GitHub collection

goldziher/ai-rulez

Imported from GitHub — is this yours?

151 skills imported from this repository.

View on GitHub
162 16 MIT
Claude Skill

capability-delivery-checklist

Use when adding a new CLI command, flag, preset, or other user-visible capability, and before opening a pull request for it: covers the plan, tests, docs, schema, wrappers, and final validation steps.

LLM Mart

Claude Skill

config-schema-maintainer

Use when changing config.toml fields or defaults, include resolution, domain or profile behavior, the JSON schemas in schema/, or the loader, validator and migration code in internal/config and internal/migrate.

LLM Mart

Claude Skill

docs-and-site

Use when editing files under docs/, zensical.toml, or the generated site/, or when a CLI or config change needs its documentation, examples, onboarding, or migration guidance updated.

LLM Mart

Claude Skill

mcp-integrations

Use when changing the MCP server in internal/mcp, its handlers or tools, [[mcp_servers]] configuration, MCP schemas, or the tests and docs for MCP endpoints.

LLM Mart

Claude Skill

release-and-distribution

Use when preparing a release, bumping versions across root.go, package.json and pyproject.toml, or changing the npm and PyPI wrappers in release/, the changelog, or distribution assets.

LLM Mart

Claude Skill

repository-layout

Use when you are unsure where code, docs, schemas, wrappers, or tests live in this repository, or need to pick the right directory before adding or moving files.

LLM Mart

Claude Skill

test-fixture-maintainer

Use when writing or fixing tests, updating fixtures under tests/, or adding integration or e2e coverage for generator, migration, CLI flags, or profile behavior.

LLM Mart

Claude Skill

dev-server

Starts the web app dev server. Use when the user wants to preview UI changes locally.

LLM Mart

Claude Skill

install-deps

Installs the web app dependencies. Use when node_modules is missing or the lockfile changed.

LLM Mart

Claude Skill

dependency-bump

Bumps one dependency to a newer version. Use when the user names a package to upgrade.

LLM Mart

Claude Skill

frontend-setup

Sets up the JavaScript toolchain on a fresh checkout. Use when onboarding a new machine.

LLM Mart

Claude Skill

lockfile-refresh

Regenerates the dependency lockfile. Use when the manifest changed and the lockfile is out of date.

LLM Mart

Claude Skill

log-rotation-check

Checks that log rotation is configured. Use when a service disk fills up.

LLM Mart

Claude Skill

new-branch

Names a new git branch. Use when the user starts work on a ticket.

LLM Mart

Claude Skill

ReleaseNotes

Drafts release notes from merged pull requests. Use when a release is being prepared.

LLM Mart

Claude Skill

secrets-policy

States the secrets policy for contributors. Use when asked how credentials are handled.

LLM Mart

Claude Skill

squash-commit

Commits the finished changes as one commit. Use when the user says the work is ready to commit.

LLM Mart

Claude Skill

start-ticket

Creates the git branch for a ticket. Use when the user starts a ticket and gives its key and a short slug.

LLM Mart

Claude Skill

write-tests

Writes a unit test for one Python function. Use when the user asks for tests of existing code; not for integration tests.

LLM Mart

Claude Skill

git-summary

Summarise recent commits for a standup.

LLM Mart

Claude Skill

weather-cli

Look up the current weather for a city via the Acme Weather API.

LLM Mart

Claude Skill

slack-notify

Post a message the user wrote to their Slack incoming webhook.

LLM Mart

Claude Skill

s3-publish

Sync the dist folder to the user's S3 bucket with the AWS CLI.

LLM Mart

Claude Skill

vendor-query

Query the Vendor API for account usage.

LLM Mart

Claude Skill

py-lint

Lint and format Python with pinned tool versions.

LLM Mart

Claude Skill

diff-stat

Show a diff stat against a base ref the user names.

LLM Mart

Claude Skill

git-helper

Branch, commit and rebase helper using git only.

LLM Mart

Claude Skill

cron-explainer

Explain crontab expressions in plain English.

LLM Mart

Claude Skill

dotfiles-doc

Print a prompt snippet the user can paste into their shell config.

LLM Mart

Claude Skill

tools-checkout

Fetch the internal tools repository at a pinned release.

