skills

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 wants to know it works, is about to merge/push and wants confidence, says "did this actually work", "verify this works", "prove it works", "confirm the change", "make sure it works", wants runtime evidence, or is re-running tests / importing-and-calling just to check behavior, even if they never say the word "verify". When in doubt after any code change, reach for this. For post-deploy production health checks use verify-deploy; for static correctness/quality review use simplify or code-review.

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 raw transcripts to a single static page. Use when asked to "run lesson transcripts", "test the course end to end", "self-play the lessons", "publish raw test transcripts", "walk a synthetic student through every lesson", or to QA an interactive-instruction skill by actually running it rather than just reviewing findings. Distinct from dogfood and adversarial-ux-test (web-app browser QA) and synthetic-userstudies (findings plus a few cherry-picked transcripts). This one captures the COMPLETE run of every lesson and ships them all raw.

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 memory decay", or from the scheduled cron job.

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 review, review my changes before I push, pre-push review, leave inline comments on a pull request.

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 mode, iterative loop, autonomous loop, /goal.

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 only. Use when: adversarial UX test, stress-test the UX, find UX pain points, roleplay a difficult user, hostile user testing.

Post-merge deploy verification. Waits for deploy, benchmarks production, monitors for regressions. Use after merging a PR to confirm the deploy is healthy.

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.

Generate ASCII art and text banners using pyfiglet, cowsay, boxes, toilet, and image-to-ASCII converters. Use when: make ASCII art, ASCII banner, figlet text, cowsay, box around text, convert image to ASCII, ASCII logo, QR code as ASCII, weather ASCII art.

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 review, or analyze a product's user experience.

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context.

Plan-only mode — inspect context and write a markdown plan into `~/.hermes/plans/` when the user wants planning instead of execution. Use when the user says "plan this", "make a plan", "/plan", "don't implement yet", or "investigate and make a plan". If the user asks to plan and then implement, save the plan first, present it for approval, then continue.

Run synthetic user research sessions natively — no backend required. The agent plays an AI-generated persona and simulates a user interview based on the 4 Ps framework (Persona, Problem, Promise, Product). Use when a user wants to run a user research session, interview a synthetic persona, validate product ideas, generate user personas, or simulate customer conversations. Triggers on "user research", "synthetic persona", "simulate a user", "userstudies", "interview a persona", "validate my idea", or "talk to a user".

Eval-driven skill optimizer: runs a skill repeatedly, scores outputs against binary evals, mutates the prompt via structured edits, and keeps only changes that improve a held-out validation score (cross-model optimizer/target, three-way splits, golden cases, checkpoint resume). Use when: optimize/improve this skill, make this skill better, run autoresearch on, self-improve skill, benchmark/eval my skill, run evals on.

Use when building content strategy: hooks, angles, and ideas from what's trending now. Covers organic and paid creative across TikTok, X, YouTube, Meta, LinkedIn.

Generate structured scene-by-scene video scripts with production metadata (visuals, audio, sources, transitions, captions) ready to feed into the video-production pipeline (Sora, Kling, ElevenLabs, InfiniteTalk, Remotion, stock-footage, video-editor). Use when asked to "write a video script", "script for TikTok", "video outline", "plan a video", "storyboard", "scene breakdown", "video concept", "content brief for video", "shooting script", or whenever the video-production pipeline needs a structured script before production begins. Also trigger for "Reels script", "Shorts script", "YouTube script", "video idea with scenes", or any request that implies breaking a video concept into timed scenes with production directions.

Use when creating animation-rich HTML presentations or convert PPT to web.

Reference for the two-tier skill loading system — preloaded vs category-gated skills, how to add/remove preloaded skills, and the external-services category layout.

Orchestrator for the 3-article content pipeline — runs research phase, spawns parallel article sub-agents, creates Typefully drafts. Use when running the full content pipeline (usually via cron at 3am).

Use when generating outlines, article structures, content outlines, blog outlines, planning article sections, structuring posts, breaking down topics into sections, or organizing ideas for long-form content. Also use for 'outline this', 'structure this article', or 'plan the sections'.

