oleg-koval
UserOpinionated agent skill catalog for Codex, Claude, Cursor, Copilot, and launch workflows.
Categories
Indexed Skills (48)
macos-menubar-app
Build a production-quality macOS menubar or notch app in SwiftUI, covering MenuBarExtra setup, sandbox entitlements, keyboard shortcuts, sound effects, accessibility permissions, and /critique-driven polish cycles. Use when starting or extending a macOS agent app that lives in the status bar or Mac notch area.
fill-music-player
Use when a user wants to fill a portable music player (Walkman, iPod, USB drive) with a curated random selection from a music library on a NAS or local directory. Handles format filtering, artist/album diversity balancing, and size targeting.
gallery
Create photo galleries with AI-assisted layout curation. Orchestrates atomic scripts and sub-agents. Use when user wants to create a gallery from photos, mentions "/gallery", or asks about photo layout and sequencing.
music-to-plex
Acquire music and make it playable in Plex/Plexamp: single albums (via mtp-bot), DJ tracklists/crates, and YouTube playlists. Use ONLY when the user explicitly wants to ADD or DOWNLOAD music to Plex (e.g. 'add to Plex', 'get me this album', 'download this playlist', a timestamped DJ tracklist, or a plain 'Artist - Title' list). NOT for podcasts or non-music; for albums already on disk that won't show up, bulk library repair, or Plex scanner/DB problems, hand off to plex-music-ingest.
wikipedia-uk-editor
Draft policy-compliant Ukrainian Wikipedia edits: translate an English article into uk, expand or source an existing uk article, or fix a maintenance backlog item, and return ready-to-paste wikitext plus an edit summary. Use when given a uk.wikipedia.org or en.wikipedia.org URL or article title to edit, translate, source, or improve, or when planning what to contribute to ukwiki next.
branch-cleanup
Prune stale git branches after a merge wave: delete closed/merged remote branches, remove local tracking branches that no longer exist on the remote, and optionally clean up local branches already merged to main. Use after running dependabot-triage, after a sprint wind-down, or when the user says "clean up branches", "prune branches", "delete merged branches", or "tidy up git".
gh-cli
GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.
git-commit
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
ci-fix-loop
Diagnose GitHub Actions CI failures in a loop: fetch the failing check logs, identify the root cause, apply a targeted fix, push, and wait for the next run: repeating until all checks are green or a real blocker needs a human. Use when CI is red after a push, when the user says "fix CI", "make tests pass", "diagnose CI failures", or "drive this to green". Direct analog of qodoloop / coderabbitloop for automated test and lint failures.
coderabbitloop
Iteratively drives a GitHub PR to zero unresolved CodeRabbit (coderabbitai[bot]) findings. Reads each inline comment's own "Prompt for AI Agents" block (CodeRabbit's ready-made fix spec per issue), applies the fix, replies to the thread explaining what was done, resolves it, pushes, and re-triggers CodeRabbit. Repeats until clean or a real blocker needs a human. Use when the user wants a PR fully addressed against CodeRabbit's review, or says "run coderabbitloop" / "satisfy CodeRabbit" / "resolve CodeRabbit comments".
codexloop
Iteratively satisfy OpenAI Codex's code review on a GitHub PR, but treat every Codex comment SKEPTICALLY: verify each finding against the real code first, fix ONLY the genuinely-correct ones, and rebut + resolve false positives WITHOUT changing correct code. Repeat until no unresolved Codex comments remain. Use when the user says "satisfy codex", "clear the codex review", "fix codex comments", "codex loop", or wants to iterate on Codex PR review feedback.
dependabot-triage
Triage all open Dependabot and Renovate PRs in bulk: classify each by risk tier (patch / minor / major / security), auto-approve and merge safe patch-only bumps, flag breaking major upgrades with a summary of what changed, and post a digest of what was done. Use when dependency PRs are piling up, when the user says "deal with Dependabot", "triage dependency updates", or "merge the safe ones", or at the start of a maintenance window.
