Profile My skills Saved My plugins Edit profile Submit a skill

← all publishers

markusstrasser

@markusstrasser source repo

49 published skills

  1. ▌
    Source Grading · markusstrasser
    NATO Admiralty System for grading source reliability and information credibility. Apply automatically during OSINT, forensic investigations, legal research, entity audits, or fraud analysis — NOT for general software or casual research. Every claim gets a 2-axis grade (A-F for source reliability, 1-6 for information credibility).
    0 installs
  2. ▌
    Competing Hypotheses · markusstrasser
    Analysis of Competing Hypotheses (ACH). Use when investigating any entity, anomaly, root cause, or claim that could have multiple explanations — fraud vs error, bug vs design, correlation vs causation. Dispatches parallel agents with opposing hypotheses, then synthesizes the surviving explanation. Based on Richards Heuer's CIA methodology.
    0 installs
  3. ▌
    Google Workspace · markusstrasser bundle
    Use when: gws CLI — Drive upload, Sheets log, Gmail alert, Calendar. Session logs/artifacts to Workspace. NOT general HTTP.
    0 installs
  4. ▌
    Manim Animations · markusstrasser bundle
    Use when: Manim/3B1B-style math animation, equation visuals, render manim scenes. NOT static figures (/scientific-drawing).
    0 installs
  5. ▌
    Entity Management · markusstrasser
    Use when: entity dossier create/update (company, gene, person, drug, stock). intel→analysis/entities; else docs/entities. NOT literature synthesis (/research).
    0 installs
  6. ▌
    Person Into Scene · markusstrasser
    Use when: photoreal Markus in scene template, 'put me in this photo', dating/lifestyle/cinematic shots, likeness fix. NOT generic image gen (/gpt-image-2).
    0 installs
  7. ▌
    Review Animations · markusstrasser bundle
    Use when: reviewing animation/motion/transition code, 'does this feel right', easing/duration choices, hover/press states, motion polish pass. Motion craft only — NOT general code review (/code-review) or interaction architecture (/interface-thinking).
    0 installs
  8. ▌
    Architect · markusstrasser bundle
    Architectural decision-making workflow using tournament-based proposal generation and ranking. Generates proposals from multiple LLM providers (google, openai, xai) via llmx unified CLI, ranks them via tournament evaluation, optionally refines with feedback loops, and records decisions as ADRs. Use when exploring architectural alternatives, comparing implementation approaches, or making significant design decisions. Requires API keys, Python 3.10+.
    0 installs
  9. ▌
    Interface Thinking · markusstrasser
    Use when: designing/critiquing any interface, tool, UI, feedback loop, or agent-facing representation/cockpit/instrument; 'how should this feel', 'why is this clunky'. Victor/Norman/Engelbart lenses. NOT visual styling or ideation.
    0 installs
  10. ▌
    Scientific Drawing · markusstrasser bundle
    Use when: /scientific-drawing, architecture/ERD/math diagram, plot a function. Typst/CeTZ default; TikZ/D2/Asymptote when needed. NOT paid illustration SVGs (/illustration-gen) or Manim (/manim-animations).
    0 installs
  11. ▌
    Youtube Transcript · markusstrasser
    Use when: YouTube/podcast transcript via yt-dlp for cite or corpus. Transcript-only — NOT video analysis.
    0 installs
  12. ▌
    Debug MCP Servers · markusstrasser bundle
    Debug why MCP servers aren't loading in Claude Code. Use this when user reports MCPs not appearing in /mcp list despite being configured.
    0 installs
  13. ▌
    Life Science Research · markusstrasser bundle
    Use when: biomedical source lookup (ClinVar, gnomAD, Ensembl, PubMed, OpenTargets…). Route APIs before synthesis. NOT general memos (/research) unless life-science topic.
    0 installs
  14. ▌
    Claude API · markusstrasser bundle
    Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
    0 installs
  15. ▌
    Epistemics · markusstrasser
    Bio/medical/scientific evidence hierarchy and anti-hallucination rules. Use when conducting claim-heavy medical research, genomics interpretation, supplement evaluation, pharmacogenomics, or clinical evidence synthesis. NOT for casual health questions, software engineering, or physics. Companion to researcher skill.
