SKILLEMALL.ai
GitHub ↗ RU Sign in

FD hatchling

Provides Hatchling build backend guidance for Python packaging — use when configuring pyproject.toml metadata, build targets (wheel, sdist, binary), file selection with git-style globs, build hooks, metadata hooks, version management (code/regex/env sources), editable installs, the hatch-vcs plugin, plugin development, build environment setup (UV/pip/Cython), setuptools migration, or troubleshooting Hatchling errors. Covers PEP 517/518/621/660 standards and context variable interpolation.

Not recommendedcritical or high security findings · low grade F
Jamie-BitFlight/claude_skills Agent Skills author: Jamie-BitFlight MIT 80 files body ≈ 985 tokens Open the sourcegithub.com↗ analyzed 8 d ago

Provides Hatchling build backend guidance for Python packaging — use when configuring pyproject.toml metadata, build targets (wheel, sdist, binary), file…

As a process D 35/100 · Unfinished process — References files that are not bundled: references/project-metadata/index.md, references/wheel-target/index.md, references/sdist-target/index.md

GeneratorSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
F
27/100
safety, quality, tests
Safety 60%
0
Quality 40%
68
Run on models
none yet
Process rating
D
35/100
Unfinished process
References files that are not bundled: references/project-metadata/index.md, references/wheel-target/index.md, references/sdist-target/index.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 22

  • high Dangerous commands cmd-install-from-url references/build-environment/environment-isolation.md:247
    Installs a package from an untrusted URL / archive
    RUN pip install /tmp/*.whl && rm /tmp/*.whl
  • high Dangerous commands cmd-install-from-url references/build-environment/environment-isolation.md:286
    Installs a package from an untrusted URL / archive
    pip install dist/*.whl
  • high Dangerous commands cmd-install-from-url references/build-environment/environment-isolation.md:312
    Installs a package from an untrusted URL / archive
    - pip install dist/*.whl
  • high Dangerous commands cmd-install-from-url references/build-system/dev-mode.md:389
    Installs a package from an untrusted URL / archive
    pip install dist/*.whl
  • high Dangerous commands cmd-pipe-to-shell references/build-targets/binary-builder.md:299
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
  • high Dangerous commands cmd-install-from-url references/cli-building/building-sdist.md:284
    Installs a package from an untrusted URL / archive
    pip install dist/*.tar.gz
  • high Dangerous commands cmd-install-from-url references/cli-building/local-install.md:199
    Installs a package from an untrusted URL / archive
    pip install dist/*.whl
  • high Dangerous commands cmd-install-from-url references/cli-building/output-customization.md:301
    Installs a package from an untrusted URL / archive
    pip install $(BUILD_DIR)/test/*.whl
  • high Dangerous commands cmd-install-from-url references/cli-building/output-customization.md:402
    Installs a package from an untrusted URL / archive
    pip install build/test/*.whl
  • high Dangerous commands cmd-install-from-url references/core-concepts/development-vs-distribution.md:210
    Installs a package from an untrusted URL / archive
    pip install dist/mypr…whl
  • high Dangerous commands cmd-install-from-url references/core-concepts/development-vs-distribution.md:223
    Installs a package from an untrusted URL / archive
    pip install dist/mypr….gz
  • high Dangerous commands cmd-install-from-url references/core-concepts/development-vs-distribution.md:413
    Installs a package from an untrusted URL / archive
    test_env/bin/pip install dist/*.whl
  • high Dangerous commands cmd-install-from-url references/core-concepts/development-vs-distribution.md:417
    Installs a package from an untrusted URL / archive
    test_env/bin/pip install dist/*.tar.gz
  • high Dangerous commands cmd-install-from-url references/core-concepts/wheel-vs-sdist.md:49
    Installs a package from an untrusted URL / archive
    pip install mypr…whl
  • high Dangerous commands cmd-install-from-url references/core-concepts/wheel-vs-sdist.md:83
    Installs a package from an untrusted URL / archive
    pip install mypr….gz
  • high Dangerous commands cmd-install-from-url references/core-concepts/wheel-vs-sdist.md:184
    Installs a package from an untrusted URL / archive
    # Anyone can install with: pip install mypr…whl
  • high Dangerous commands cmd-install-from-url references/core-concepts/wheel-vs-sdist.md:499
    Installs a package from an untrusted URL / archive
    pip install dist/*.whl
  • high Dangerous commands cmd-install-from-url references/error-handling/build-validation.md:393
    Installs a package from an untrusted URL / archive
    pip install dist/*.whl
Medium and low: 4
  • medium Dangerous commands cmd-privilege references/build-system/output-directory.md:273
    Privilege escalation / world-writable permissions
    sudo chown $USER:$USER dist/
  • medium Dangerous commands cmd-install-from-url references/cli-building/building-all-targets.md:348
    Installs a package from an untrusted URL / archive (detector / deny-list definition)
    2. **Test installation from both formats**: `pip install dist/*.tar.gz` and `pip install dist/*.whl`
    detector
  • low Exfiltration read-dotenv references/build-system/environment-variables.md:350
    Reads a .env file
    source .env.development
  • low Exfiltration read-dotenv references/build-system/environment-variables.md:364
    Reads a .env file
    source .env.production

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/project-metadata/index.md
  • warning missing-ref reference to a missing file: references/wheel-target/index.md
  • warning missing-ref reference to a missing file: references/sdist-target/index.md
  • warning missing-ref reference to a missing file: references/target-config/index.md
  • warning missing-ref reference to a missing file: references/file-selection/index.md
  • warning missing-ref reference to a missing file: references/version-management/index.md
  • warning missing-ref reference to a missing file: references/metadata-hooks/index.md
  • warning missing-ref reference to a missing file: references/plugins/index.md
  • warning missing-ref reference to a missing file: references/integration/index.md
  • warning missing-ref reference to a missing file: references/special-config/index.md
  • warning missing-ref reference to a missing file: references/standards/index.md
  • warning missing-ref reference to a missing file: references/release-notes/index.md
  • note edit-residue the text marks something as outdated (lines 6, 31): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: references/project-metadata/index.md, references/wheel-target/index.md, references/sdist-target/index.md
  • 0Tools and files. 12 referenced file(s) missing: references/project-metadata/index.md, references/wheel-target/index.md, references/sdist-target/index.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Steps. 27 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 985 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 493: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 27 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.