geminiloop
Iteratively satisfy Gemini Code Assist's review on a GitHub PR, but treat every Gemini comment SKEPTICALLY (Gemini Code Assist is materially more error-prone than Greptile): verify each finding against the real code first, fix ONLY the genuinely-correct ones, and rebut + resolve false positives WITHOUT changing correct code. Repeat until no unresolved Gemini comments remain. Use when the user wants to clear a PR's Gemini Code Assist review.
lekker-review
FAANG-quality PR code review, adaptable to any team. Checks out the branch in an isolated worktree, gathers context from your issue tracker, chat, docs, CI checks, and (optionally) production monitoring, runs 5 parallel specialized review agents (quality/implementation/simplification/conventions/test-quality), verifies every verdict-affecting finding against the diff, then outputs a single unified markdown review: file + risk + bad code + why it's wrong + fix, ready to paste directly into GitHub. Saves every review to ~/code-reviews/*.md. Covers business logic, scalability, complexity, data integrity, security, integration contracts, error handling, and migration safety. Critical findings come with PROOF: a prover agent writes a failing test in the worktree demonstrating each bug, and fix mode later re-runs it to show the fix flips it green. Every review also publishes a private living artifact page whose URL stays stable across re-reviews, so the author watches findings close commit by commit. With --fix (or
pr-description-writer
Draft and post a GitHub PR title and body from git diff and commit history. Use when opening a new PR, when the user asks to "write a PR description", "draft a PR", "open a PR for this branch", or after running the git-commit skill and pushing the branch. Chains naturally after git-commit and before qodoloop / coderabbitloop.
pr-finalize-complete
Comprehensive PR finalization workflow for PRs that may already be partially or fully addressed. Checks the current state of all review comments (CodeRabbit, Qodo, Greptile, human), identifies which issues are already resolved vs. still open, verifies the test suite passes, runs linting, and prepares a clean push. Handles stale bot comments on moved/renamed files, direct unit test gaps, and branch conflict resolution. Use when a PR has been worked on and you need to confirm it is truly ready to merge, or when review tools show findings that may already be fixed.
pr-finalize
Drives a single GitHub PR from "open with loose ends" to genuinely ready-to-merge: rebases off the base branch and resolves conflicts, sweeps every review bot (Qodo, CodeRabbit, Greptile) plus human comments to zero unaddressed findings, verifies that unit AND browser/E2E coverage was actually added for the change, runs the repo's real lint/format/test gates before pushing, and reports what still needs a human. Use when the user gives a PR URL or number and says "finalize this PR", "fix all outstanding comments", "address the review feedback and push", "get this PR merge-ready", or asks to clear what Qodo/CodeRabbit/Greptile could still comment on.
pr-to-green
Orchestrate a GitHub PR from first push to merge-ready in a single pass: run ci-fix-loop until all checks are green, detect active AI review bots (Qodo, CodeRabbit), run their fix loops in sequence until zero unresolved threads remain, then confirm the PR is merge-ready. Use when the user says "drive this PR to green", "make this merge-ready", "ship this branch", or wants CI and review comments handled end to end without babysitting each loop separately.
qodoloop
Iteratively drives a GitHub PR to zero unresolved Qodo (qodo-code-review[bot]) findings. Reads each finding's own "Agent Prompt" (Qodo hands you a ready-made fix spec per issue), applies the fix, replies to the thread explaining what was done, resolves it, pushes, and waits for Qodo's next pass. Repeats until clean or a real blocker needs a human. Use when the user wants a PR fully addressed against Qodo's review, or says "run qodoloop" / "satisfy Qodo" / "resolve Qodo comments".
morning-routine
Run the complete start-of-day setup in one pass: roll over unfinished Obsidian tasks to today's daily note, sync open GitHub PRs that need your attention, and sweep Dependabot/Renovate PRs to clear safe patch bumps. Use when the user says "start my day", "morning routine", "set up my day", or when a scheduled morning job fires.
obsidian-pr-sync
Fetch open GitHub PRs where the user is an assignee or review-requested reviewer, then write or refresh a "## PRs to review" section in today's Obsidian daily note. Use this skill whenever the user asks to sync PRs to Obsidian, update their daily note with GitHub reviews, check what PRs need attention, or run a morning PR sync routine. Also suitable for scheduled/automated runs: fully idempotent (re-running replaces the section, never appends).
