Simplify skill: trust the agent, keep the engine - #4
Merged
Conversation
Cuts SKILL.md from 569 to ~60 lines by removing defensive prose that capable agents handle naturally: - Trust boundary / anti-sunk-cost / engine substitution rules - Phase 7 multi-turn revision tables - Input sanity bounds - 15+ failure-mode subsections - Mandatory 6-cell scenario matrix - Pseudocode clarify loop Kept: deterministic engine contract, live fetch URLs, three hard rules, one example payload per subcommand, MoE / infeasible / api_wins / quality notes. calc.py still enforces input validation and honest infeasible output.
Drop extraction-hint paragraphs, confidence-when-defaulted column, and validation-errors section. The engine's exit-2 JSON is already self-describing; extraction hints are agent common sense.
5-step workflow (not 6), correct scripts/calc.py path in file list, drop 6-cell matrix claim.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Removes defensive prose that capable agents handle naturally. Keeps the deterministic engine and its tests untouched.
Before / after
Commits
scripts/calc.pypath, drop 6-cell matrix language.Bets
calc.pywhen inputs change.scripts/calc.pystill rejects bad input with exit 2.If something regresses, add one sentence — not a 70-line section.