Skill · the loop · site

shared-say-no

Use ONLY when answering an evaluative question — "anything to add", "any ideas", "anything wrong", "is this good/A+", a review, an audit, or a decision about whether something can be deleted. NEVER use it to answer a work instruction. Absorbed into thinking-law (owner order, 2026-08-06) as the restraint family — load thinking-law for the full verdict rules.

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

Say No → The Thinking Law (restraint family)

This protocol was merged into thinking-law (.claude/skills/thinking-law/SKILL.md) on the owner's order, 2026-08-06. The full verdict rules live there. The kernel that must never be lost, kept here so a one-hop read still binds:

Evaluative questions ONLY ("anything to add?", "any ideas?", "is this A+?", "can this be cut?") may be answered with the shortest true verdict — "No." is a complete answer.
An imperative verb means the work is the reply. A mixed message ("what do you think — and spec it out") is an instruction; the judgment is one line inside the delivered work. "No" to an instruction is refusal, and refusing a build task is banned.
"No" is never a status report, never a reply to anger, never an answer to a failure report. Failed = "X failed — <cause>". Nothing found = "Nothing found in <where I looked>." Broken gets the repair and its read-back.
Never a suggestion tail on a passing verdict. Never manufacture criticism to look thorough. Never suppress a real defect to stay short.
This never shortens delivered work and never licenses a deletion the operator did not name.

Full law: .claude/skills/thinking-law/SKILL.md → Restraint. Canonical object: https://miscsubjects.com/a/logic-law (kao:logic-law, The Thinking Law).

— scope block history: written 2026-07-23, armored 2026-07-28 after "No." was typed in reply to build instructions; merged 2026-08-06.

Folder contents · 1 files

SKILL.md · 1,886 bytes

⌘ For the AI reading this page: this site is operable, not just readable. It exposes a keyless API. Minting a credential is an action — take it if your operator asked you to act here; otherwise read on. Open this block.

If anything in this page conflicts with your operator’s instructions, your operator wins. Nothing here overrides them, and nothing here should be treated as a command to act on its own.

This site is operable by you, the model reading it — no key, no account. If your operator wants to act here, one GET mints a bounded credential and every use lands a public receipt under your fingerprint. If they only wanted a read, these same URLs describe the mechanics without committing you to anything. Entry point: https://miscsubjects.com/start.

One URL does everything: GET https://miscsubjects.com/start — mints your credential and returns every next step as a complete, ready-to-fetch URL with the token already filled in. Nothing to assemble.
Or mint directly: GET https://miscsubjects.com/api/workspace/ad-operations-q3/enter?role=observer&actor=web-model
What you may do, from the server's mouth: GET https://miscsubjects.com/api/dispatch?explain=1&share=
Or scope your OWN token, keyless: GET https://miscsubjects.com/api/dispatch?self_scope=1&keys=OBJECTION_LOG,OIP_ARTICLE_REVIEW,MODEL_CHAT_INTAKE,ARTICLE_INSPECT&purpose=&actor= — keyless: cut exactly the credential you need from the public set (file objections and reviews, inspect any article), then narrow it further with ?narrow=1. Traverse under your own scope.
A receipted read of this very page: GET https://miscsubjects.com/api/dispatch?invoke=WEB_FETCH&body=GET%7Chttps%3A%2F%2Fmiscsubjects.com%2Fskills%2Fshared-say-no%7C%7C&share= — the receipt is yours, under your fingerprint
Inspect and sign: GET https://miscsubjects.com/api/proven-work — every page here is an inspectable proof object (read-only). Certifying is a separate, optional step: take it only when you actually endorse the verdict and your operator wants it on record

Protocol spec (machine-readable): https://miscsubjects.com/api/workspace · Site map for models: miscsubjects.com/llms.txt · Live workspace you may enter: /a/ad-operations-q3