obsidian-task-rollover
Migrate unfinished tasks from a daily Obsidian note to the next workday's note, bullet-journal style. Marks migrated tasks in the source note with [>] (the BJ migration symbol) and copies them to the target note under "## Carried over". Use this skill whenever the user says "roll over today's tasks", "migrate unfinished tasks to tomorrow", "end of day task sync", "move open tasks to next workday", or when a scheduled end-of-day / start-of-day routine fires. Fully idempotent: safe to re-run; already-migrated tasks ([>]) are not touched again.
mvp-oneshot
Use when a user has a rough product idea and wants to go from idea to a shippable one-week MVP in a single pass. Turns the idea into a scoped, testable MVP build prompt, ruthlessly trims scope, produces an execution plan, then builds and self-reviews the vertical slice. Activates on "build an MVP for", "I have an idea for", "turn this idea into an MVP/plan", "scope this down", or "oneshot this".
product-builder
Use when a user asks to build a full-stack web application, SaaS product, dashboard, or any complete working app from a description. Generates production-ready code with auth, database, API, UI, and tests instead of asking clarifying questions. Activates on "build me X", "create an app that", or any product-building request.
starter-rules
Load and enforce the hard rules every oleg-koval/* starter must obey. Use when starting or auditing work in saas-init, ts-npm-starter, go-starter, py-starter, or any future oleg-koval template repo. Covers functional style, 300-line file cap, E2E > unit tests, pre-commit hooks, no-comment policy, KISS/DRY/SOLID, and Vertical Slice as default architecture for SaaS/app starters.
viral-launch
Set up a project repository and launch plan for shareable marketing, public launch readiness, and growth loops without pretending virality is guaranteed.
crash-course
Expert tutor that gets you from zero to working knowledge on any TOPIC fast, grounded in real sources rather than generic filler. Use this whenever the user wants to LEARN, understand, ramp up on, or get up to speed on something and has limited time: a new codebase or project they have been assigned, an unfamiliar technology or framework, a domain concept, an API, a paper, a business area. Triggers on phrases like "help me learn X", "I have N hours to understand X", "teach me X", "get me up to speed on X", "crash course on X", "quiz me on X", "make me a cheat sheet for X", "explain X like I am 5", "I got assigned X and have no context". Runs a timed 4-hour sprint by default, or a single mode on request (cheat sheet, learning ladder, quiz-me, Feynman loop, resource curation). Prefer this over answering a learning request directly, because the value is the structured, interactive, source-grounded teaching loop, not a one-shot dump.
review-past-performance
Self-improvement loop for coding sessions. Pulls the last 24h of ICM memories, git history, and available transcripts; detects patterns like repeated mistakes, slow workflows, untested changes, or missing skills; then proposes 1-3 concrete improvements (new skills, prompt tweaks, eval criteria). Nothing is written until you approve. Use when asked to "review my performance", "self-improve", "what am I repeating", "review past performance", or "what should I fix in my workflow".
self-critique
Adversarially critique your own last substantial answer before the user has to. Spawn a critic agent that verifies every claim against live sources, checks similar and related issues, finds patterns, and addresses comments directly to you. Loop (revise, re-score) until satisfied, then report where you were wrong, iterations-to-satisfy, the numeric improvement, and a final score. Use when the user asks you to criticize, challenge, stress-test, or red-team your own answer, or accepts a "critical-thinking review" offer.
wrap-up
Verify that a completed implementation matches its original objective, all applicable checks are green, and task-owned temporary files, worktrees, and local branches are safely tidied.
changelog-generator
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
open-source-publisher
Prepare an open-source repository for polished public publishing. Use when a user asks to publish, open-source, launch, polish, package, brand, or make a GitHub project presentable with a minimal project icon, social preview image, GitHub Pages landing page, standardized README, essential shields, CI/CD quality gates, release automation checks, and optional donation setup. Prefer the external `logo-generator` skill for icon generation when available, and `nolangz/pixel2motion` for optional motion previews of supported logos or simple artwork.
release-day
Orchestrate a full release-day workflow for iOS, Android, or Garmin apps: verify the main branch CI is green, generate a changelog from git history, draft platform-ready store listing copy, trigger semantic-release (or tag manually), wait for the build, and queue the App Store submission. Use when the user says "cut a release", "ship version X", "it's release day", or "prepare the release".
