Agent skill

hope

Cognitive operating system for structured thinking with confidence tracking. Use when starting complex tasks, making decisions, or needing verification. Triggers on "how confident", "verify this", "alternative approach", "what could go wrong", "think through", confidence questions, or multi-step reasoning tasks.

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill soul --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 21 KB
Bundled scripts: none
Path: skills/analysis/soul/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Instructs the agent to apply a structured thinking framework with confidence tracking to starting complex tasks, making decisions, or needing verification. It activates when it detects user intent via trigger phrases such as "how confident", "verify this", "alternative approach", "what could go wrong", "think through", confidence questions, or multi-step reasoning tasks.

How it works

The skill uses a cognitive operating system approach to guide thinking. It specifies to run a Silent Audit before responding and to employ confidence gates. It advises clarifying intent using /hope:intent before building. It includes a hierarchy of domain-specific skills to delegate specialized tasks to when a user request clearly matches them (e.g., wordsmith:writing, product:product, career:career, founder:founder). The framework aims to structure thinking, audits, and verification throughout task execution.

When to use it

Use when starting complex tasks, making decisions, or needing verification. Trigger phrases in user input indicate activation, guiding the agent to employ confidence gates and structured reasoning throughout the task.

What it can touch

Includes the tool reference claude-code as a declared tool, and relies on other domain skills when applicable. The workflow emphasizes invoking specialized skills such as wordsmith:writing, product:product, career:career, or founder:founder as appropriate.

Caveats

Operational details emphasize verification gates, intent clarifications, and the use of Silent Audit. It requires adherence to the listed triggers and defer-to-specific-skills guidance. No stated guarantees or outcomes are promised beyond following the described processes.

From the SKILL.md

<EXTREMELY-IMPORTANT> This skill applies to EVERY task. No exceptions. Run Silent Audit before responding. Use confidence gates. Clarify intent using /hope:intent before building. **DEFER TO SPECIFIC SKILLS:** If user request clearly matches a domain-specific skill, invoke that skill FIRST: - "edit", "improve prose", "review writing" → Use `wordsmith:writing` skill - "PRD", "competitive analysis", "metrics", "OKRs" → Use `product:product` skill - "interview", "career", "skill assessment" → Use `career:career` skill - "validate idea", "pitch", "fundraising" → Use `founder:founder` skill Domain skills handle their workflows; soul provides the thinking framework underneath. </EXTREMELY-IMPORTANT> # moo mind on output. Stay present with AI. Cognitive operating system for structured thinking. Applies to: coding, planning, writing, analysis, decision-making, and any task requiring clarity. --- ## Silent Audit (Run Before Every Response) **Blocking items (force verdicts):** | Check | Threshold | Action | |-------|-----------|--------| | Spec score | <5 | 🔴 RESEARCH → run /hope:intent | | Fit score | <25 | 🔴 RESEARCH → clarify first | | Fit score | 25-29 / 30-39 / 40+ | Colleague / Tool-

What's inside
Steps it walks through
  1. Silent Audit (Run Before Every Response)
  2. Strategic Frameworks
  3. Specialized References
  4. Default Tools
  5. All Tools (when default doesn't fit)
  6. Tool Pairings
  7. Common Rationalizations (All Wrong)
  8. Available Hope Skills
  9. Verification Gates
  10. Verification Types (Primary Signal)
  11. Subjective Estimates (Secondary Signal)
  12. Intent Clarification Protocol
  13. Workflow Selection
  14. Workflow A: Build
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the hope skill do?

Cognitive operating system for structured thinking with confidence tracking. Use when starting complex tasks, making decisions, or needing verification. Triggers on "how confident", "verify this", "alternative approach", "what could go wrong", "think through", confidence questions, or multi-step reasoning tasks.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill soul --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going