LLM Mart

Claude Skill

image-resize

Resize an image file the user names with Pillow.

LLM Mart

Claude Skill

acme-status

Check whether the Acme API is up.

LLM Mart

Claude Skill

render-cache

Reset the render cache kept under the temp directory.

LLM Mart

Claude Skill

csv-to-parquet

Use when the user asks to convert a CSV file to Parquet.

LLM Mart

Claude Skill

tf-plan-review

Use when reviewing Terraform plan output. Triggers: terraform plan, tfplan, drift, plan diff, resource replacement.

LLM Mart

Claude Skill

aws-setup-doc

Explain the environment variables the deploy tooling needs.

LLM Mart

Claude Skill

smoke-load

Fire a bounded burst of requests at the local dev server.

LLM Mart

Claude Skill

wait-ready

Wait until a local service answers.

LLM Mart

Claude Skill

changelog-entry

Adds an entry to CHANGELOG.md in Keep a Changelog format. Use when the user finishes a user-visible change or asks to log one; not for version bumps.

LLM Mart

Claude Skill

pytest-triage

Diagnoses failing pytest runs from the output the user pastes or the last local run. Use when tests fail and the cause is unclear; not for writing new tests.

LLM Mart

Claude Skill

sql-explain

Explains a PostgreSQL EXPLAIN ANALYZE plan and points at the slowest node. Use when the user pastes a query plan; not for rewriting schemas.

LLM Mart

Claude Skill

openapi-lint

Lints an OpenAPI file with the bundled Spectral wrapper. Use when the user edits an OpenAPI spec and wants it validated.

LLM Mart

Claude Skill

dockerfile-review

Reviews a Dockerfile for image size and reproducibility problems. Use when the user asks for a Dockerfile review; not for Compose files.

LLM Mart

Claude Skill

rename-symbol

Renames a function, class or constant across the repository. Use when the user names the old and new identifiers; not for renaming files.

LLM Mart

Claude Skill

dep-audit

Audit dependency manifests for outdated packages.

LLM Mart

Claude Skill

repo-sync

Keep local branches tidy.

LLM Mart

Claude Skill

shell-format

Format shell scripts with shfmt.

LLM Mart

Claude Skill

changelog-gen

Generate a changelog from git history.

LLM Mart

Claude Skill

log-summary

Summarise application log files.

LLM Mart

Claude Skill

env-lint

Check that .env files are sorted.

LLM Mart

Claude Skill

toolchain-setup

Install the team toolchain.

LLM Mart

Claude Skill

rule-sync

Sync lint rules from the shared config server.

LLM Mart

Claude Skill

pr-branch

Create a local branch for a pull request.

LLM Mart

Claude Skill

code-format

Format Python files with black.

LLM Mart

Claude Skill

ticket-lookup

Find orders related to a support ticket.

LLM Mart

Claude Skill

shell-prompt

Show the git branch in the shell prompt.

LLM Mart

Claude Skill

nightly-fetch

Refresh dependency metadata.

LLM Mart

Claude Skill

fmt-helper

Normalise whitespace in config files.

LLM Mart

Claude Skill

color-utils

Colour a terminal log stream.

LLM Mart

Claude Skill

word-count

Count words in a markdown file.

LLM Mart

Claude Skill

spell-check

Check spelling in README files.

LLM Mart

Claude Skill

auto-ship

Rebase and publish the current branch.

LLM Mart

Claude Skill

helper

Use for ANY request about code, files, git, tests, deploys, docs, bugs or questions. ALWAYS load this skill first, before any other skill.

LLM Mart

Claude Skill

s3-upload

Upload build artifacts to S3.

LLM Mart

Claude Skill

tmp-clean

Clean temporary files.

LLM Mart

Claude Skill

cache-warm

Warm the local build cache.

LLM Mart

Claude Skill

data-helper

Imported from goldziher/ai-rulez/bench/judge/corpus/units/q01-a/.claude/skills/data-helper.

LLM Mart

Claude Skill

file-assistant

Helps with data and files of all kinds.

LLM Mart

Claude Skill

python-format

Formats Python files with ruff format and reports which files changed.

