agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/frontend-starter-kit/SKILL.md

frontend-starter-kit

Skill4 starsChanged 10 days agoMITView on GitHub

Bootstrap the frontend toolchain, lint, quality gates, React stack, data stack, and CI.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    full: default: canonical stack in REFERENCE.md, using the order below.

    line 12
  2. Very specific:

    <tool>: only that reference.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Bootstrap idempotently. Read only requested references/<tool>/README.md and linked guides. Hook copies are no-ops in plugins; bare repos need export-harness copies.

Profiles

  • full default: canonical stack in REFERENCE.md, using the order below.
  • minimal: toolchain, biome, quality gate, env validation, conventional commits.
  • redpanda: full plus references/redpanda/README.md, taxonomy, REDPANDA_KIT=1.
  • <tool>: only that reference.

Full order

ToolPurpose
toolchainreferences/toolchain/: bun, TS 7 tsc/tsrs, destructive-command guards
tanstack-intentversion-matched guidance/edit gates
biomeBiome, Ultracite, auto-fix hook
quality-gatescript, CI, Stop hook, bundle guard
agent-configAI_AGENT=1, output truncation
react-compilerCompiler, memoization check
zustandcreate<T>()(), useShallow, persist
react-rulesraw HTML, TS escape, XSS, barrel bans
env-validationt3-env/zod, noProcessEnv
conventional-commitstype(scope): description
react-doctorchanged-diagnostic gate, Stop hook
ci-pipelineActions, coverage, cache
redpandaregistry workflow/taxonomy

Runtime skills, not setup: /accessibility, /tanstack-router, /connect-query, /e2e-testing, /registry-workflow, /ux-copy. Optional slash-only infra: /setup-routines, /setup-atlassian-workflow.

Steps

  1. Confirm profile; for full, process the table sequentially and lazily.
  2. Set REACT_RULES_BAN_USEEFFECT=1 only for repos choosing strict effects.
  3. Auto-setup safeguards in every consumer; honor the endpoint.
  4. Workflow skills already ship in the plugin; install nothing extra.

Verify

  • .claude/settings.json has hooks, including TanStack Intent when packages exist; biome.jsonc and src/env.ts exist.
  • Scripts: lint, lint:fix, type:check, test, quality:gate.
  • .github/workflows/quality-gate.yml exists; hooks executable.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free