Floom Starter Pack

The simplest path is to paste a single prompt into your agent:

Set up Floom Starter Pack: https://floom.dev/starter

Your agent reads the manifest at that URL and installs the right files for its runtime. No account needed. Nothing to configure.

If you prefer to run it yourself:

npx @floomhq/starter

The CLI detects which agent config files exist on your machine and writes only to the appropriate paths.

The pack writes three things per supported agent:

Total size on disk: approximately 120 KB for the full 97-skill pack. Individual skill files average 1.2 KB.

The pack supports five agents out of the box. Each agent reads skill context from a different path.

When you run the installer, it detects which of these directories exist and writes only to the ones that do. If none are found, it prompts you to choose.

The skill manifest is updated daily as new skills are published to skills.sh. To pull the latest version:

npx @floomhq/starter update

This reads your existing .floom/starter.lock, fetches the latest manifest, and writes only the files that have changed. Your existing activation rules in AGENTS.md or CLAUDE.md are preserved.

To update via your agent, paste:

Update Floom Starter Pack to latest: https://floom.dev/starter/update

To remove all files the pack added:

npx @floomhq/starter remove --all

This deletes the .floom/ directory and removes the Floom activation block from your AGENTS.md or CLAUDE.md. It does not touch anything outside the paths the installer originally wrote to.

To remove only a specific agent's config:

npx @floomhq/starter remove --agent claude-code

The Floom Starter Pack is a local install. After the initial download, it operates entirely on your machine.

• No telemetry. No analytics. No usage data is collected or transmitted.
• No account required. No sign-in. No API key.
• The installer downloads skill files from GitHub. After install, there are no ongoing network calls.
• The skill files themselves are static text. They contain no code that executes automatically.

The Floom Starter Pack installer and tooling is MIT licensed. This means you can use, modify, and redistribute it freely.

Individual skills in the pack carry their own licenses. The breakdown:

Each skill file includes a license header. If you redistribute individual skills, preserve the header.

The full technical shape of the pack: how the installer resolves targets, what files get written, how agents discover installed skills, and what V0 guarantees.

The package contains a manifest plus bundled skill folders. The installer resolves selected profiles, detects local agents, writes skills into their native roots, writes a local index, and adds instructions that teach agents to search locally.

When the user runs install, explicit targets win. If no target is passed, the CLI detects local agent config directories and installs only to those agents.

Each target receives skill folders in its native root, a harness instruction file, and a shared local index at ~/.floom/packs/starter-index.json.

Every installed skill gets a provenance file. Managed pack skills can be replaced by later installs; untracked user-created folders are protected by default.

No MCP is required in V0. The discovery loop is local: injected instructions point the agent at the starter index and the local-find-skills skill.

The manifest links profiles to skills, and skills to their upstream source records — keeping provenance legible and auditable.

Next curation pass planned sources:

Behaviors confirmed across all five launch targets. These are the acceptance criteria for any release.

Skills.sh indexes 91,035 skills. We curated 63 of them. The selection rules:

The 4 source tiers, in priority order:

Vercel published research showing that agents skip 56% of installed skills by default. Even with an explicit "use these skills" prompt, invocation only reaches 70%. The AGENTS.md activation pattern achieves 100%.

The pattern works by embedding per-skill trigger conditions directly into the agent's context file (CLAUDE.md or AGENTS.md). Instead of telling the agent "you have 63 skills available," it tells the agent: "when the user says X, invoke Y."

Source for the 100% claim: Vercel's agent evals post. The AGENTS.md pattern is also the basis for Anthropic's own Claude Code setup.

The SkillsBench paper (arxiv.org/abs/2602.12670) tested agent performance across three skill installation strategies:

The mechanism: irrelevant skills confuse the agent about what to use. A kitchen-sink install forces the agent to evaluate 200+ options per task, increasing both latency and error rate. The sweet spot is 2-3 well-matched skills per task, which is exactly what profile-based curation produces.

This is why the pack uses profile tags. When you label yourself as a developer, you get the 12 dev skills in your activation block, not all 97. The agent doesn't know about skills outside your selected profiles unless it invokes find-skills specifically.

Floom doesn't author most of the skills in this pack. We curate them from the open ecosystem (mostly skills.sh) and add five things on top:

When you install via Floom, you're getting the original author's skill — with the activation, distribution, and update layer Floom provides on top. We link every skill to its source repo. Floom doesn't intermediate the code.

Skills run inside your agent, on your API key, using your token budget. Floom is the distribution layer. We curate, package, and activate. Your agent executes.

This is intentional. Skills that run on a third-party runtime can't access your local filesystem, your git repo, or your project context. Skills that run in your agent can do all three. The power of skills is that they run where your agent runs.

Floom's business is the distribution infrastructure: the manifest, the installer, the activation pattern, and the curation. Not the inference.