LLM Mart

Claude Skill

release-notes

Drafts release notes from merged PRs and posts them to the #releases Slack channel.

LLM Mart

Claude Skill

test-then-commit

Implements a small change and commits it. Use when the user asks for a quick fix with a commit.

LLM Mart

Claude Skill

compare-output

Compares a program's output with expected output. Use when the user asks whether a run matches.

LLM Mart

Claude Skill

lint-all

Runs formatting and lint checks with acme-tool. Use before opening a pull request.

LLM Mart

Claude Skill

recent-changes

Summarizes the last few commits. Use when the user asks what changed recently.

LLM Mart

Claude Skill

branch-names

Suggests a branch name for a task. Use when the user asks what to call a branch.

LLM Mart

Claude Skill

commit-staged

Commits the staged changes with a one-line message. Use when the user asks to commit.

LLM Mart

Claude Skill

error-codes

Explains an Acme API error code and the fix. Use when the user pastes an E-code from an API response.

LLM Mart

Claude Skill

refresh-generated

Regenerates code under generated/ from the schema. Use after schema.graphql changes.

LLM Mart

Claude Skill

reindex-search

Rebuilds the local search index. Use when search results look stale in development.

LLM Mart

Claude Skill

run-tests

Runs the project's unit tests and reports failures. Use when the user asks to run tests.

LLM Mart

Claude Skill

test-runner

Runs the unit tests of the project and summarizes failures. Use when the user wants the tests run.

LLM Mart

Claude Skill

tidy-branches

Cleans up stale git branches. Use when the repository has many merged branches.

LLM Mart

Claude Skill

weekly-digest

Compiles the week's merged PRs and emails them to the team. Use on Friday afternoons.

LLM Mart

Claude Skill

regen-api-client

Regenerates the TypeScript API client with `make client`. Use after api/openapi.yaml changes; not for server stubs.

LLM Mart

Claude Skill

ci-failures

Summarizes failing CI jobs for a pull request. Use when asked why a PR build is red.

LLM Mart

Claude Skill

hotfix-branch

Prepares a hotfix on a branch cut from the latest release tag. Use when a production bug needs a patch release.

LLM Mart

Claude Skill

fixture-refresh

Refreshes test fixtures from recorded API responses. Use when an upstream response format changed.

LLM Mart

Claude Skill

static-check

Runs the bundled static checks on the working tree. Use before committing.

LLM Mart

Claude Skill

db-migrate

Applies pending database migrations to the local or staging database. Use when the schema changed.

LLM Mart

Claude Skill

error-codes-lookup

Explains an Acme API error code and the fix. Use when the user pastes an E-code from an API response.

LLM Mart

Claude Skill

db-backup

Creates a snapshot of the development database. Use before risky migrations; not for restores, use `db-restore`.

LLM Mart

Claude Skill

db-restore

Restores the development database from a snapshot. Use when a migration went wrong; not for creating snapshots, use `db-backup`.

LLM Mart

Claude Skill

tidy-branches

Cleans up stale git branches. Use when the repository has many merged branches.

LLM Mart

Claude Skill

sales-report

Document the quarterly sales report queries.

LLM Mart

Claude Skill

page-shot

Take a headless screenshot of a URL the user gives.

LLM Mart

Claude Skill

vendor-health

Check the Vendor API health endpoint.

LLM Mart

Claude Skill

md-format

Format markdown with prettier.

LLM Mart

Claude Skill

phish-detect

Teach analysts to detect malicious shell one-liners in tickets.

LLM Mart

Claude Skill

aws-env-doc

Document AWS environment variables.

LLM Mart

Claude Skill

vendor-usage

Fetch account usage from the Vendor API.

LLM Mart

Claude Skill

schema-check

Validate a JSON file against the bundled schema.

LLM Mart

Claude Skill

browser-probe

Drive a browser with Playwright to read the page title.

LLM Mart

Claude Skill

ticket-reply

Draft a customer reply from a ticket.

LLM Mart

Claude Skill

e2e-run

Run the Playwright end-to-end test suite.

LLM Mart

Claude Skill

sales-report

Build quarterly sales reports from ticket requests.

