feat: add tos evaluator skill#51
Merged
Merged
Conversation
Add a local-first Terms of Service evaluator that checks robots.txt, discovers legal pages, and optionally uses a low-cost LLM to interpret ambiguous automation restrictions. Sync the new skill with docs, examples, and focused tests so it integrates cleanly with Skillware. Made-with: Cursor
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Adds a new
compliance/tos_evaluatorskill that performs a local-first compliance check before automated website access.The skill evaluates
robots.txt, discovers likely legal/terms pages, extracts and scores relevant clauses for the requested action, and optionally uses a low-cost LLM fallback (gemini-2.5-flash-liteas example) for ambiguous policy language.This change also synchronizes repository surfaces so the skill is production-ready in Skillware:
manifest.yaml,skill.py,instructions.md,card.json,__init__.py, localtest_skill.py)tests/skills/compliance/test_tos_evaluator.pyType of Change (Matches Issue Templates)
manifest.yaml,skill.py, andinstructions.md)base_skill.py,loader.py, etc.)Checklist (For the Submitting Agent / Developer)
manifest.yaml(if submitting a new skill).env_varsare explicitly documented in the manifest.SkillLoadersuccessfully loads this module without missing dependency errors.Constitution & Safety (If adding/modifying a Skill)
This skill is evaluation-only and does not execute scraping/crawling actions itself.
It applies conservative decisioning (
SAFE,UNSAFE,CAUTION,INSUFFICIENT_EVIDENCE) and prioritizes caution when legal evidence is incomplete or ambiguous.It does not claim legal certainty or legal advice, and only sends clause snippets to an external model when explicitly enabled via
use_llm_evaluator.Related Issues
Fixes #40