ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
integration-testing-http
Run curl-style integration checks against the docker-compose stack for HTTP APIs. Required for use-case changes.
frostaura/ai.toolkit.gaia 31
-
spec-consistency
Prevent and repair drift between `/docs` (source of truth), code, tests, CI, and runtime artifacts. Use before marking work done.
frostaura/ai.toolkit.gaia 31
-
gaia-process
End-to-end Gaia SDLC workflow (Repo Explorer → drift/CI fixes → task graph → gated delivery → QA veto → MCP proof). Use for any work in a repo.
frostaura/ai.toolkit.gaia 31
-
stack-default-web-ts
Opinionated baseline for JS/TS web repos: lint/format, tests, Playwright, docker (if HTTP API), Makefile targets, and CI wiring.
frostaura/ai.toolkit.gaia 31
-
manual-regression-api
Manual backend regression via curl-like HTTP checks against the docker-compose stack. Required for API use-case changes (label: curl).
frostaura/ai.toolkit.gaia 31
-
manual-regression-web
Perform manual web regression using Playwright MCP tools (interactive). Required for web use-case changes. Keep evidence low-context (labels + paths only).
frostaura/ai.toolkit.gaia 31
-
linting
Add or extend lint/format tooling and ensure it runs locally (Makefile) and in CI. Lint/build are always required in Gaia.
frostaura/ai.toolkit.gaia 31
-
stack-default-flutter
Opinionated baseline for Flutter apps: format/analyze, tests, Makefile targets, and CI wiring (no docker unless backend exists separately).
frostaura/ai.toolkit.gaia 31
-
doc-derivation
Derive comprehensive `/docs` from an existing codebase when docs are missing/stale. This is blocking work before new features.
frostaura/ai.toolkit.gaia 31
-
dockerize-http-api
Add docker-compose for HTTP APIs (required before implementing/changing use cases). Provide .env.example + Make targets: up/down/test/lint/build.
frostaura/ai.toolkit.gaia 31
-
stack-default-dotnet-maui
Opinionated baseline for .NET MAUI apps: analyzers/format, tests where feasible, Makefile targets, and CI wiring (build validation).
frostaura/ai.toolkit.gaia 31
-
playwright-e2e
Add/extend Playwright E2E/integration specs for web use-case changes. UC ID must be in spec filename. Prefer existing repo conventions; else standardize.
frostaura/ai.toolkit.gaia 31
-
ci-baseline
Ensure GitHub Actions CI exists and is green. CI must run lint/format, build, and tests as applicable. Failing CI is blocking.
frostaura/ai.toolkit.gaia 31
-
repository-audit
Survey repo reality (stack, docs/code/skills drift, CI/lint/tests/docker/Makefile) and produce a compact Repo Survey + suggested tasks for the orchestrator.
frostaura/ai.toolkit.gaia 31
-
stack-default-python
Opinionated baseline for Python projects: ruff-based lint/format, pytest, optional dockerization for services, Makefile targets, and CI wiring.
frostaura/ai.toolkit.gaia 31
-
bun
Use Bun instead of Node.js, npm, pnpm, or vite. Provides command mappings, Bun-specific APIs, and development patterns.
brianlovin/agent-config 310
-
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
brianlovin/agent-config 310
-
fix-sentry-issues
Use Sentry MCP to discover, triage, and fix production issues with root-cause analysis. Use when asked to fix Sentry issues, triage production errors, investigate error spikes, or clean up Sentry noise. Requires Sentry MCP server. Triggers on "fix sentry", "triage errors", "production bugs", "sentry issues".
brianlovin/agent-config 310
-
workflow
Workflow orchestration for complex coding tasks. Use for ANY non-trivial task (3+ steps or architectural decisions) to enforce planning, subagent strategy, self-improvement, verification, elegance, and autonomous bug fixing. Triggers: multi-step implementation, bug fixes, refactoring, architectural changes, or any task requiring structured execution.
brianlovin/agent-config 310
-
react-doctor
Diagnose and fix React codebase health issues. Use when reviewing React code, fixing performance problems, auditing security, or improving code quality.
brianlovin/agent-config 310
-
playwriter
Control the user's currently open Chrome tab through the Playwriter CLI (no new browser launch). Use when you need to inspect live UI state, run scripted browser actions, capture console output, or reproduce frontend issues directly in the user's tab.
brianlovin/agent-config 310
-
deslop
Remove AI-generated code slop from the current branch. Use after writing code to clean up unnecessary comments, defensive checks, and inconsistent style.
brianlovin/agent-config 310
-
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
brianlovin/agent-config 310
-
reclaude
Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.
brianlovin/agent-config 310