conorluddy/marketplace

12 agent skills in one repository, published by conorluddy. One command installs the lot; each skill also has its own page below.

1. and-then

   Ambiguity-first planning — identify and resolve unknowns before committing to a plan. Use when the user wants to plan, scope, or think through work before building.

2. app-review-guidelines

   Audit an iOS app against Apple's App Store Review Guidelines, triage a rejection message, or prepare for submission. Scans Info.plist, entitlements, PrivacyInfo.xcprivacy, StoreKit and Swift/SwiftUI source for likely review risks (in-app purchase, subscriptions, Sign in with Apple, account deletion, UGC moderation, privacy and ATT, Kids Category, health data, minimum functionality, background modes, private APIs) and writes an advisory REVIEW-RISK.md citing guideline numbers. Also maps a pasted App Review rejection to the guideline, likely cause, fix and a drafted Resolution Center reply. Use this skill whenever the user mentions App Review, App Store review, review guidelines, rejection, rejected build, Guideline 2.1 / 3.1.1 / 4.8 / 5.1.1 (or any guideline number), Resolution Center, submission readiness, "will Apple reject this", "can I do X on the App Store", TestFlight external review, or is about to submit an iOS app — even if they never say "guidelines".

3. claude-md-kit

   Compose or extend a project's CLAUDE.md from a library of stack-agnostic, composable prompt-segment modules (naming, error handling, testing, agentic patterns, a condensed spec-speak, etc.) stored as standalone files under references/. Use this skill whenever the user wants to bootstrap a new CLAUDE.md, add a specific convention module to an existing one, or audit a CLAUDE.md against the standard module set. Also use when the user says "compose a CLAUDE.md", "give me a starter CLAUDE.md", "add the [topic] module", or "what conventions are we missing".

4. code-reviewReview & testing

   Review code against Conor's style guide — naming, progressive disclosure, function design, error handling, agentic patterns, and token economics. Use this skill whenever the user asks for a code review, says things like "review this", "check my code", "look over this PR", "roast this", asks for feedback on a diff/branch/file, or after finishing an implementation and wants a pass before commit. Also trigger proactively after substantial code changes where a self-review would catch issues. Produces a structured findings report grouped by severity (blocker / major / minor / nit) with file:line references and concrete suggested fixes — not generic platitudes.

5. github-labels

   Set up structured GitHub issue labels for any repository. Installs curated label groups (priority, clarity, risk, blast radius, size, parallelism, sequencing, type, and special labels) using the GitHub CLI. Use this skill when a user mentions "set up labels", "github labels", "label taxonomy", or wants to organise their issue tracker.

6. ios-asoResearch

   Generate a paste-ready English (U.S.) App Store Optimization metadata file (ASO.md) for an iOS app by scanning its Swift/SwiftUI codebase. Produces App Name (30), Subtitle (30), Keywords (100), Promotional Text, Description, category recommendations, screenshot caption suggestions, IAP names, and a research-notes appendix grounded in the codebase. Use this skill whenever the user mentions ASO, App Store Optimization, App Store metadata, app store listing, app name, app subtitle, keywords field, App Store Connect copy, App Store keywords, app store description, promotional text, custom product pages, or wants help writing/auditing/improving the metadata for an iOS App Store submission — even if they don't say "ASO" explicitly. Also trigger when the user asks to prepare an app for submission, audit a listing for rejection risk, pick a category, or extract keywords from a codebase.

7. liquid-glassDesign

   Implement iOS 26 Liquid Glass effects in SwiftUI and UIKit. Use this skill whenever the user mentions liquid glass, glass effects, glassEffect, iOS 26 UI design, translucent navigation bars, glass morphing, GlassEffectContainer, or wants to add the new Apple glass material to their app. Also use when migrating an existing app's UI to iOS 26 style, or when the user asks about glass button styles, tab bar minimization, or the new sheet presentations.

8. openhue

   Control Philips Hue lights from the CLI. Use this skill whenever the user wants to control smart lights, adjust brightness or color, manage lighting scenes, or automate lighting. Examples include turning lights on/off, setting brightness levels, changing colors, controlling multiple lights/rooms at once, discovering light bridges, or configuring Hue bridge connections. Works with individual lights, entire rooms, or batch operations across multiple devices.

9. sonos-cli

   Control Sonos speakers from the CLI using the `sonos` command. Translates natural language requests into sonos CLI commands for playback, volume, grouping, queue management, and music search. Use this skill whenever the user mentions Sonos, asks to play music on a speaker, control volume on a room, group or ungroup speakers, manage their Sonos queue, or references speaker names like "Kitchen" or "TV". Trigger phrases: "play X on Sonos", "turn up the kitchen speaker", "pause Sonos", "what's playing on Sonos", "group my speakers", "play my Sonos favorites", "Sonos volume", "skip track on Sonos", "add to Sonos queue".

10. spec-speakBusiness & ops

    Convert any subject matter — rough feature ideas, brain-dumps, meeting notes, loose PRDs, existing docs — into a rigorous, testable spec written to industry requirements standards (EARS templates, RFC 2119 keywords, INCOSE/ISO 29148 rules, Gherkin acceptance criteria). Use this skill whenever the user wants to write, rewrite, tighten, or formalize a PRD, technical spec, requirements document, or acceptance criteria, or says things like "spec this out", "formalize this", "turn these notes into a spec", "write requirements for", "make this testable", "tighten this doc", or shares loose product thinking that needs to become an unambiguous document. Also use it to audit an existing spec for ambiguity, weak words, and untestable requirements.

11. swift-accessibility-agentDeploy & operate

    Audit, fix, and initialise SwiftUI accessibility so an app is navigable by VoiceOver users, XCUITest, and AI agents. Use this skill whenever a user mentions an accessibility audit, accessibility modifiers, identifiers/labels/hints/values/traits, VoiceOver, Dynamic Type, Reduce Motion, colour contrast, making an iOS app navigable by agents, CoordinateTracker, trackElement, or wants to improve SwiftUI accessibility coverage. Also trigger on "audit accessibility", "add accessibility", "make navigable", "init accessibility", "VoiceOver can't reach X", or a ticket whose acceptance criteria list VoiceOver or Dynamic Type. Three modes: init (scaffold CoordinateTracker infrastructure), audit (report gaps), fix (add missing modifiers and repair the traps that silently break VoiceOver).

12. team-workBuilding agents

    Decompose the current session's jobs-to-be-done into a parallelizable task plan for an agent team. Assigns each task a model tier (haiku / sonnet / opus) and a specialist subagent when one fits. Organises work into dependency waves with no shared-file edits inside a wave to avoid merge conflicts. Use this skill whenever the user says "team this up", "use a team", "use agent teams", "delegate this", "split this work", "parallelize this", "fan this out", "divide and conquer", or otherwise asks to coordinate multiple agents on work already discussed in the session. Also trigger when the user says a task is big and wants help farming it out, or when they explicitly invoke /team-work.