Agent skill

Specx Project Tooling

by maksimzayats in maksimzayats/specx

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

MITAuto-check passedDevelopment

Install Specx Project Tooling

skills CLI
$ npx skills add maksimzayats/specx --skill specx-project-tooling -a claude-code

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

GitHub CLI
$ gh skill install maksimzayats/specx specx-project-tooling --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/maksimzayats/specx.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/specx-project-tooling .claude/skills/specx-project-tooling && 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
specx-project-tooling
GitHub stars
202
Token cost
~965 tokens
SKILL.md length
474 words
Files
3 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 12 steps: Use specx init for the fresh… → Preserve the repo's Python version if it… → Use uv metadata in pyproject.toml. → …
  • Updating pyproject.toml
  • SKILL.md covers Workflow, Guardrails, Code Style and References
  • Calls uv

What it does

Specx Project Tooling is an agent skill from maksimzayats/specx. Add strict Python project tooling for a specx service. Use when creating or updating pyproject.toml, uv dependency groups and lock checks, Ruff formatting and linting, mypy strict mode, pytest and HTTPX2 test configuration, Makefile commands, root AGENTS.md command guidance, or CI-like local guardrails.

Its SKILL.md is about 970 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/tooling.md`).

It sits in Development, covering Linting and formatting, Unit testing and Type safety. It works with Python, Ruff and pytest. The repository describes itself as: ⚙️ Executable architecture guardrails and agent skills for building structured Python services! The licence is MIT.

When your agent uses it

  • Updating pyproject.toml
  • Uv dependency groups and lock checks
  • Ruff formatting and linting
  • Mypy strict mode

Example prompts

  • “/specx-project-tooling”

Requirements

  • Python 3
  • Docker

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. Use specx init for the fresh framework-neutral baseline. It renders
  2. Preserve the repo's Python version if it already exists. For a new repo,
  3. Use uv metadata in pyproject.toml.
  4. For a new project, verify current compatible releases against the official
  5. Add runtime dependencies only for real runtime features. For a starter API,
  6. Add dev dependencies for pytest, Ruff, mypy, HTTP testing, and ASGI lifespan
  7. Keep mypy strict. Do not enable the DIWire mypy plugin for constructor-field
  8. Enable select = ["ALL"] for Ruff in new projects. Ignore only formatter
  9. Generate [tool.specx] with select = ["ALL"] so every applicable built-in
  10. Add simple Makefile targets: check, format, lint, test, and dev
  11. If SQLAlchemy adapters exist, add Alembic dependency/config and
  12. When adding or changing Makefile targets, update root AGENTS.md Commands

What it can do on your machine

Read from SKILL.md and the folder at commit 9362406. 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

Specx Project Tooling loads about 965 tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 474 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~965
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.3k

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 maksimzayats/specx at commit 9362406, republished under its MIT licence (© maksimzayats). 474 words, ~965 tokens.

Download SKILL.mdSave it as .claude/skills/specx-project-tooling/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
specx-project-tooling
description
Add strict Python project tooling for a specx service. Use when creating or updating `pyproject.toml`, `uv` dependency groups and lock checks, Ruff formatting and linting, mypy strict mode, pytest and HTTPX2 test configuration, Makefile commands, root `AGENTS.md` command guidance, or CI-like local guardrails.

specx Project Tooling

Use this skill to make the repository executable and checkable. Read references/tooling.md before editing tooling files.

Workflow

  1. Use specx init <path> for the fresh framework-neutral baseline. It renders the canonical pyproject.toml, Makefile, .python-version, health core/IOC scaffold, mirrored unit tests, and root guidance, then runs uv add specx diwire and uv add --dev mypy pytest ruff unless --no-sync is passed. Let uv select and record compatible releases rather than rendering dependency floors.
  2. Preserve the repo's Python version if it already exists. For a new repo, default to Python 3.14. The initializer accepts any major.minor value; do not hardcode a release allowlist that blocks future Python versions.
  3. Use uv metadata in pyproject.toml.
  4. For a new project, verify current compatible releases against the official package indexes and documentation before copying reference floors. Preserve intentional versions in an existing repo unless the user asks to upgrade.
  5. Add runtime dependencies only for real runtime features. For a starter API, include specx, FastAPI, diwire, pydantic-settings, and Uvicorn.
  6. Add dev dependencies for pytest, Ruff, mypy, HTTP testing, and ASGI lifespan testing when there is a FastAPI app.
  7. Keep mypy strict. Do not enable the DIWire mypy plugin for constructor-field injection; it is only needed if an existing project intentionally uses resolver_context.inject function wrappers.
  8. Enable select = ["ALL"] for Ruff in new projects. Ignore only formatter conflicts and deliberate file-category conventions, and put a concise comment describing what each ignored rule checks beside its code.
  9. Generate [tool.specx] with select = ["ALL"] so every applicable built-in guardrail is explicit. Missing technology surfaces are skipped for ALL; explicit technology selectors still warn when their surface is absent.
  10. Add simple Makefile targets: check, format, lint, test, and dev when there is a FastAPI delivery app. lint runs Ruff, mypy, and uv run --locked specx check; do not create separate guardrails or lock-check targets.
  11. If SQLAlchemy adapters exist, add Alembic dependency/config and migrate/makemigrations targets with $specx-sqlalchemy-migrations.
  12. When adding or changing Makefile targets, update root AGENTS.md Commands so coding agents run the right project commands.
  13. Use locked execution for non-mutating validation commands.
  14. Run the smallest useful checks after changing tooling.
Show full SKILL.md (112 more words)Show less

