superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Workflow orchestration, verification, and contribution skills for AI coding agents — plan-first execution, evidence-backed completion, autonomous bug fixing, subagent strategy, and changeset management.
Plugin unional-skills from marketplace unional in unional/skills. Commands read from the repo's manifest — 7 days ago.
add-changesetAdd a changeset to the current change. Use when preparing a PR that affects published packages, when asked to 'add a changeset', or when CI reports a missing changeset. Detects monorepos and selects affected packages automatically.
autonomous-bug-fixingFix bugs without hand-holding. Investigate logs, errors, failing tests — then resolve. Zero context switching for the user. Use when given a bug report, fixing failing CI, or when the user reports an error.
community-proposalUse this skill when contributing a design proposal to an open-source community — research, draft with evidence, file.
create-skillUse this skill when the user asks to create a new agent skill. Creates the skill directory under ~/.agents/skills/ and links it into all detected agents so they can pick it up.
demand-elegancePause on non-trivial changes to ask for a more elegant solution. Skip for simple fixes. Use when a fix feels hacky, implementing non-trivial changes, or before presenting work. Elegance for non-trivial; pragmatism for trivial.
fix-security-prFix a PR that is failing due to security or vulnerability issues — npm/pnpm/yarn/bun audit failures, CVE alerts, Dependabot merge conflicts, Snyk failures, or GitHub security advisory blocks. Use when asked to 'fix the security PR', 'resolve the vulnerability failure', or 'unblock the Dependabot PR'
initUse this skill when the user wants to initialize or improve an AGENTS.md file with codebase documentation. Creates AGENTS.md and symlinks CLAUDE.md to it, or suggests improvements if AGENTS.md already exists.
self-improvement-loopCapture corrections in tasks/lessons.md. Update after ANY user correction, write rules to prevent repeat mistakes, review at session start. Use when receiving corrections, starting a session, or building a lessons-learned practice.
setup-changesetsSet up changesets in a new or existing repository, or upgrade an existing setup across a major. Use when asked to 'add changesets', 'set up releases', or 'configure versioning'; when a release job fails with a Changesets CLI/action version mismatch; or when asked to upgrade changesets from v2 to v3.
subagent-strategyUse subagents liberally for research, exploration, and parallel analysis. Offload work to keep main context clean. Use when context is crowded, tasks can run in parallel, or for research/exploration work. One focused tack per subagent.
validate-skillValidate a SKILL.md file for structure, quality, and security before committing or publishing. Use this skill when reviewing a new or modified skill — catches broken references, vague triggers, baked-in assumptions, scope creep, and security risks in one pass.
verification-before-doneNever claim a task complete without proving it works. Run tests, check linter, verify build. Use when finishing tasks, before marking done, or when the user asks for verification. Requires evidence for every completion claim.
workflow-planningPlan-first for non-trivial tasks. Enter plan mode, write to tasks/todo.md, stop and re-plan when things go sideways. Use when starting complex work (3+ steps), making architectural decisions, or before implementation.
add-websiteAdd a website to one of unional's TypeScript packages or monorepos — an Astro + Starlight docs site in apps/website, deployed to GitHub Pages, matching the cyberuni house layout (base path, cyber-* icon system, Linear theme). Use when asked to 'add a website', 'add a docs site', 'add an astro websit
apply-repo-baselineBring one of unional's repos or organizations up to the standard baseline — branch protection ruleset, merge and Actions settings, security toggles, and the CI/release file layout. Use when setting up a new repo, when asked to 'update branch protection', 'require all-checks', 'apply my repo settings
audit-release-healthSweep an owner's repos to find which ones stopped publishing, classify each failure by root cause, and report the evidence needed to fix them. Use when asked 'which of my repos are broken?', 'is anything not publishing?', 'audit my releases', 'find repos that need modernizing', or before running mod
migrate-legacy-ciDecide what to do with one of unional's repos still on a legacy CI shape — a single `nodejs.yml` calling `typescript-build.yml`/`typescript-test.yml`/`npm-release.yml`, or inlined yarn steps — and then archive it, drop its CI, or migrate it to the `pull-request.yml` + `release.yml` split. Use before
modernize-repoBring one repo fully current: settings baseline, a release that publishes without long-lived tokens, dependency PRs that merge themselves, and proof it all works. Use this skill when asked to 'modernize this repo', 'bring it up to standard', 'fix everything about this repo', or after a sweep flags a
modernize-toolchainReplace a TypeScript library's build, lint, test and dependency stack in one pass — tsdown for the build, biome for lint, turbo for tasks, vitest for tests — instead of upgrading tools that the swap deletes. Use when asked to 'modernize the toolchain', 'bring the deps current', 'replace webpack/esli
post-on-xDraft, review, and plan posts on X (Twitter) to grow a developer account, using the ranking weights X publishes. Use when asked to 'draft a tweet', 'announce the release on X', 'plan the release posts', 'write a thread', 'review this post', 'when should I post', 'how do I get more reach', or 'grow m
replicate-wsl-machineCapture what an Ubuntu WSL machine has installed and configured into a manifest, then rebuild it on a fresh WSL distro or another PC. Use this skill when asked to 'set up a new WSL like this one', 'replicate my machine', 'move to Ubuntu 26.04', 'bootstrap a new dev box', 'what's different between my
setup-orgSet up a new GitHub organization in the cyberuni house style — a public .github repo with the org profile, community health files, and reusable pnpm workflows; Discussions; an org Project; org description and homepage; and a logo drawn in the cyber-* icon frame, rendered as light and dark PNG avatar
setup-secretless-releaseMove a package's release off long-lived NPM_TOKEN/PAT secrets onto OIDC trusted publishing, migrating it to pnpm + changesets on the way, and keep dependency PRs merging themselves. Use this skill when a release publishes with a token, has silently stopped publishing, fails with 401 on /-/whoami or
ship-itShip a pending changesets release: find the repo's open Version Packages PR, approve the workflow run GitHub is holding for approval, verify the required check goes green, merge, and confirm the version actually advanced on the registry. Use when asked to 'ship it', 'release', 'ship', or 'publish' a
sweep-dependencyUse this skill when bumping one package across all repos the owner publishes, leaf-first, merging and releasing each.
technical-writerApply a consistent documentation standard: controlled plain prose, one home per fact, and every external claim backed by a source. Use when writing or revising documentation, READMEs, or skill bodies; when deciding where a document belongs; when moving, renaming, or splitting a page; when a draft re
transfer-repo-to-orgMove a repo from a personal namespace into an organization without breaking its release — re-registers the npm trusted publisher that pins owner/repo, fixes package metadata and badges, and turns on the merge queue that only org-owned repos can have. Use when asked to 'transfer this repo', 'move it
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.