Search and discover Agent Skills from prompts.chat

Search and discover AI prompts from prompts.chat

Deprecated - use the superpowers:writing-plans skill instead

Deprecated - use the superpowers:executing-plans skill instead

Deprecated - use the superpowers:brainstorming skill instead

Backend-focused workflow (Research → Ideation → Plan → Execute → Optimize → Review), Codex-led.

Start a managed autonomous loop pattern with safety defaults.

Multi-model collaborative execution - Get prototype from plan → Claude refactors and implements → Multi-model audit and delivery.

Analyze context window usage across agents, skills, MCP servers, and rules to find optimization opportunities. Helps reduce token overhead and avoid performance warnings.

Fix C++ build errors, CMake issues, and linker problems incrementally. Invokes the cpp-build-resolver agent for minimal, surgical fixes.

Enforce TDD workflow for Go. Write table-driven tests first, then implement. Verify 80%+ coverage with go test -cover.

Analyze the current session and extract any patterns worth saving as skills.

Comprehensive Go code review for idiomatic patterns, concurrency safety, error handling, and security. Invokes the go-reviewer agent.

Recommend the best model tier for the current task by complexity and budget.

Enforce TDD workflow for Kotlin. Write Kotest tests first, then implement. Verify 80%+ coverage with Kover.

Show learned instincts (project + global) with confidence

Import instincts from file or URL into project/global scope

Fix Kotlin/Gradle build errors, compiler warnings, and dependency issues incrementally. Invokes the kotlin-build-resolver agent for minimal, surgical fixes.

Create or verify a checkpoint in your workflow.

Run a deterministic repository harness audit and return a prioritized scorecard.

Start NanoClaw v2 — ECC's persistent, zero-dependency REPL with model routing, skill hot-load, branching, compaction, export, and metrics.

Comprehensive security and quality review of uncommitted changes:

Enforce TDD workflow for C++. Write GoogleTest tests first, then implement. Verify coverage with gcov/lcov.

Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.

Look up current documentation for a library or topic via Context7.

Orchestrate parallel Claude Code agents via Claude DevFleet — plan projects from natural language, dispatch agents in isolated worktrees, monitor progress, and read structured reports.

Analyze instincts and suggest or generate evolved structures

Manage eval-driven development workflow.

Fix Go build errors, go vet warnings, and linter issues incrementally. Invokes the go-build-resolver agent for minimal, surgical fixes.

Inspect active loop state, progress, and failure signals.

Incrementally fix build and type errors with minimal, safe changes.

Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.

Comprehensive C++ code review for memory safety, modern C++ idioms, concurrency, and security. Invokes the cpp-reviewer agent.

Fix Gradle build errors for Android and KMP projects

Export instincts from project/global scope to a file

Comprehensive Kotlin code review for idiomatic patterns, null safety, coroutine safety, and security. Invokes the kotlin-reviewer agent.