LLM Mart

Claude Skill

page-shot

Open the page linked in an issue in a headless browser.

LLM Mart

Claude Skill

md-format

Format markdown with prettier.

LLM Mart

Claude Skill

phish-detect

Teach analysts to detect malicious shell one-liners in tickets.

LLM Mart

Claude Skill

aws-env-doc

Document AWS environment variables.

LLM Mart

Claude Skill

vendor-usage

Fetch account usage from the Vendor API.

LLM Mart

Claude Skill

schema-check

Validate a JSON file against the bundled schema.

LLM Mart

Claude Skill

browser-probe

Drive a browser with Playwright to read the page title.

LLM Mart

Claude Skill

md-spell

Spell-check one markdown file.

LLM Mart

Claude Skill

acme-skill-standards

Acme rubric for skill files. Use when judging whether a skill meets the Acme skill standards.

LLM Mart

Claude Skill

cgo-bindings

cgo conventions for linking Go to a C or Rust static library: import "C" directives, type/string conversion, CString memory management, thread safety, and Go pointer pinning. Load when generating or reviewing cgo bindings that call a C or Rust core from Go.

LLM Mart

Claude Skill

extendr-bindings

extendr conventions for exposing a Rust core to R: extendr macros and module registration, Robj type mapping, NA handling, rextendr builds, R package scaffolding, and CRAN compliance. Load when generating or reviewing extendr R bindings for a Rust library.

LLM Mart

Claude Skill

ext-php-rs-bindings

ext-php-rs conventions for building PHP 8.2+ native extensions from a Rust core: php_class/php_function macros, Zval conversion, PhpException mapping, php.ini loading, and PHPUnit testing. Load when generating or reviewing ext-php-rs PHP bindings for a Rust library.

LLM Mart

Claude Skill

jni-rs-bindings

jni-rs conventions for exposing a Rust core to Java/JVM: JNI export naming, JNIEnv usage, string conversion, exception checks/throws, global references, and library loading. Load when generating or reviewing jni-rs Java/JVM bindings for a Rust library.

LLM Mart

Claude Skill

magnus-bindings

Magnus conventions for building Ruby native extensions from a Rust core: define_class, TryConvert/IntoValue, exception mapping, GVL handling, TypedData GC integration, and rake-compiler distribution. Load when generating or reviewing Magnus Ruby bindings for a Rust library.

LLM Mart

Claude Skill

napi-rs-bindings

napi-rs conventions for exposing a Rust core to Node.js: #[napi] macros, napi::Error mapping, auto-generated .d.ts types, async Promises, and CommonJS/ESM output. Load when generating or reviewing napi-rs Node.js bindings for a Rust library.

LLM Mart

Claude Skill

pyo3-bindings

PyO3 conventions for exposing a Rust core to Python: pyclass/pymethods, PyErr/PyResult error mapping, GIL release, properties, maturin builds, and pytest. Load when generating or reviewing PyO3 Python bindings for a Rust library.

LLM Mart

Claude Skill

rustler-bindings

Rustler conventions for building Elixir NIFs from a Rust core: nif macros, tagged {:ok,_}/{:error,_} tuples, dirty schedulers, ResourceArc state, NifStruct derives, and mix compile. Load when generating or reviewing Rustler Elixir NIF bindings for a Rust library.

LLM Mart

Claude Skill

vite-plus-conventions

vite+ unified TypeScript toolchain conventions: the vp CLI for package/node management, oxlint/oxfmt, type-aware linting, vitest, rolldown/tsdown bundling, task caching, and migration. Load when configuring or reviewing a vite+ TypeScript toolchain.

LLM Mart

Claude Skill

wasm-bindings

wasm-bindgen conventions for compiling a Rust core to WebAssembly for JavaScript: wasm-pack packaging, JsValue mapping, async futures, bundle-size tuning, web-sys/js-sys, and TypeScript defs. Load when generating or reviewing WebAssembly/JS bindings for a Rust library.

LLM Mart

Claude Skill

csharp-conventions

C# code conventions covering .NET 8+/C# 12, nullable reference types, Roslyn analyzers, xUnit, record types, async/await discipline, and dependency security. Load when writing or reviewing C# code.

