents the tools themselves; this skill governs what belongs in the store and what does not.

Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

Create new skills for the helioy-tools plugin. Use when the user asks to build, create, or add a new skill inside helioy-plugins, or when you need to scaffold a skill as part of a Helioy task. Enforces Helioy plugin conventions: correct location, frontmatter, naming, MCP inheritance, and Linear issue structure. For generic (non-Helioy) skill scaffolding, use the standard `skill-creator` instead.

Enforces parent/sub-issue structure for all Linear work planning. INVOKE THIS SKILL whenever you are about to create Linear issues, plan features, break down tasks, scope work for Nancy, or organize any unit of work that will be executed autonomously. This skill fires BEFORE the first save_issue call. If you find yourself reaching for save_issue without having invoked this skill first, stop and invoke it. Also use when the user says 'create an issue', 'plan this', 'break this down', 'send this to Nancy', or discusses any feature/bug that needs tracking.

Write content in Stuart's voice for social media, GitHub, essays, or any public-facing writing. Use when asked to draft posts, write tweets, compose replies, create threads, write copy, or generate any content that should sound like Stuart — not like an AI. Also use when the user says "my voice", "draft a post", "write a tweet", "compose a reply", or "help me write".

Preserve the prior version of a doc to its sibling .archive/ directory before editing. Use when the user is about to make material edits to a doc worth versioning, or asks to snapshot, version, archive, preserve, shelve, or save the current state before changes.

Dispatch social engagement across 11 post types on X and LinkedIn for Stuart's @KnowMoreContext (engine) and @HelioyMatters (brand) handles. Covers original posts (blog-promo, build-log, product-release), reactive posts (proactive-reply, comment-reply, quote-tweet, retweet), threads, and DMs (cold, followup, reply). Hands prose drafting to my-voice; this skill owns taxonomy, context gathering, state writes, and the paste-flow publish for v1. Use when the user invokes /content and picks a social action, when blog-architect cascades a blog-promo, or when the user says "tweet this", "reply to that", "DM them", "thread about X", or names any of the 11 type slugs directly.

MCP-first code navigation for this codebase. Use before any symbol lookup, file search, dependency trace, impact analysis, or codebase evaluation — replaces grep/glob/read with O(1) fmm_* tool calls. Trigger when: starting any task involving unfamiliar code, navigating code structure, finding where a symbol is defined, checking what imports a file, tracing blast radius before a rename, mapping test coverage, or evaluating/auditing a codebase.

Preserve cognitive state before the worker is terminated. Writes only information that cannot be recovered from git. The next iteration of this worker reads the handover to pick up where you left off.

Print the current session ID. Useful for debugging, logging, or any time you need to reference the session context. Use when asked "what's the session ID?", "print the session ID", or "what session am I in?".

Hand over session activity to another agent for future reference. Logs a summary of the session, including key findings and artifacts produced, to a markdown file and persists it to context-matters.

Log activity for this session

Use for any helioy-bus mail operation: checking your inbox, sending messages to other agents, broadcasting to all agents, or responding to a "you have mail!" nudge. Use at the start of any task to check for directives from peer agents.

MCP-first code navigation for this codebase. Use before any symbol lookup, file search, dependency trace, impact analysis, or codebase evaluation — replaces grep/glob/read with O(1) fmm_* tool calls. Trigger when: starting any task involving unfamiliar code, navigating code structure, finding where a symbol is defined, checking what imports a file, tracing blast radius before a rename, mapping test coverage, or evaluating/auditing a codebase.

Create a task specification (SPEC.md) through interactive requirements elicitation. Use when helping users define what they want to build before autonomous execution begins.