New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Gate

by guardana in guardana/guardana

Run this project's verification — the full local CI mirror (ruff, mypy, import contract, pytest with PostgreSQL, coverage floors, dogfood, generated docs and site, the isolated example suites, the…

Apache-2.0Auto-check passedTesting & QA

Install Gate

skills CLI
$ npx skills add guardana/guardana --skill gate -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install guardana/guardana gate --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/guardana/guardana.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/gate .claude/skills/gate && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gate
GitHub stars
129
Token cost
~776 tokens
SKILL.md length
349 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run this project's verification — the full local CI mirror (ruff, mypy, import contract, pytest with PostgreSQL, coverage floors, dogfood, generated docs and site, the isolated example suites, the…

  • Tasks that involve Unit testing
  • SKILL.md covers While iterating — scoped,…, Before every commit — the…, Before a tag and Report
  • Calls uv
  • Tasks that involve Linting and formatting

What it does

Gate is an agent skill from guardana/guardana. Run this project's verification — the full local CI mirror (ruff, mypy, import contract, pytest with PostgreSQL, coverage floors, dogfood, generated docs and site, the isolated example suites, the setup checks), a scoped subset, or a fast run that marks the slow jobs NOT RUN — and read the verdict lines. Use while iterating (scoped) and always before a commit (full).

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Unit testing, Linting and formatting and Type safety. It works with PostgreSQL, pytest and Ruff. The repository describes itself as: Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Unit testing
  • Tasks that involve Linting and formatting
  • Tasks that involve Type safety

Example prompts

  • “/gate”

Requirements

  • Docker

What it can do on your machine

Read from SKILL.md and the folder at commit ae7ee8b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gate loads about 776 tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 349 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~776

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from guardana/guardana at commit ae7ee8b, republished under its Apache-2.0 licence (© guardana). 349 words, ~776 tokens.

Download SKILL.mdSave it as .claude/skills/gate/SKILL.md (or your agent's skills folder).
name
gate
description
Run this project's verification — the full local CI mirror (ruff, mypy, import contract, pytest with PostgreSQL, coverage floors, dogfood, generated docs and site, the isolated example suites, the setup checks), a scoped subset, or a fast run that marks the slow jobs NOT RUN — and read the verdict lines. Use while iterating (scoped) and always before a commit (full).
argument-hint
[full | release | one <path::test> | <paths>]

Gate — prove it is green

Requested: $ARGUMENTS (nothing = full).

While iterating — scoped, seconds

bash
uv run pytest <path>[::test] -q                  # one file or one test; --cov stays off on purpose
uv run ruff check <paths> && uv run ruff format <paths>
uv run mypy --strict <paths>
uv run guardana rule test <rule-id>              # a rule's positive, negative and inconclusive fixtures

A scoped run is what green looks like right up until CI disagrees: failures live in packages nobody touched, and a rule change moves docs/generated/ (regenerate, do not edit).

Before every commit — the whole thing

bash
scripts/ci_local.sh --quiet          # --fast skips the slow jobs (reported NOT RUN); --skip-audit when offline

One line per gate; a red gate prints its last 40 lines and the full log sits in cache/ci/. It runs every job of .github/workflows/ci.yml — the locked sync, lint, types, the import contract, pytest with PostgreSQL, the coverage floors, uv audit, the dogfood scan, the four generated-truth checks, the isolated example suites, the clean-install check, the SBOM check and the image smoke — plus two local-only gates CI has no job for: the ops catalogue (scripts/check_ops_catalogue.py) and the agent setup (scripts/check_claude_setup.py). --fast leaves out the three slow jobs and reports them as NOT RUN, so a fast run is never called green. For a long run hand the command to runner and keep working.

What the script does so you do not have to remember it: deletes .ruff_cache and __pycache__ (both have answered for changed files before), starts the PostgreSQL from deploy/docker-compose.dev.yml and sets GUARDANA_REQUIRE_POSTGRES=1 so the collector's tests cannot skip, runs the example suites with --no-cache (a cached wheel hides exactly the data files an extension change touches), and reports any gate it could not run as NOT RUN with exit 1. A skipped gate is not a passing gate; say which ones did not run and why.

Read the verdict lines themselves — pytest's N passed, M skipped, mypy's Success: no issues / Found N errors, Contracts: N kept, in sync, is current. Red for a reason that is not yours → say so in the commit message. Never push past it silently.

Before a tag

The same command, without --fast: the clean-install check (five distributions in an empty venv, the documented commands), the SBOM check and the image smoke are part of every run. release.py runs its own gate again before it bumps anything.

Report

Per gate: ✓/✗/– and the verdict line verbatim. Anything you did not run, name it as NOT RUN.

© guardana, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/gate of guardana/guardana.

