Comments
Code comments and annotations
employee-1
by DrewDey
Project-local Employee 1 operating skill for PathForge in /Users/ddtuchfarber/Desktop/Business Ideas/Prompt Project Platform. Use when Codex is working in this repo throughout the day, receiving product notes, bug reports, screenshots, voice-dictated brainstorming, implementation requests, local verification tasks, public project page repairs, source-run approvals, page-publishing consistency checks, production-readiness checks, or night-end commit preparation. Work toward production-ready outcomes, act as the user's practical engineering worker, verify changes, protect user intent, avoid over-interpreting rough voice notes as broad rewrite mandates, and commit, push, or deploy when the current user direction calls for it. Keep production data changes gated on explicit approval.
pr-review-loop
by rculbertson
Automates the AI reviewer response loop for GitHub PRs. Polls the PR for comments from an AI reviewer (Gemini, Copilot, etc.), addresses or disputes each comment, pushes changes, requests re-review, and repeats until the PR is approved. Optionally auto-merges when all comments are resolved. Invoked explicitly via "/pr-review-loop".
docx-official
by mit-network
"A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks."
review-deep
by gopherguides
"Deep-review a PR or branch with issue and repo context, then fix and commit actionable findings; PR-backed runs push new review commits by default. Use for 'review my changes', 'check this PR', or post-implementation quality/spec review requests. SKIP existing human/bot review comments that need replies/thread resolution; use address-review."
gr-ph-launch
by Gingiris-1031
Product Hunt 发布剧本。从 30x 日冠经验提炼的完整 GTM 流程：T-14 预热 → T-0 发布日 → T+7 post-launch。 覆盖 hunter 选择、maker comment、community seeding、评论节奏、防踩雷。当用户说"我要发 PH"、 "Product Hunt 准备"、"找 hunter"、"写 maker comment"时调用。
documenting-code-comments
by rileyhilliard
Standards for self-documenting code and minimal comments. Use when auditing inline documentation or deciding when comments add value vs clutter.
grafana-skill
by julianobarbosa
Comprehensive skill for interacting with Grafana's HTTP API to manage dashboards, data sources, folders, alerting, annotations, users, teams, and organizations. Use when Claude needs to (1) Create, read, update, or delete Grafana dashboards, (2) Manage data sources and connections, (3) Configure alerting rules, contact points, and notification policies, (4) Work with folders and permissions, (5) Manage users, teams, and service accounts, (6) Create or query annotations, (7) Execute queries against data sources, or any other Grafana automation task via API.
bio-gene-calling
by fmschulz
Call genes and annotate basic features for prokaryotes, viruses, and eukaryotes.
browser
by inkeep
"Browser automation with Playwright — navigate pages, fill forms, take screenshots, test responsive design, validate UX, test login flows, check links, inspect network requests, inject JavaScript, monitor console errors, capture network traffic, record video, inspect browser state, run accessibility audits, measure performance, simulate network conditions, discover page structure, persist auth sessions, create annotated GIFs, handle dialogs, dismiss overlays, capture traces, generate PDFs, and download files. Headless by default for CI/Docker. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform browser-based testing. Triggers: playwright, browser test, browser automation, web test, screenshot, responsive test, test the page, automate browser, headless browser, UI test, console errors, console monitoring, network inspection, network capture, accessibility audit, a11y test, performance metrics, web vitals, video recording, browser state, localStorage, network simulation, offline testing, page structure, accessibility tree, authenticated testing, auth state, session reuse, annotated gif, dialog handling, overlay dismissal, cookie banner, tracing, trace viewer, pdf generation, file download, time manipulation, websocket interception."
creating-test-structure
by klamping
Use when creating or extending WebdriverIO test structure from a markdown test plan by adding describe/it/hooks and pseudo-code comments without implementing WDIO commands yet.
screenshot-ui-analyzer
by ignaciosua
Takes a screenshot, analyzes it using AI (Gemini Vision) to detect UI elements with bounding boxes, names, and descriptions, saves to JSON, and generates an annotated image. Use when you need to identify and label screen elements with advanced AI. Key commands: screenshot, analyze, annotate.