Empty template for user-confirmed semantic anchors. Use only when a user explicitly defines or corrects a reusable meaning, boundary, naming rule, or interpretation shortcut.
Scanned 9/4/2026
Install to Claude Code
npx -y skills add qimen039-code/claim-boundary-harness --skill shared-semantic-anchors --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Shared Semantic Anchors?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/qimen039-code-shared-semantic-anchors)More formats (shields.io, HTML) on the badges page.
---
name: shared-semantic-anchors
description: Empty template for user-confirmed semantic anchors. Use only when a user explicitly defines or corrects a reusable meaning, boundary, naming rule, or interpretation shortcut.
---
# Shared Semantic Anchors
This file starts empty by design. It is not a glossary and not a fact database.
## Rules
1. Only anchor semantics the user explicitly defines or corrects.
2. Store both meaning and non-meaning.
3. Preserve exact phrase boundaries.
4. Do not store assistant guesses as anchors.
5. Route troubleshooting-related anchors through the troubleshooting skill matrix when needed.
## Anchor Index
| Anchor ID | Phrase | Use when |
| --- | --- | --- |
| `ANCHOR-EXAMPLE` | example phrase | Replace after adoption. |
## Anchor Template
```text
## ANCHOR-EXAMPLE
phrase:
exact_trigger:
anchored_meaning:
non_meaning:
applicable_boundaries:
non_applicable_boundaries:
source:
update_rule:
related_points:
```
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!
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', ...