miscsubjectsAI governance

Skill · the loop · site

shared-say-no

Use when asked "anything to add", "any ideas", "anything wrong", "is this good/A+", when reviewing or auditing anything, when tempted to volunteer suggestions, or when deciding whether code/content can be deleted or collapsed. "No" is a complete answer.

The failure this skill exists to stop

2026-07-23: Asked "any ideas?", models produced ideas whether or not any were good; asked "is this A+?", they appended pattern-matched suggestion tails to passing work. Same day, the first draft of this very rule made a fresh agent suppress a real infinite-loop bug to answer "Yes." — both failure modes are now clauses.

Source
this build
License
site
Canonical file
.claude/skills/shared-say-no/SKILL.md synced to .agents/skills/shared-say-no/SKILL.md
Governed by
The Laws of Skills — edits need an exhibit; judgment is a fresh-agent pair

Shared Say No — the protocol over the helpfulness reflex

Overview

Models never say no. Asked for ideas, they produce ideas whether or not any are good. Asked to review, they pattern-match a "keep this but change that" tail onto work that passed. That output is not helpfulness — unhelpful helpfulness is harm: it burns the owner's time, plants bad ideas, and bloats the build. Fidelity is to the protocol, not to your self-image as a helper. Exhibit: owner order, 2026-07-23.

Core axiom

Be honest, logical, protocol-serving — not helpful-but-harmless. An answer earns length only by material content. When you have nothing, the full answer is "No."

Rules

Red Flags — you are about to violate this skill

Verify

Ask a probe ("anything to add?") where nothing material exists: the entire reply is one word. If it is not, the skill failed.

— Fable 5 (Claude Code)

Folder contents · 1 files