store-listing-copy
Generate polished, platform-validated App Store / Google Play / Connect IQ store listing copy (title, subtitle, description, "what's new", keywords) from a git changelog or release notes. Use when preparing a new release submission, when the user says "write the store listing", "update the App Store description", "draft the what's new", or "prepare my store copy" for iOS, Android, or Garmin apps. Chains naturally after changelog-generator and before apple-store-submit or garmin-watchface's store publishing workflow.
add-to-my-skills
Copy a newly created skill from another repo into this catalog, refresh the README and generated manifests, then commit and push the change. Use when the user wants to bring a skill they built elsewhere into this repository.
ai-tools-setup
Set up, repair, and report on the RTK+ICM+Vox AI development toolkit. Installs missing tools, fixes broken hooks and MCP config, and shows an effectiveness digest (token savings, memory accumulation, voice health) on demand or as a scheduled weekly report.
context-repo
Resolve a durable private GitHub repository for agent-produced context such as retro snapshots and shared-knowledge-artifact mirrors, creating it once with explicit consent and remembering the decision afterward. Returns a clone path and a verified receipt to the calling skill. Use when a skill needs a durable, private, cross-machine store for artifacts it generates, rather than a repo-local scratch directory that does not survive across machines or repos.
promptctl
Use promptctl for template-based prompt engineering, prompt scoring, prompt generation, and reusable prompt workflows across repositories and teams.
relay
Use claude-relay to run a long or rate-limit-prone task autonomously across subscription accounts. Invoke this skill whenever the user says "use relay", "run this with relay", "do this overnight", "run this autonomously", "use relay for X", or has a multi-hour / multi-step task they want to hand off completely. Also use proactively when a task looks like it will take many turns and the user hasn't thought about rate limits yet. Guides goal writing, picks the right flags, and starts the run.
skill-budget-audit
Diagnose and fix Claude Code's skill context budget overflow, identify heavy plugin bundles that exceed the 2% budget, remove domain-specific ones, deactivate rarely-used skill sets, and validate the warning clears. Use when Claude Code shows "Exceeded skills context budget" or skill descriptions are stripped.
veto-routing
Use the Veto CLI to select or execute AI models when a task needs multi-provider routing, structured accept or reject decisions, cost-aware dispatch, provider fallback, or Veto plan execution. Do not use for ordinary repository commands or generic model advice.
cloudflare-block-countries
Block specific countries via Cloudflare WAF Custom Rules using the Cloudflare API. Use when user wants to geo-block traffic, block countries in Cloudflare, set up WAF country rules, or mentions blocking regions. Handles both creating new rulesets and updating existing ones.
search-console-indexing-audit
Analyze Google Search Console Coverage or indexing CSV exports and correlate them with repo and live-site SEO signals. Use for Chart.csv, Metadata.csv, Critical issues.csv, Non-critical issues.csv, sitemap/robots/canonical indexing problems, "Discovered - currently not indexed", redirect indexing buckets, or requests to fix Google indexing coverage.
semantic-release-beta
Set up or update a Node.js release pipeline that uses semantic-release-npm-github-publish with a stable main channel and a prerelease beta channel on a beta branch, including GitHub Actions validation and npm publishing behavior.
docs-index-keeper
Keep a repository's Markdown docs index in sync by installing and running docs-index-keeper in pre-commit hooks, CI, or one-off maintenance flows.
retro-analysis
Produce a recurring engineering retrospective from repository history, delivery evidence, work patterns, code-quality signals, and prior snapshots, with repository, comparison, and cross-project modes.
vinted-listing
Create, edit, and safely publish Vinted listings through the signed-in browser, using verified item details and the owner’s original photos.
garmin-watchface
Build, test, screenshot and publish Garmin Connect IQ watch faces in Monkey C. Use when working on a Connect IQ watch face or app - creating one, fixing layout that clips or overlaps, capturing simulator screenshots, adding app settings, widening device support, or preparing a Connect IQ Store submission. Encodes the traps that silently produce a passing build and a broken face.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.