Guardrails

  • Do not add heavyweight services such as Docker, Alembic, Redis, or PostgreSQL unless the repo has code that uses them.
  • Once a SQLAlchemy adapter exists, Alembic is required. Do not use metadata.create_all as a replacement for migrations.
  • Do not split linting rules across many files unless the project already does.
  • Keep commands copyable and non-interactive.
  • Keep AGENTS.md command guidance aligned with the actual Makefile. Do not list migration commands before SQLAlchemy/Alembic exists.

Code Style

Use blank lines as logical separators in all code. Keep related statements together, but separate independent setup, action, assertion, response, branch, and transformation groups so long blocks stay readable.

References

  • references/tooling.md - recommended pyproject.toml, Makefile, and command patterns.

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

Files

SKILL.md and 2 other files (references) in skills/specx-project-tooling of maksimzayats/specx.

  • SKILL.md
  • agents/openai.yaml
  • references/tooling.md

Open the folder on GitHubat commit 9362406

Compare with similar skills

Specx Project Tooling 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.

Specx Project Tooling compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Specx Project Tooling this skillmaksimzayats/specx202—~965Automated safety check: PassMIT
Kedro Babysitkedro-org/kedro11k—~4kAutomated safety check: PassCustom licence
Modern Pythonantoinebou12/uml-mcp105—~1kAutomated safety check: PassMIT
Pythonalinaqi/maggy707—~1.1kAutomated safety check: PassMIT
Python ProJeffallan/claude-skills12k—~1.6kAutomated safety check: PassMIT
Pythonericrisco/rsc-harness180—~3.8kAutomated 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
  • Modern Python

    antoinebou12/uml-mcp

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

    105 GitHub stars~1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Python

    alinaqi/maggy

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

    707 GitHub stars~1.1k tokensUpdated 16 days ago
    DevelopmentAuto-check passed
  • Python Pro

    Jeffallan/claude-skills

    Writes type-annotated Python 3.11+ with async patterns, dataclasses and pytest suites, validated with mypy in strict mode, black and ruff.

    12k GitHub stars~1.6k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Python

    ericrisco/rsc-harness

    A skill your agent uses when the task is Python itself, in any framework or none: PEP 695 generics, mypy --strict typing, dataclass/Protocol/TypedDict/Enum choices, asyncio.TaskGroup, stdlib idioms…

    180 GitHub stars~3.8k tokensUpdated yesterday
    Backend & APIsAuto-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 5 days ago
    Testing & QAAuto-check passed

More from maksimzayats/specx

All 12 skills in this repo
  • Specx Add Core Service

    maksimzayats/specx

    Add or refactor a specx core scope service. An agent skill from maksimzayats/specx.

    202 GitHub stars~688 tokensUpdated 2 mo ago
    Auto-check passed
  • Specx Add Core Use Case

    maksimzayats/specx

    Add or refactor a specx core scope use case. An agent skill from maksimzayats/specx.

    202 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Add delivery controllers for specx services, especially FastAPI HTTP routes.

    202 GitHub stars~704 tokensUpdated 2 mo ago
    Auto-check passed
  • Add technical infrastructure adapters for specx core scopes.

    202 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed
  • Design or review specx core scope boundaries in Python services.

    202 GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed
  • Specx Diwire Composition

    maksimzayats/specx

    Wire dependency injection for a specx Python service with diwire.

    202 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Specx Project Tooling

What does Specx Project Tooling do?

Add strict Python project tooling for a specx service. An agent skill from maksimzayats/specx. Specx Project Tooling is an agent skill from maksimzayats/specx. Add strict Python project tooling for a specx service.

When should I use Specx Project Tooling?

Specx Project Tooling fits situations like: updating pyproject.toml; uv dependency groups and lock checks; ruff formatting and linting; mypy strict mode.

How do I install Specx Project Tooling in Claude Code?

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

How do I install Specx Project Tooling in Codex?

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

Can I use Specx Project Tooling 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 maksimzayats/specx --skill specx-project-tooling -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/specx-project-tooling, .gemini/skills/specx-project-tooling, .github/skills/specx-project-tooling and .opencode/skills/specx-project-tooling in your project.

What does Specx Project Tooling need to run?

Going by SKILL.md and its folder, Specx Project Tooling needs the command-line tools its instructions call (uv). Our summary lists: Python 3; Docker.

Does Specx Project Tooling 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 Specx Project Tooling 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 Specx Project Tooling use?

Specx Project Tooling is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Specx Project Tooling use?

About 965 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Specx Project Tooling?

Skills that share tags, products or a category with Specx Project Tooling: Kedro Babysit (kedro-org/kedro, 11k stars), Modern Python (antoinebou12/uml-mcp, 105 stars), Python (alinaqi/maggy, 707 stars) and Python Pro (Jeffallan/claude-skills, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Specx Project Tooling?

maksimzayats (a GitHub user) maintains it in maksimzayats/specx, which has 202 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on August 8, 2026.

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