Reconcile App Store Connect subscriptions and in-app purchases with RevenueCat products, entitlements, offerings, and packages using the asc CLI and the revenuecat mcporter server. Use when setting up or syncing subscription catalogs across ASC and RevenueCat.

Use the asc CLI for all App Store Connect tasks — releases, TestFlight, builds, metadata, screenshots, signing, subscriptions, IAPs, pricing, analytics, users, notarization, and more. Primary catch-all for any App Store Connect work. For deep workflows, also see specialized asc-* skills.

How to clean up duplicate/untracked skills in the skills repo

Daily Meta ad operations via Marketing API — competitor research via Ad Library, check performance, kill losers, promote winners, generate 6 fresh creatives via Nano Banana Pro + gpt-image-2 + Higgsfield MCP, upload as new ads, and report to Signal. Runs as cron at 2am ET.

Manage Render.com services, deploys, databases, logs, and infrastructure using the official Render CLI (`render`). Use this skill whenever the user asks about Render deployments, service management, viewing Render logs, restarting Render services, running database queries on Render Postgres, triggering deploys, managing environments/projects, or anything related to their Render infrastructure. Also use when the user mentions render.com, Render dashboard actions, or wants to automate Render workflows.

Use when a first draft is complete and all Phase 1 gates are done: topic selected (seo-research), title approved (hooks), outline approved (outline-generator), draft written (writer). Runs autonomous diagnosis-prescribe-rewrite loop before Substack.

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

Use when defining product positioning, choosing strategic angles, crafting value propositions, competitive positioning, product messaging, differentiation strategy, or go-to-market angles. Also use for 'how should I position my app', 'what angle should I use', 'painkiller vs vitamin', or 'market positioning'.

Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.

Download audio/video from YouTube and other sites using yt-dlp. Use when the user asks to download music, songs, albums, podcasts, or video from YouTube or similar platforms. Triggers on 'download song', 'get mp3', 'yt-dlp', 'youtube download', 'rip audio'.

Use when scanning Sentry issues and creating fix PRs. Trigger phrases include "sentry scan", "fix sentry", "scan errors", "what's crashing".

Full pull request lifecycle — create branches, commit changes, open PRs, monitor CI status, auto-fix failures, and merge. Works with gh CLI or falls back to git + GitHub REST API via curl.

Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.

Build a complete brand identity from scratch or refresh an existing one — for solopreneurs, apps, and consumer products. Covers brand purpose, values, personality, voice and tone, visual identity system (colors, typography, logo direction, imagery style), and brand guidelines. Includes a Claude/Anthropic case study showing what world-class brand identity looks like in practice — counter-positioning, palette strategy, naming, and consistency. Use when creating a new brand, rebranding, auditing visual identity, or making brand decisions consistent. Trigger on "create my brand", "brand identity", "brand guidelines", "define my brand voice", "brand personality", "what should my brand look like", "brand strategy", "rebrand", "brand tone", "what makes a strong brand", "brand case study".

Use when create browser-based motion graphics with Framer Motion, GSAP, and Tailwind.

Create and manage consistent AI video characters — define the persona, generate the portrait with Nano Banana, and store the config for reuse across all videos in the series.

Find the funniest moments in a video, cut them as standalone clips, optionally reformat 16:9 → 9:16 (face-pan or split-screen), and burn opus-style word-by-word captions. Use when the user mentions "clipify," "cut clips from this video," "make shorts from this," "find funny moments," "reframe to 9:16," "vertical clips," or pastes a video file path and wants social-ready cuts.

Create product demo videos by automating browser interactions and capturing frames. Use when the user wants to record a demo, walkthrough, product showcase, or interactive video of a web application. Supports Playwright CDP screencast for high-quality capture and FFmpeg for video encoding.

Build, preview, and render videos with Editframe, the HTML/CSS/React video composition tool. Use this whenever the user mentions Editframe, wants code-generated videos, asks to scaffold an Editframe project, build an HTML/CSS video composition, render MP4 locally, use ef-timegroup/ef-video/ef-audio/ef-text components, or automate video generation with Node.js and FFmpeg.