superpowers-extensions

Runs a groomed queue of plans without a human present: denies questions nobody will answer, keeps stops from ending the run early, and logs every call made on the user's behalf. Includes ready-check, which checks the work is ready and writes the queue.

2 skills · hooks

Finds shallow modules in the areas the git history changes most, publishes a ranked report with before/after diagrams, lets you pick one candidate and hands it to brainstorming. Includes codebase-design, the shared deep-module vocabulary for designing and deepening interfaces.

2 skills

Waits for CI as an event, fixes red CI, merges a green PR when asked and follows the release. A hook starts the watch whenever a PR is opened.

1 skill · hooks

Keeps long sessions cheap. Hands off to a fresh session at a natural break once the context grows large, and requires an explicit non-Fable model on general-purpose subagent dispatches. States the suite-wide model rule: Sonnet by default, Opus for marked tasks, retries and the final review, Haiku for lookups.

1 skill · hooks

Records a finished web feature as a paced browser walkthrough video. A storyboard drives a real Chromium on the running app, then ffmpeg builds chapter MP4s with captions and cards, speeds up slow waits, and checks frames before it reports done.

1 skill · 1 MCP server

AI-powered regression testing for web applications. Discovers existing test suites, runs them, then performs functional checks and visual evaluation via Playwright MCP browser automation at desktop, tablet, and mobile viewports. Generates detailed markdown reports with screenshots.

1 skill · 1 MCP server

Rewrites AI prose tics out of text Claude is about to publish, in English and Dutch. Commit messages, PR and issue text, comments, READMEs and docs are checked against a pattern catalogue and published in their plain form, with no report.

1 skill

Waits for CodeRabbit, validates and fixes its findings, and hands an approved, green PR to ci-watch to merge.

1 skill

Compress natural-language memory files (CLAUDE.md, STATE.md, ROADMAP.md, project notes) to save input tokens replayed every session. Preserves code blocks, URLs, file paths, frontmatter, headings, tables, and list structure byte-exact. Refuses to operate on downstream-consumed plan artifacts. Opt-in via project-orchestration plan-roadmap; auto-invoked by pause-work.

1 skill

Persistent cross-cutting decision tracking using long-term memory. Automatically extracts decisions during brainstorming and planning, recalls them at session start and subagent dispatch.

1 skill

Generates a brand mark: three concepts drawn as SVG, then the winner shipped as a docs/design/LOGO.md brief plus full, stacked, mark-only, wordmark-only, mono, and favicon variants. Exports the PNG and ICO icons hosts actually read, and optionally replaces a project's existing icon files. Renders a contact sheet and, when Playwright MCP is available, self-critiques with vision before presenting. Scoped to geometric, monogram, wordmark, and abstract marks; refuses pictorial, mascot, and emblem work. Includes logo-review for auditing existing marks.

1 skill

Superpowers integration for MemoryLens memory profiling. Enhances systematic-debugging with .NET memory snapshot analysis, leak detection, and before/after fix validation when MemoryLens MCP tools are available.

1 skill

Comprehensive branch review before push or PR. Diffs against the base branch and reviews plan adherence, code quality, commit hygiene, and regression testing. Produces a PASS/FAIL verdict with a prioritized remediation plan on failure.

1 skill

GSD-inspired project lifecycle management for larger multi-session projects. Brownfield codebase mapping, milestone tracking, phase management (add/insert/remove), session pause/resume, progress overview, milestone audit, and release cycle management.

1 skill

Transitive impact analysis for complex refactorings. Maps all affected files, classifies breaking vs cosmetic changes, identifies risks like dynamic references and cross-boundary impacts, and produces a safe execution order with checkpoint boundaries.

1 skill

Reads a finished session's transcript and ranks setup improvements most severe first: information access, guardrails, reviewer rules, navigation, tool cost and steering files. Each finding is fixed, filed as a grouped issue or dropped, chosen per finding.

1 skill

Superpowers integration for Roslyn CodeLens intelligence. Enforces use of 32 semantic .NET code analysis tools (instead of Grep/Glob and dotnet build) across every superpowers skill — brainstorming, refactor-analysis, writing-plans, executing-plans, subagent-driven-development, systematic-debugging, TDD, verification, code review, and pre-push review — for architectural context, dependency mapping, risk detection, and code quality analysis.

1 skill

Persistent AI agent teams for Claude Code. Lead, Backend Engineer, Frontend Engineer, Tester, and Scribe agents participate actively in brainstorming and planning, answer domain questions from project-specific knowledge, and grow smarter across sessions via automatic history write-back.

1 skill

Generates complete design systems before frontend implementation. Curated mode adapts a vendored real-world reference (Stripe, Linear, Notion, ...), guided mode asks 7 questions, quick mode takes a one-liner; five OKLch directions and a WCAG contrast check on every text pair. Auto-detects Blazor, React, Vue, Astro stacks. Outputs docs/design/MASTER.md for consumption by ui-workflow ui-phase.

1 skill

Frontend design contracts and visual auditing. Generates structured UI design contracts before implementing frontend phases (ui-phase) and performs retroactive visual audits against those contracts using regression-test (ui-review).

1 skill

Reports a bug to an upstream project only after proving it is theirs. A minimal repro is built and run, a skeptic and a clean-room runner check it independently, and the issue draft passes anti-slop and a privacy scan before the user approves it.

1 skill

Generates an interactive bash script that walks a person through setup steps only they can do: dashboards, API keys, .env values, GitHub secrets and variables, one-off migrations. Claude scopes the steps from the repo, writes the script from a shared template and checks it with one command. Adapted from Matt Pocock's wizard skill (MIT).

1 skill