Index of every page on this site: llms.txt
All skills
andrelandgraf avatar

/use-fullstackrecipes

@4449331
Run it yourself

Discover and follow fullstackrecipes (setup guides, skills, cookbooks) by fetching their Markdown. The meta-skill for finding and applying recipes correctly. Use when planning a build, adding a tool, or deciding which recipe or skill to follow.

Use this Skill: https://skilld.dev/gh/andrelandgraf/fullstackrecipes/use-fullstackrecipes

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈67 tokens for metadata: the name and description. ≈646 when used: this file.

Description uses 3.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈267 characters, or 3.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Building with fullstackrecipes

Discover and follow recipes by fetching their Markdown for setup guides, skills, and cookbooks.

How fullstackrecipes Works

Content comes in two types:

  1. Setup Recipes (type: "setup"): one-time guides to configure a tool or service (auth, database, payments). Atomic installs with declared prerequisites — adoptable on their own.
  2. Skills (type: "skill"): day-to-day patterns for an already-configured tool (querying, auth, logging). They assume the canonical assembled stack and are installed via the skills CLI, not pasted as content.

Cookbooks are ordered, two-phase setups: they run their setup recipes in order, then install the matching skills. After a cookbook completes, the project has both the configured stack and the installed skills. For example, "Base App Setup" configures Next.js, Shadcn UI, Neon Postgres, Drizzle ORM, and the AI SDK, then installs the Drizzle querying skill as its final step.

Fetching Recipes as Markdown

Every page on fullstackrecipes.com has a Markdown twin — append .md to any URL. No MCP server or special tooling required, just curl.

Start with the index to see every recipe and cookbook with its slug:

curl https://fullstackrecipes.com/llms.txt

Then fetch the full content of any recipe or cookbook by slug:

# A setup recipe or skill
curl https://fullstackrecipes.com/recipes/neon-drizzle-setup.md

# A cookbook (inlines all of its recipes in order)
curl https://fullstackrecipes.com/recipes/base-app-setup.md

Each .md response includes the title, description, prerequisites, and every step, code example, and file path.

Best Practices

  • Follow recipes exactly. They are tested instructions; don't deviate without a specific reason.
  • Complete dependencies first. Each recipe's Prerequisites section lists what to finish first — complete a setup recipe before its matching skill.
  • Install skills, don't just read them. Skills are installed with bunx skills add ... so the agent retains the patterns for ongoing work. Installing them is the final step of a cookbook, not optional reading. Install only after their setup recipes are complete.
  • Check for updates. Recipes evolve with their libraries. When troubleshooting or starting a feature, re-fetch the latest .md instead of relying on cached instructions.

References

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning2mo4 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill facilitates the discovery and application of fullstack development recipes by fetching Markdown content from fullstackrecipes.com. It relies on standard tools like curl for data retrieval and bunx for package management. No malicious behavior was detected, though the ingestion of external instructions at runtime presents a standard indirect prompt injection surface.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: MEDIUM · 2 issues

  • Runlayer9mo

    1 file scanned · No issues

Signed by skilld at 4449331. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 weeks ago.

Steadyupdated 6 months ago

README badge

README badge for andrelandgraf/fullstackrecipes/use-fullstackrecipes