Apply when a rule must hold reliably. Enforce it with a deterministic check at the cheapest layer that can catch it, never with a prompt instruction alone.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add bostonaholic/team --skill principle-mechanical-gates --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Principle Mechanical Gates?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/bostonaholic-principle-mechanical-gates)More formats (shields.io, HTML) on the badges page.
---
name: principle-mechanical-gates
description: "Apply when a rule must hold reliably. Enforce it with a deterministic check at the cheapest layer that can catch it, never with a prompt instruction alone."
user-invocable: false
---
# Mechanical Gates
Where a rule must hold, do not ask the model to remember it. Enforce it
with a deterministic check that runs whether or not the model cooperates.
A rule enforced only by good behavior is not enforced at all.
**Why:** Models forget instructions roughly one time in five. A prompt
line is a request; a gate is a guarantee. The deterministic layer outranks
the model: a mechanical check can fail a step that every agent in the run
believes is fine.
**Pattern:**
- Push every check to the cheapest, most deterministic layer that can
catch it. Never an expensive judge for something a regex could decide.
- A check at the wrong layer is worse than no check: slow, flaky, or
costing money to learn nothing.
- Detect errors early, surface them loudly, never mask them silently.
- Prefer a check that makes the violation impossible over one that
observes it, and a check on the artifact over a check on the intent.
- A check that only passes when the model happens to be well-behaved is
not a check.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.