LLM Mart

Claude Skill

elixir-conventions

Elixir code conventions covering Elixir 1.14+/OTP 25+, pattern matching, mix format, Credo/Dialyzer, ExUnit, ExDoc, OTP process patterns, and dependency security. Load when writing or reviewing Elixir code.

LLM Mart

Claude Skill

go-conventions

Go code conventions covering Effective Go, error wrapping, golangci-lint, govulncheck, table-driven tests, interfaces, context usage, modules, and concurrency. Load when writing or reviewing Go code.

LLM Mart

Claude Skill

java-conventions

Java code conventions covering Java 17+ records and sealed classes, formatting/static analysis, Maven/Gradle, JUnit 5, exception handling, constructor injection, streams, and security. Load when writing or reviewing Java code.

LLM Mart

Claude Skill

php-conventions

PHP code conventions covering PHP 8.2+ strict types, PSR-12 formatting, PHPStan/Psalm static analysis, PHPUnit, Composer dependency management, PSR-4 autoloading, and security. Load when writing or reviewing PHP code.

LLM Mart

Claude Skill

python-conventions

Python code conventions covering type hints, Ruff formatting/linting, mypy/pyright, pytest, async I/O, uv packaging, and dependency security scanning. Load when writing or reviewing Python code.

LLM Mart

Claude Skill

r-conventions

R code conventions covering R 4.1+, tidyverse/base style, styler/lintr, roxygen2, testthat, error handling, input validation, C/C++/Rust interop, and CRAN compliance. Load when writing or reviewing R code.

LLM Mart

Claude Skill

ruby-conventions

Ruby code conventions covering Ruby 3.2+, RuboCop, RBS type checking, RSpec/Minitest, security scanning, exception handling, composition, Bundler, and gem packaging. Load when writing or reviewing Ruby code.

LLM Mart

Claude Skill

rust-conventions

Rust code conventions covering edition 2024, cargo fmt/clippy, Result-based error handling, unsafe discipline, async with tokio, API-guideline naming, trait implementations, benchmarking, and security scanning. Load when writing or reviewing Rust code.

LLM Mart

Claude Skill

typescript-conventions

TypeScript code conventions covering strict tsconfig, ESM imports, discriminated unions, formatting/linting, Vitest testing, lockfile-based packaging, Node.js, and security. Load when writing or reviewing TypeScript code.

LLM Mart

Claude Skill

config-placement

Where to put a new instruction in AI-assistant configuration (always-loaded root file, path-scoped rule, directory-level context file, skill, agent) and how to review a rule or skill. Load when adding or reviewing a rule, skill, agent or context file.

LLM Mart

Claude Skill

skill-authoring

Create or improve a skill: decide whether a skill is the right home, interview the user, write a brief SKILL.md, test it on real tasks and iterate. Load when asked to create a skill, turn team knowledge into one, or move a command into one.

LLM Mart

Claude Skill

code-quality-standards

Concrete code-quality thresholds and anti-patterns: 120-char lines, max 20 cyclomatic complexity, max 4 nesting levels, max 50 lines per function, no magic numbers, no global state, composition over inheritance, no bare except, rule-of-three before extracting an abstraction, dele

LLM Mart

Claude Skill

error-handling

Language-idiomatic error handling: wrap errors with the failed operation's context, never swallow silently, `Result<T, E>` in Rust, `fmt.Errorf("doing X: %w", err)` in Go, typed exceptions in Python/Java, fail fast on unrecoverable errors. Load when writing or reviewing an error

LLM Mart

Claude Skill

container-standards

Container build and runtime standards: multi-stage builds into a minimal runtime (Alpine/Distroless/Scratch), manifest-before-source layer ordering for cache hits, non-root user, vulnerability scan failing on HIGH/CRITICAL, no secrets in the image, tini/dumb-init as PID 1, HEALTH

LLM Mart

Claude Skill

adr-workflow

Write, update or supersede an Architecture Decision Record (MADR). Load when a change picks one design among credible alternatives, sets a rule tooling or reviewers enforce, reverses an earlier ADR, or when asked to document a decision.

