Floom starter skills
Small starter templates for company knowledge, brand voice, PR review, and team onboarding.
or use the CLI
floom library subscribe floom-startersCurated collections from the community. Add a whole library, or pick one skill at a time. Works in Claude Code, Codex, Kimi, Gemini CLI, and OpenCode.
Each library is a folder of related skills. Subscribe and they all flow into your agent.
Small starter templates for company knowledge, brand voice, PR review, and team onboarding.
floom library subscribe floom-startersSelected MIT-licensed skills from garrytan/gstack for shipping, review, browser, and operational workflows.
floom library subscribe gstackSelected MIT-licensed skills from obra/superpowers-skills for planning, debugging, TDD, and agent collaboration.
floom library subscribe superpowers21 public skills. Open one and copy the install command.
TDD for process documentation - test with subagents before writing, iterate until bulletproof
Run verification commands and confirm output before claiming success
Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.
Write the test first, watch it fail, write minimal code to pass
Dispatch code-reviewer subagent to review implementation against plan or requirements before proceeding
Execute detailed plans in batches with review checkpoints
Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context
Interactive idea refinement using Socratic method to develop fully-formed designs
OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack) Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug directly) when the user reports errors, 500 errors, stack traces, unexpected behavior, "it was working yesterday", or is troubleshooting why something stopped working. (gstack)
Code quality dashboard. Wraps existing project tools (type checker, linter, test runner, dead code detector, shell linter), computes a weighted composite 0-10 score, and tracks trends over time. Use when: "health check", "code quality", "how healthy is the codebase", "run all checks", "quality score". (gstack)
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". (gstack)
Codify the most recent successful /scrape flow into a permanent browser-skill on disk. Future /scrape calls with the same intent run the codified script in ~200ms instead of re-driving the page. Walks back through the conversation, synthesizes script.ts + script.test.ts + fixture, runs the test in a temp dir, and asks before committing. Use when asked to "skillify", "codify", "save this scrape", or "make this permanent". (gstack)
Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is ready, asks about deploying, wants to push code up, or asks to create a PR. (gstack)
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes. (gstack)
A starter workflow for bringing an agent into a project.
Review code changes for launch-risk issues.
Make agent output sound like the team.
Reusable company context for agents.
A practical review workflow for agents checking pull requests.
Publish from your terminal in a single command. Free. Open source.