agentsclimarketplace
Sign in

Bootstrap

Skill yousefkadah/laravel-ai-kit/skills/bootstrap

Use ONCE right after installing this kit into a project (or when onboarding an agent to an unfamiliar repo). Scans the codebase and fills in .ai/context.md + .ai/architecture.md, replaces the «placeholders», and drafts project-specific skills — turning the blank template into a project-aware guide.From its SKILL.md

Install
npx -y skills add yousefkadah/laravel-ai-kit --skill bootstrap

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.7 KB, 587 tokens by cl100k_base, as published. Nobody here has run it

Bootstrap this project's AI guidance

The kit ships as a template full of «placeholders». Your job is to read the actual repository and fill it in, so every agent that reads .ai/ gets accurate, project-specific guidance. Do this as a read-only scan that proposes edits — never auto-commit; the human reviews your draft.

1. Scan (read-only)

  • Detect the stack from manifests: composer.json, package.json, pyproject.toml/requirements.txt, go.mod, Gemfile, etc. Note framework(s), test runner, and build tooling.
  • Map the layout: where controllers/services/models/components/tests/config live; entry points; how the app is run and tested (check README, Makefile, composer/npm scripts, CI config).
  • Identify cross-cutting rules from the code itself: multi-tenancy scoping, money/units handling, auth/permissions, queueing, i18n/RTL — anything an agent would get wrong without being told.
  • List the third-party integrations already present (SDKs, webhooks, API clients, file formats).

2. Fill the canonical source

  • .ai/context.md — what the project is, who uses it, the top priorities, domain vocabulary.
  • .ai/architecture.md — the real stack, the real "where things live" table, the real cross-cutting rules.
  • Replace every «placeholder» across .ai/ (including coding-standards, testing-policy, release-policy) with what the repo actually does. If you can't determine something, leave a clearly marked «TODO: confirm …» rather than guessing.

3. Draft project-specific skills

  • For each recurring workflow you can see in the repo, draft a skills/<name>/SKILL.md using the existing skills as templates (sharp description, imperative body, concrete file paths).
  • Especially: for each existing third-party integration, draft a short skill capturing its endpoints, auth, credential location (never values), quirks, and a drift-watch source — following skills/add-integration.

4. Hand back for review

  • Present the filled files and drafted skills as a diff for the human to review and edit.
  • Do not invent facts. Do not include any secret, key, token, or .env value (see .ai/security-policy.md).
  • Suggest which tool adapters to (re)generate if the kit's installer is available.

This is the "scan & fill" step: the kit gives the structure, your agent supplies the project knowledge.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most project setup skills give in 587 tokens

Counted across 999 of the 1,637 authors here whose files we hold, read 2026-08-07

  • Ask one question at a timein 29 of 999, across 28 files
  • Detect the package manager from lockfilesin 28 of 999, across 9 files
  • Present findings to the userin 26 of 999, across 5 files
  • Explore current repo statein 24 of 999, across 3 files
  • Update the agent skills block in place if it existsin 24 of 999, across 3 files
  • Install husky lint-staged and prettierin 23 of 999, across 4 files
  • Create the lintstagedrc filein 22 of 999, across 3 files
  • Commit all changed filesin 22 of 999, across 3 files
  • Run lint-staged to verify it worksin 22 of 999, across 3 files
  • Create the husky pre-commit filein 21 of 999, across 2 files
  • Create a prettierrc file if missingin 21 of 999, across 2 files
  • Initialize huskyin 21 of 999, across 2 files

Said here and by no other author read

  • map the repository layout
  • identify cross-cutting rules from code
  • list third-party integrations present
  • fill the canonical source files
  • replace all placeholders with accurate facts
  • draft skills for recurring workflows

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,861. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.