CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

managing-python-dependencies

Ensures proper Python dependency management, avoiding global `pip install` and adhering to project-specific tooling. Use this skill if any of the following are true: 1. Attempting to run `pip install {package_name}`. 2. Python packages or dependencies need to be added or modified. 3. Initiating a new Python project. 4. Creating a new notebook, even if just using BigQuery cells. 5. Generating Python code that includes `import` statements for third-party libraries. 6. Before executing Python scripts via the terminal to ensure the correct virtual environment is active.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Excellent actionable content: a priority-ordered detection table with exact per-tool commands, a complete venv fallback, and explicit prohibitions, all with no padding. The only gaps are minor repetition of the venv+pip commands and the absence of any validation step confirming the detected manager or active environment.

Suggestions

Consolidate the venv+pip install/setup commands: make detection items 5 and 6 reference the 'Default: venv + pip' section instead of repeating the same commands a third time.

Add a lightweight verification step, e.g., confirm the detected manager's lockfile/config changed after install, or verify the active interpreter with '.venv/bin/python -c "import <package>"' before reporting success.

Cover the description's trigger 6 in the body: a short note on how to check which virtual environment is active before executing Python scripts would close the loop between stated purpose and content.

DimensionReasoningScore

Conciseness

Lean body with zero concept explanations and direct commands throughout. Not 5 because the venv+pip install/setup commands are repeated three times (detection items 5 and 6, the Default code block, and the rules list) and could be consolidated; not 3 since there is no unnecessary explanation, only minor redundancy.

4 / 5

Actionability

Fully executable, copy-paste-ready commands for every dependency manager ('uv add <package>', 'poetry add <package>', 'pipenv install <package>', 'conda install <package>', '.venv/bin/pip install <package>') plus a complete venv initialization block ('python3 -m venv .venv', '.venv/bin/pip freeze > requirements.txt'), covering all common cases.

5 / 5

Workflow Clarity

The detection-then-install sequence is clear with an explicit priority order and default fallback. Not 5 because there is no verification checkpoint (e.g., confirming the detected manager or that the correct venv is active before/after installing); not 3 because the priority-ordered decision procedure resolves ambiguity well.

4 / 5

Progressive Disclosure

A short (~45 non-blank line), single-file skill with well-organized sections (caution, detection, default, prohibited) and no content that belongs in separate files; no bundle files exist, so per the simple-skill guidance well-organized sections alone merit full credit.

5 / 5

Total

18

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit what/when structure and an unusually well-enumerated trigger list of six concrete scenarios. Trigger vocabulary is natural and domain-specific, with only minor gaps in synonym/tool-name coverage and slight breadth in the 'before executing Python scripts' trigger.

DimensionReasoningScore

Specificity

Names concrete behaviors ('avoiding global `pip install`', 'adhering to project-specific tooling') and concrete trigger scenarios like 'Attempting to run `pip install {package_name}`'. Falls short of 5 because it never enumerates the skill's actual capabilities (detecting uv/Poetry/Pipenv/Conda signals and running matching commands), and exceeds 3 which requires only 1-2 concrete actions.

4 / 5

Completeness

Explicitly answers both: 'what' ('Ensures proper Python dependency management, avoiding global `pip install` and adhering to project-specific tooling') and 'when' via an explicit 'Use this skill if any of the following are true:' clause with six numbered concrete triggers, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Covers natural user phrases well: 'pip install', 'Python packages or dependencies need to be added or modified', 'new Python project', 'import statements for third-party libraries', 'virtual environment'. Not 5 because common variations users say are missing — e.g., tool names (poetry, uv, conda) or 'requirements.txt'.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Python dependency management) with distinct triggers tied to pip/package/project/venv language. Not 5 because trigger 6 ('Before executing Python scripts via the terminal') and the notebook trigger create minor overlap with general Python-execution or notebook skills.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

saski/arnesto

Path

.agents/skills/managing-python-dependencies/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.