Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

mattdweigand-sketch

@mattdweigand-sketch source repo

6 published skills

  1. ▌
    Swarm · mattdweigand-sketch
    Invocation-only workflow. Use only when the user includes literal `swarm` as an instruction to apply this workflow. Do not trigger for broader agent, harness, judge, checker, orchestration, or multi-agent requests unless the literal `swarm` invocation is present.
    0
    installs
  2. ▌
    60 30 10 · mattdweigand-sketch bundle
    Evaluate how a project allocates judgment across owned data, deterministic code, and prompt-model work. Invocation-only: use this skill only when the user explicitly invokes `$60-30-10` or `/60-30-10`, or explicitly asks to use or run the 60-30-10 skill. Do not infer its use from related audit, architecture, prompt, agent, harness, workflow, or judgment-allocation requests.
    0
    installs
  3. ▌
    Skill Tune · mattdweigand-sketch bundle
    Audit or refactor an existing skill or prompt artifact for prompt technical debt. Use when the user invokes $skill-tune or /skill-tune, or explicitly asks to audit, tune, or refactor a SKILL.md, skill directory or archive, AGENTS.md, CLAUDE.md, system prompt, command wrapper, or tool instruction for prompt debt, over-steering, context bloat, stale model-specific steering, duplicated canonical rules, misplaced executable checks, or missing authority boundaries. Use skill-creator for net-new skill scaffolding. Do not use for rubric design or general pull-request review.
    0
    installs
  4. ▌
    Icm Architect · mattdweigand-sketch bundle
    Build or audit a folder, repo, or vault against ICM (Interpretable Context Methodology): folder structure as agent architecture. Use for explicit ICM requests, walk tests, agent workspace design, and mapping a repo into objects, processes, and change impact. Not for generic file organization or folder cleanup.
    0
    installs
  5. ▌
    Weekly Signal Diff AI · mattdweigand-sketch bundle
    Use when the user wants a weekly structural diff on the AI ecosystem: frontier labs, open models, dev tooling and agents, cloud AI platforms, data and model infrastructure, enterprise AI buyers, creative media, robotics and embodied AI, and AI regulation. Starts from 10 suggested categories and 30 suggested entities. Best for prompts like "run my weekly AI signal diff", "what changed in AI this week", "what moved in frontier labs", "track the AI market", or "turn this week's AI news into structural shifts". Optional live search upgrade: if OpenRouter access is available, prefer the Perplexity Sonar family for fresh web-grounded retrieval with citations.
    0
    installs
  6. ▌
    Write Discoverable Code · mattdweigand-sketch bundle
    Write and review source code with distinctive names and precise public APIs so coding agents can find it efficiently across text search, repo maps, and semantic retrieval. Do NOT load for Markdown corpora, wikis, or docs sites that navigate via explicit indexes and wikilinks. Do NOT load for prompt/skill authoring — use `create-skill` or `skill-tune`. Use when writing, reviewing, or refactoring code in a repository; picking names for functions/files/types/directories; tightening type annotations; or drafting an AGENTS.md/CLAUDE.md for a code repo. Triggers: 'write this code', 'review this code', 'refactor this file', 'name this function/file/type', 'is this agent-navigable', 'grep-friendly', 'discoverable code'.
    0
    installs