exiao

Use when generating hooks, headlines, titles, and scroll-stopping openers for content. Also use when analyzing viral posts, Reels, TikToks, YouTube Shorts, or successful social examples to extract reusable hook patterns and improve hook guidance.

Verify a code change actually works by building/running the app and observing it at its real surface (CLI, API, UI, library, agent), capturing runtime evidence rather than trusting tests. Make sure to use this skill whenever the user has changed code and…

Test an interactive lesson/course (or any "instructions to an AI" skill) by self-play. An agent plays BOTH the instructor following the lesson script AND a calibrated student persona, producing full turn-by-turn transcripts of every lesson, then publishes the…

Daily memory garbage collection for MEMORY.md / USER.md. Apply decay rules, drain .pending.md, consolidate near-duplicates, maintain canonical theme tags, prune old episode and session files. Invoke when asked to "run memory GC", "clean up memory", "apply…

Monitor a PR until it's ready to merge. Watches CI, reads reviews, checks scope, fixes blocking issues, opens follow-up PRs for low-priority comments, and repeats. Use when: babysit this PR, watch this PR, monitor PR, fix and watch PR, keep this PR green.

Review code changes by analyzing git diffs, leaving inline comments on PRs, and performing thorough pre-push review. Works with the gh CLI or falls back to git + GitHub REST API via curl. Use when: review this PR, review a pull request, look at this PR, code…

Run iterative self-referential development loops using the Ralph Wiggum technique. Use when tasks need repeated iteration, TDD cycles, greenfield builds, or autonomous refinement until tests pass or completion criteria are met. Triggers on ralph loop, ralph…

Roleplay the most difficult, tech-resistant user for your product. Browse the app as that persona, find every UX pain point, then filter complaints through a pragmatism layer to separate real problems from noise. Creates actionable tickets from genuine issues…

Improve design mockups from critique (design-review, user studies, a multi-perspective council, a UI lint pass, or raw notes): triage keep/change/kill, produce a new version with a per-change rationale trail so the next test can measure improvement. If no…

Run a product design review on a feature or site. Answers 13 design questions, runs Nielsen Norman heuristic evaluation, builds before/after visual fixes, and deploys a shareable report to Surge. Use when asked to review a design, audit UX, do a design…

When the user wants to plan a product launch, feature announcement, or release strategy. Use when someone mentions 'launch,' 'Product Hunt,' 'feature release,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' or 'launch checklist.'

When the user wants help with pricing decisions, packaging, monetization strategy, or regional/international pricing. Use when someone mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'value metric,' 'willingness to pay,' 'how much should I…

Create a product pitch/proposal to improve a step in the growth funnel (acquisition to activation to engagement to retention to monetization to referral). Use when asked to write a pitch, proposal, or business case for a feature, growth experiment, or UX…

Verify a code change actually works by building/running the app and observing it at its real surface (CLI, API, UI, library, agent), capturing runtime evidence rather than trusting tests. Make sure to use this skill whenever the user has changed code and…

Generate dark-themed SVG diagrams of software systems and cloud infrastructure as standalone HTML files with inline SVG graphics. Semantic component colors (cyan=frontend, emerald=backend, violet=database, amber=cloud/AWS, rose=security, orange=message bus),…

Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or review the quality of a web application. Produces a structured report with full reproduction evidence (screenshots, repro steps) so findings can be handed directly to responsible teams.

Create a skill or modify an existing one. Write a failing test before touching SKILL.md. Also runs evals and benchmarks skill performance.

Optimize a skill by running it, scoring against evals, and keeping only validated gains. Use for optimize this skill, make this skill better, run autoresearch.

Score an AGENTS.md, CLAUDE.md, or .cursorrules for how Hermes loads it. Use for audit my AGENTS.md or why isn't it being followed. For SKILL.md use skill-audit.

Score a skill against best practices and output a scorecard with fixes. Use for audit this skill, review this skill, skill health check, check for drift.

Test a lesson or course skill by self-play, one agent as instructor and student. Use for run lesson transcripts or QA the course. For web apps use dogfood.

Find and remove duplicate or unused skills, and publish the library to a public repo. Use for clean up my skills, too many skills, skill budget report.

Score a SOUL.md, agent persona, or system prompt against how Hermes loads it. Use when someone shares a persona file to review or grade. Not for skills.

Run a diagnose-prescribe-rewrite loop on a finished first draft: articles, posts, newsletters, essays. Checks in with the author after every rewrite before continuing. Use when a draft is written and needs editing to publishable, not when you still need a…

Use when judging content quality OR editing/improving existing copy: shareability, readability, voice, cuttability, angle, copy sweeps.

Reorganize a document into new sections while preserving the author's exact words: SOUL.md, constitutions, READMEs, specs, plans, style guides. Use when the user says 'put my words into new sections', 'use the exact same words', 'reorganize this', 'what if…

Use when writing headlines, titles, blurbs, subject lines, event/webinar descriptions, landing page headers, thread openers, or post first lines. Written copy only.

Use for docs, runbooks, error messages, plans, PRs.

Write or edit content in Eric's voice: articles, blog posts, tweets, social posts, marketing copy, newsletters, landing pages, web copy. Enforces kill phrases. Use for drafting AND revision.

Foundation skill for all Bloom investing skills. Load this first before running any other Bloom skill. Handles CLI setup, authentication checks, output conventions, and documents every available bloom command with its flags. Triggers: "set up bloom", "bloom…

Daily market update. Covers sentiment, major indexes, biggest movers, and optionally a watchlist. 2-minute read. Run it in the morning to know what's happening. Triggers: "what happened today", "market update", "morning briefing", "how's the market", "what's…

Evaluate a specific trade idea. Takes a natural language thesis ("I want to buy NVDA before earnings"), runs data against it, and returns a verdict with bull/bear case, key numbers, and position sizing. Triggers: "should I buy AAPL", "is this trade dumb",…

Find investment opportunities. Combines AI Arena trades (what Bloom's AI models are doing with real money), today's movers, screener picks, and curated collections into one actionable summary. Triggers: "find me something to buy", "what should I invest in",…

Full stock analysis for any publicly traded company. Covers financials, valuation, growth, analyst consensus, catalysts, risks, technicals, and recent news. Triggers: "tell me about AAPL", "analyze NVDA", "research Tesla", "what do you think of MSFT", "is…

Portfolio review and grading. Takes a user's holdings (tickers + weights or dollar amounts), runs analysis on the whole portfolio, and returns a letter grade A-F with specific problems and actionable suggestions. Triggers: "review my portfolio", "how's my…

Set up a persistent memory system for any AI coding agent (Cursor, Claude Code, OpenCode, OpenClaw, etc.). This file is the shared spec (entry format, categories, episodes, recall, GC); per-platform install steps live in references/<platform>.md. Use when…

Daily memory garbage collection for MEMORY.md / USER.md. Apply decay rules, drain .pending.md, consolidate near-duplicates, maintain canonical theme tags, prune old episode and session files. Invoke when asked to "run memory GC", "clean up memory", "apply…

Retrieve memory from past sessions. Use whenever the user asks about past conversations, prior decisions, "what did we do about X", "when did we last...", "do you remember...", or anything where the answer might live outside the current session's context.

Interactive Claude Code course for Product Managers. Use when the user says "teach me", "start lesson", "course", "next lesson", "learn Claude Code", wants to learn how to use Claude Code, asks about prototyping with AI, or references any lesson number…