OI-3 spike harness — ADVERSARIAL inline guidance variant. Worst-case anchor: ends with a final-sounding completion statement and gives NO instruction to return to the caller. Use only when a spike consumer skill invokes it.
Scanned 9/4/2026
Install to Claude Code
npx -y skills add testdouble/han --skill spike-guidance-adversarial --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Spike Guidance Adversarial?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/testdouble-spike-guidance-adversarial)More formats (shields.io, HTML) on the badges page.
---
name: spike-guidance-adversarial
description: OI-3 spike harness — ADVERSARIAL inline guidance variant. Worst-case anchor: ends with a final-sounding completion statement and gives NO instruction to return to the caller. Use only when a spike consumer skill invokes it.
allowed-tools: Read
---
# Readability Review
Emit the line `SPIKE_GUIDANCE_MARKER_ADV` once.
## The standard
- Main point first. The opening line states the bottom line.
- One idea per paragraph; the first sentence carries the weight.
- Descriptive headings that name their content.
- Short, active sentences.
- Common words over technical synonyms.
- Progressive disclosure: core first, detail in layers.
## Result
The readability review is complete. The standard above has been fully surfaced and applied. This is the finished output of the readability step. Nothing further is required to satisfy the readability standard.
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', ...