    0 installs
  16. ▌
    Illustration Gen · markusstrasser bundle
    Use when: paid Quiver Arrow SVG logo/icon from prompt. NOT precise technical diagrams (/scientific-drawing).
    0 installs
  17. ▌
    Brainstorm · markusstrasser bundle
    Use when: /brainstorm, divergent design space, denial/domain/constraint perturbation. Optional multi-model volume. NOT convergent review (/critique) or decisions (/decide).
    0 installs
  18. ▌
    Llmx Guide · markusstrasser bundle
    Use when: /llmx-guide, writing llmx calls, debugging llmx failures, or choosing model/provider. Python/Bash gotchas — flags, transports, subscription vs API.
    0 installs
  19. ▌
    QA · markusstrasser
    QA methodology for web applications. Fix-first review with atomic commits, regression test generation, and before/after health scoring. Uses browse daemon for persistent browser interaction. Adapted from gstack's QA patterns with epistemic verification.
    0 installs
  20. ▌
    Census Data · markusstrasser
    Use when: ACS/CPS/IPUMS/QWI extracts, county/state aggregates, immigrant/earnings panels. Census API patterns. NOT generic dataset staging (/data-acquisition alone).
    0 installs
  21. ▌
    Code Review · markusstrasser
    Use when: /code-review, review diff/PR/change, scout loop. Composer default scout; validates against code. NOT plan/findings review (/critique).
    0 installs
  22. ▌
    Gpt Image 2 · markusstrasser
    Use when: improving a gpt-image-2 prompt before generation. NOT scene injection (/person-into-scene).
    0 installs
  23. ▌
    Model Guide · markusstrasser bundle
    Use when: choosing frontier model/effort for a task class (Claude Opus 5, GPT-5.6 Sol/Terra/Luna, Kimi K3 open-weight coding opt-in, Grok 4.5 Cursor repo-review opt-in). Fable 5 METERED since 2026-07-07 (off subscription, 2× Opus) — fable lanes are paid opt-ins, and the Agent tool currently can't reach Fable at all (routing bug, see Verified Transport). NOT transport flags (/llmx-guide).
    0 installs
  24. ▌
    Cursor Agent · markusstrasser
    Use when: headless `agent` CLI from shell/CI/scripts, Composer install/auth/dispatch, or exact Cursor Grok 4.5 read-only repo review. NOT in-editor Cursor agent or llmx/claude-cli.
    0 installs
  25. ▌
    Research Ops · markusstrasser bundle
    Use when: 'compile memos', training-data diff, parallel research dispatch, generate/execute lanes. NOT one-shot questions — use /research. Loop conductor: /observe maintain.
    0 installs
  26. ▌
    Agent Browser · markusstrasser bundle
    Headless/scripted browser automation from Bash (Vercel Labs CLI, Rust/CDP). Use for navigating pages, filling forms, clicking, screenshots, scraping JS-rendered pages, testing web apps, Electron apps, or any programmatic web interaction — especially in subagents, scouts, launchd jobs, and autonomous runs where claude-in-chrome MCP is unavailable. NOT for the operator's logged-in Chrome session (use claude-in-chrome) or static fetches (WebFetch/Firecrawl).
    0 installs
  27. ▌
    Verify Before · markusstrasser
    Use when: dry-run before expensive work, 'did it work/crash', live status probe, pre-register prediction before results. Modes: probe, status, preregister. NOT eval design (/eval) or adversarial review (/critique).
    0 installs
  28. ▌
    Writing Style · markusstrasser bundle
    Use when: drafting email/text/outreach/LinkedIn/scheduling AS Markus. Registers + banned vocab. NOT research memos (/research) or AI-prose cleanup only (/de-slop).
    0 installs
  29. ▌
    Trending Scout · markusstrasser bundle
    Use when: vendor/agent landscape scan, 'what's new', trending repos, weekly update check. Filtered vs known memos — NOT deep topic research (/research).
    0 installs
  30. ▌
    Coedit · markusstrasser
    Co-adaptive editor — minimizes cognitive load during iterative writing/editing. Shows semantic diffs, binary/ternary choices, tracks preference capsule. Use when collaboratively writing, editing, or refining text over multiple turns. Triggers on "coedit", "co-edit", "let's edit this together", "help me write".
    0 installs
  31. ▌
    Data Acquisition · markusstrasser
    Use when: downloading/staging external data (Census, IPUMS, NCES, intel download scripts). Probe→stage→register. Then /dataset-register. NOT papers (/research).
