Policy Lawyer

Reference the workspace policy playbook, answer "What are the rules for tone, data, and collaboration?" by searching the curated policy doc or listing its sections.

Security Scan

The skill's code, instructions, and requirements are consistent with a small CLI that reads and searches a local policies.md — it does what it says and does not request extra credentials or perform network/exfiltration actions.

Purpose & Capability

Name/description (reference workspace policy playbook) matches the included CLI and policies.md. The script only implements listing sections, showing a topic, and keyword search — all aligned with the stated purpose.

Instruction Scope

SKILL.md and the CLI only read a specified policy file and print sections/snippets. The optional --policy-file parameter lets you point to another policy document (local path) which is reasonable for comparing workspaces; the skill does not instruct the agent to read arbitrary system credentials or unrelated files.

Install Mechanism

There is no install spec (instruction-only skill with bundled scripts). No downloads or package installs are performed — the script runs with the local Python interpreter.

Credentials

The skill requires no environment variables, credentials, or config paths. All file I/O is limited to the provided policy file path, which is proportional to the task.

Persistence & Privilege

always is false and the skill does not request persistent system presence or modify other skill configurations. It runs on-demand and does not store agent-wide settings.

Assessment

This skill is coherent and low-risk: it only reads and prints sections from a markdown policy file. Before installing, confirm you are comfortable allowing the agent to read any local path you might pass via --policy-file (do not point it at sensitive files). Review the bundled references/policies.md to ensure the content is appropriate for your workspace. If you plan to allow autonomous invocation, be aware the skill could be asked to read a policy file path the agent has access to — restrict filesystem permissions accordingly.

Overview

policy-lawyer is built around the curated policy notebook at references/policies.md. The CLI (scripts/policy_lawyer.py) lets you:

• --list-topics to list every policy heading.
• --topic <name> to show the section that matches a topic (case-insensitive).
• --keyword <term> to search all policies for a given keyword.
• --policy-file <path> to point at a different policy document when comparing workspaces.

Use this skill when you need to remind yourself of the community standards before drafting announcements or when a question lands that needs an authoritative policy quote.

CLI usage

• python3 skills/policy-lawyer/scripts/policy_lawyer.py --list-topics prints every section defined under ## <Section Name> in the policy reference.
• --topic "Tone" prints the tone guidelines exactly as written so you can quote them during calm reminders.
• --keyword security (or any other keyword) shows the matching lines across all sections so you can quickly see where that topic is governed.
• Supply --policy-file /path/to/repo/references/policies.md when you want to interrogate a copy of the playbook from another workspace.

Sample commands

python3 skills/policy-lawyer/scripts/policy_lawyer.py --topic Tone
python3 skills/policy-lawyer/scripts/policy_lawyer.py --keyword data --policy-file ../other-workspace/references/policies.md

The first command prints the tone section; the second searches for "data" inside another workspace's policies and prints each matching snippet.

References

• references/policies.md is the curated policy playbook that lists tone, data, collaboration, and security rules.

Resources

• GitHub: https://github.com/CrimsonDevil333333/policy-lawyer
• ClawHub: https://www.clawhub.ai/skills/policy-lawyer