srobinson
- 40 skills
- 0 followers
- 2 hours ago last updated
- ▌ Principle Fix Root Causes · srobinsonApply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
- ▌ Technical Writing · srobinsonLayered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
- ▌ Mail 2 · srobinsonUse 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.
- ▌ Principle Never Block On The Human · srobinsonApply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.
- ▌ Principle Make Operations Idempotent · srobinsonApply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.
- ▌ Mail · srobinson bundleUse 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. Also use when the user says things like "reply to that agent", "tell the reviewer 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.
- ▌ Fmm · srobinsonMCP-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.
- ▌ How · srobinson bundleUse for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.
- ▌ Why · srobinson bundleUse for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
- ▌ Warroom · srobinson bundleOrchestrate 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.
- ▌ Arena · srobinsonSpawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
- ▌ Teach · srobinsonExplain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
- ▌ Content · srobinsonRoute social publishing and engagement work. Reads current cm state, summarizes pending posts and DMs, suggests one to three next actions, and dispatches the selected action to social-loop. Use for /content, "what should I post next", "what is open", or "help me decide what to write today".
- ▌ Reflect · srobinson bundleSpawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.
- ▌ Imagegen · srobinson bundleUse 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.
- ▌ My Voice · srobinsonWrite 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".
- ▌ Snapshot · srobinsonPreserve 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.
- ▌ NPM Claim · srobinson bundleClaim 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.
- ▌ Workflows · srobinsonList 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.
- ▌ Architect · srobinson bundleSketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
- ▌ Name Claim · srobinsonCheck 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).
- ▌ Pypi Claim · srobinson bundleClaim 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.
- ▌ Sketch Lab · srobinson bundleGenerate Sketch Lab architecture diagrams and open them with a share URL. Use when the user asks for a Sketch Lab diagram, sketchlab.app board, 3D floor stack, architecture sketch in Sketch Lab, or GeneratedGraph JSON. Use only for Sketch Lab. Route Mermaid, Excalidraw, and Mission Control diagrams to their own tools.
- ▌ Crate Claim · srobinson bundleClaim 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).
- ▌ Social Loop · srobinsonDispatch 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 content routes 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.
- ▌ Interrogate · srobinson bundleUse for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
- ▌ No Comments · srobinsonSpawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
- ▌ Poteto Mode · srobinson bundlepoteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
- ▌ Code Hygiene · srobinsonImprove 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.
- ▌ Codebase Map · srobinsonGenerate 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.
- ▌ Pull Request · srobinsonCreate 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".
- ▌ Figure It Out · srobinsonDesign an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.
- ▌ Mdx Artifacts · srobinson bundleChoose and verify storage for agent artifacts. Use when work produces a review, research report, architecture or design document, plan, decision record, session trail, handoff, reusable verification file, or delegated report that may matter after the current turn.
- ▌ Context Matters · srobinsonStorage 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.
- ▌ Show Me Your Work · srobinson bundleKeep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
- ▌ Kubernetes Fundamentals · srobinsonKubernetes 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.
- ▌ Create Verification Skill · srobinson bundleGenerate a project-local verification skill that drives your app the way a user does : any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
- ▌ Principle Build The Lever · srobinsonApply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
- ▌ Maintain Verification Skill · srobinsonPeriodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
- ▌ Principle Type System Discipline · srobinsonApply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.