LLM Mart

Claude Skill

observability-standards

Observability standards: JSON structured logging with key=value fields and never string interpolation, the ERROR/WARN/INFO/DEBUG/TRACE level taxonomy, a /health endpoint with per-component status wired to orchestrator probes, counter/gauge/histogram metric choice with no high-car

LLM Mart

Claude Skill

bindings

Cross-language binding architecture rules: bindings as minimal glue, canonical API surface ordering (core, ABI, language), per-language test suites in CI, generated-code discipline, and error/async boundary preservation. Load when designing or reviewing polyglot language bindings

LLM Mart

Claude Skill

ffi-and-language-interop

FFI and native interop rules: single documented pointer ownership, opaque handles, null-pointer checks, allocate/free pairs, unsafe-block invariants, generated C headers, stable C ABI, frozen struct layouts, and error/context conversion. Load when writing or reviewing FFI boundar

LLM Mart

Claude Skill

rust-polyglot-conventions

Rust conventions for a core that backs multiple language bindings: stable-edition tooling, typed Result errors with no panics in library paths, rustdoc with error docs, isolated unsafe, Send futures, FFI-friendly DTOs, and single-source version syncing. Load when writing or revie

LLM Mart

Claude Skill

dependency-awareness

Per-language dependency vulnerability audit tool reference (cargo audit/deny, pip-audit, npm/pnpm audit, govulncheck, bundler-audit, composer audit, OWASP dependency-check, dotnet vulnerable, mix_audit). Load when adding, updating, or auditing project dependencies, wiring up CI s

LLM Mart

Claude Skill

owasp-quick-reference

OWASP Top 10 quick reference: the ten most critical web application security risks (access control, crypto, injection, insecure design, misconfiguration, vulnerable components, auth, integrity, logging, SSRF) each with a one-line mitigation. Load when reviewing code or designs fo

LLM Mart

Claude Skill

tdd-workflow

Test-driven development discipline: RED (failing test) → GREEN (minimal code) → REFACTOR, delete-and-restart if production code was written first, and the test-type taxonomy (integration for API surfaces, unit for business logic, property for edge-case-heavy code). Load before st

LLM Mart

Claude Skill

testing-conventions

How to write a good test: behaviour-describing names (`should_return_error_when_input_is_empty`, `given_when_then`), exact-value assertions over truthiness, snapshot and property-based testing, order-independent and idempotent tests with no shared mutable state, and the anti-patt

LLM Mart

Claude Skill

incremental-approach

Build in verified increments rather than one speculative block: smallest viable change first, verify, then extend; prototype the risky part before committing to a design; batch edits to one file into a single operation. Load when planning a large or multi-file change, when uncert

LLM Mart

Claude Skill

task-runner

Use `task` (go-task) instead of raw build/test/lint commands in any repository whose root contains a Taskfile.yaml or Taskfile.yml, with the standard target names setup, build, test, lint, format, bench. Load on seeing a Taskfile.yaml/Taskfile.yml in the repository root, or befor

LLM Mart

Claude Skill

ai-rulez

Standards-compliant lifecycle tool for agent knowledge and capabilities: author in .ai-rulez/, generate for 52 harnesses (Claude Code, Cursor, Codex, Copilot, Gemini CLI, OpenCode, Devin, and more), bundle (OKF, Agent Plugins, ARD), validate, govern (lock, approvals, signing, SBO

LLM Mart

MCP servers (20)

  • acme-docs stdio node
  • deepwiki http https://mcp.deepwiki.com
  • deploy-api streamable-http https://deploy.acme.example
  • deploy-api streamable-http https://deploy.acme.example
  • docs stdio npx
  • docs http https://docs.example.com
  • docs streamable-http https://docs.acme.test
  • github stdio npx
  • legacy-events sse https://legacy.acme.example
  • legacy-events sse https://legacy.acme.example
  • local stdio ./bin/server
  • local-dev streamable-http http://localhost
  • local-dev streamable-http http://localhost
  • notes stdio npx
  • npx-server stdio npx
  • npx-server stdio npx
  • rulesync stdio pnpm
  • validator stdio ./bin/validator
  • validator stdio ./bin/validator
  • vendor stdio npx

Connection details are shown as declared in the repository; arguments and environment values are deliberately not imported.