Open the folder on GitHubat commit ae7ee8b

Compare with similar skills

Gate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gate this skillguardana/guardana129—~776Automated safety check: PassApache-2.0
Kedro Babysitkedro-org/kedro11k—~4kAutomated safety check: PassCustom licence
Checkav1155/houndarr292—~366Automated safety check: PassAGPL-3.0
Validatejuliepy/AI-Engineer-from-scrach433—~500Automated safety check: PassNone
Modern Pythonantoinebou12/uml-mcp105—~1kAutomated safety check: PassMIT
Specx Project Toolingmaksimzayats/specx202—~965Automated safety check: PassMIT

Similar skills

  • Kedro Babysit

    kedro-org/kedro

    Run Kedro's local lint / format / type-check / tests on changed files (uses the project's pre-commit hooks, ruff, mypy, pytest, lint-imports, detect-secrets, Make targets — in the right venv), or…

    11k GitHub stars~4k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Check

    av1155/houndarr

    Run Houndarr's full quality gate (ruff lint, ruff format check, mypy, bandit, pytest) and report results in a single table.

    292 GitHub stars~366 tokensUpdated 3 days ago
    Testing & QAAuto-check passed

  • Validate

    juliepy/AI-Engineer-from-scrach

    Run the full quality gate (ruff + mypy + pytest + tsc + vitest) and report PASS/FAIL for each command.

    433 GitHub stars~500 tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

  • Modern Python

    antoinebou12/uml-mcp

    Modern Python tooling and best practices using uv, ruff, ty, and pytest.

    105 GitHub stars~1k tokensUpdated today
    DevelopmentAuto-check passed

  • Specx Project Tooling

    maksimzayats/specx

    Add strict Python project tooling for a specx service. An agent skill from maksimzayats/specx.

    202 GitHub stars~965 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed

  • Python

    alinaqi/maggy

    Python development with ruff, mypy, pytest - TDD and type safety

    707 GitHub stars~1.1k tokensUpdated 14 days ago
    DevelopmentAuto-check passed

More from guardana/guardana

All 16 skills in this repo

  • Content Model

    guardana/guardana

    Route wording work to GPT (codex CLI) or Gemini (agy CLI) instead of writing it with Claude — landing-page copy, a readability rewrite of a README or docs page, attack and judge prompts for a rule…

    129 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Ship

    guardana/guardana

    Commit and push a finished change the way this repo requires — explicit paths, one commit per logical change, no attribution, the five documentation places answered, the site checks before a push (a…

    129 GitHub stars~836 tokensUpdated yesterday
    Auto-check: notes

  • Add A Rule

    guardana/guardana

    Add security coverage to Guardana the way this repository requires — as a rule, evaluator or target, never by patching the engine — with the fixtures, the framework mapping and the documentation…

    129 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Auto

    guardana/guardana

    Autonomous, non-interactive run of the whole lifecycle for one development task — size, plan, build, gate, review, fix, commit — without stopping for questions.

    129 GitHub stars~792 tokensUpdated yesterday
    Auto-check passed

  • Docs

    guardana/guardana

    Documentation work in this repo — the five places a user-visible change must answer, the page conventions the site build enforces, the tests that pin prose to the registry, and a simplification pass…

    129 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

  • False Green Audit

    guardana/guardana

    Hunt for the failure this project exists to prevent — code that compiles, types, tests green, and quietly reports "all clear" about something it never examined.

    129 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Gate

What does Gate do?

Run this project's verification — the full local CI mirror (ruff, mypy, import contract, pytest with PostgreSQL, coverage floors, dogfood, generated docs and site, the isolated example suites, the…. Gate is an agent skill from guardana/guardana. Run this project's verification — the full local CI mirror (ruff, mypy, import contract, pytest with PostgreSQL, coverage floors, dogfood, generated docs and site, the isolated example suites, the setup checks), a scoped subset, or a fast run that marks the slow jobs NOT RUN — and read the verdict lines.

When should I use Gate?

Gate fits situations like: tasks that involve Unit testing; tasks that involve Linting and formatting; tasks that involve Type safety.

How do I install Gate in Claude Code?

Run `npx skills add guardana/guardana --skill gate -a claude-code`. Or copy the skill folder (.claude/skills/gate in guardana/guardana) into .claude/skills/gate in your project. Claude Code loads it when a task matches its description.

How do I install Gate in Codex?

Run `npx skills add guardana/guardana --skill gate -a codex`. Or copy the skill folder (.claude/skills/gate in guardana/guardana) into .agents/skills/gate in your project. Codex loads it when a task matches its description.

Can I use Gate in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add guardana/guardana --skill gate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gate, .gemini/skills/gate, .github/skills/gate and .opencode/skills/gate in your project.

What does Gate need to run?

Going by SKILL.md and its folder, Gate needs the command-line tools its instructions call (uv). Our summary lists: Docker.

Does Gate access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Gate safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gate use?

Gate is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gate use?

About 776 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gate?

Skills that share tags, products or a category with Gate: Kedro Babysit (kedro-org/kedro, 11k stars), Check (av1155/houndarr, 292 stars), Validate (juliepy/AI-Engineer-from-scrach, 433 stars) and Modern Python (antoinebou12/uml-mcp, 105 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gate?

guardana (a GitHub organization) maintains it in guardana/guardana, which has 129 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 7, 2026.

Source: guardana/guardana on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.