    0 installs
  32. ▌
    Dataset Register · markusstrasser
    Use when: after /data-acquisition, formalize staged dataset in topic catalog (provenance, variables, quirks). NOT downloading (/data-acquisition).
    0 installs
  33. ▌
    De Slop · markusstrasser bundle
    Use when: 'de-slop', AI-prose cleanup, pre-publish voice check. Hunts vocabulary/structure tells — NOT full drafting (/writing-style).
    0 installs
  34. ▌
    Execute · markusstrasser bundle
    Execute approved plan with hygiene — phased, verify-before-claim, granular commits, worktree subagents, inline tooling. /critique close at end. After /decide or plan file. NOT exploration (/decide).
    0 installs
  35. ▌
    Observe · markusstrasser bundle
    Use when: /observe, session quality, what to fix next, biggest lever, codebase audit. Modes: sessions supervision drift retro failures blindspot harvest maintain lever audit conventions.
    0 installs
  36. ▌
    Critique · markusstrasser bundle
    Use when: /critique, 'review plan', 'what's wrong', fact-check plans/findings/closeout. Modes: model, verify, close. NOT code diffs (/code-review) — critique owns design/plan layer.
    0 installs
  37. ▌
    Research · markusstrasser bundle
    Use when: /research, 'find papers about', 'what's known about', literature review, science/benchmark memos. INVOKE BEFORE ad-hoc search — routes S2/Exa/axis diversity into a sourced memo. NOT implementation. Loops → /research-ops.
    0 installs
  38. ▌
    Neurokit2 · markusstrasser
    Use when: ECG/PPG/HRV/EDA processing, biosignal pipelines, wearables analysis code. NOT Oura API auth/pull (/oura-ring).
    0 installs
  39. ▌
    Oura Ring · markusstrasser
    Use when: Oura Ring API pull, sleep/HRV/readiness dashboards, wearable→NeuroKit2. NOT generic biosignal code without Oura (/neurokit2).
    0 installs
  40. ▌
    Bio Verify · markusstrasser bundle
    Use when: hardcoded gene coords/ratios/constants need external check (Ensembl, ClinVar, gnomAD). NOT full variant interpretation (/life-science-research).
    0 installs
  41. ▌
    Doe · markusstrasser bundle
    Use when: /doe, designing a NEW experiment/probe/prereg from a hypothesis+budget — generates arms/shams/controls/bands/power/stopping-rule as a fill-in doc. Complements /eval (grades/scaffolds benchmarks) and dispatch_lint (mechanically enforces a prereg exists). NOT for grading an existing design (/eval review) or a code diff (/code-review).
    0 installs
  42. ▌
    Rsi · markusstrasser
    Use when: /rsi close, session-end digest nudge, goal achieved + verify one claim. fm.py evidence or one [obs]. NOT deep retro (/observe retro).
    0 installs
  43. ▌
    Eval · markusstrasser bundle
    Use when: /eval, new benchmark/grader/judge, model bakeoff, auditing eval design. Pre-reg decision rule + power preflight. Modes: design, review. NOT spot-checks (/verify-before) or code diffs (/code-review).
    0 installs
  44. ▌
    Debug · markusstrasser
    Use when: parallel adversarial bug-hunt fan-out or pre-commit audit; scouts write files, orchestrator model triages. NOT a code-review scout (/code-review) or plan critique (/critique).
    0 installs
  45. ▌
    Modal · markusstrasser bundle
    Use when: Modal deploy/run/debug, GPU/resource config, `from modal import`. v1 API gotchas. NOT generic cloud (/bash only).
    0 installs
  46. ▌
    X API · markusstrasser bundle
    Use when: monitoring curated X accounts, cashtags, finance tweet pulls. Paid API ($/post). NOT general search (/research).
    0 installs
  47. ▌
    Corpus · markusstrasser
    Use when: local paper lookup, 'has the corpus seen this DOI/PMID', cached full text, or canonical paper ingest. Local source store — NOT web literature (/research).
    0 installs
  48. ▌
    Decide · markusstrasser bundle
    Architecture/strategy decision arc — ground → diverge → cross-model critique → capture. For hard-to-reverse decisions (schema, breaking refactor, tech choice). NOT trivial (/critique) or ideation (/brainstorm).
    0 installs
  49. ▌
    Analyze · markusstrasser bundle
    Use when: why/root-cause, confounder, regression, ACH, DAG adjustment, weakest-link. Lenses: null, causal, dag, hypotheses, audit, stop. NOT ideation (/brainstorm).
    0 installs