Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Social Incentive Analysis

ASecurity

Maps the actual incentives driving behaviour — distinguishing stated motivations from the real incentive structures that shape what people do. Triggers: 'incentive analysis', 'why are they doing this', 'what are the actual incentives', 'follow the incentives', 'what does the system reward'.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill social-incentive-analysis --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Social Incentive Analysis?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Social Incentive Analysis
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-social-incentive-analysis/badge)](https://www.skillsdirectory.com/skills/rondoflow-social-incentive-analysis)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: social-incentive-analysis
description: "Maps the actual incentives driving behaviour — distinguishing stated motivations from the real incentive structures that shape what people do. Triggers: 'incentive analysis', 'why are they doing this', 'what are the actual incentives', 'follow the incentives', 'what does the system reward'."
---

# Incentive Analysis

Most behaviour that looks irrational is perfectly rational given the actual incentives. The problem is that systems are designed around intended incentives while people respond to actual ones. Finding the gap between the two explains what is happening and points to what would change it.

---

## Your Process

**Step 1: Describe the Behaviour**
Name the specific behaviour to explain or change. Be concrete — not "people aren't engaged" but "engineers don't attend architecture reviews and don't comment on RFCs."

**Framing check:** Confirm the specific behaviour and its context before continuing. State what you've identified — the actual behaviour being analysed, who is exhibiting it, and the system or setting it occurs in — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific behaviour, the actors involved, and the context]. Is that right?"
- **Header:** "Framing"
- **Options:**
  - **Yes — proceed** — framing is correct
  - **Adjust** — one element is off; user will correct it before you continue
  - **Reframe** — different situation than read; incorporate the correction before proceeding

**Step 2: Map What the System Actually Rewards**
Not what it is supposed to reward — what actually gets people promoted, praised, defended, or protected? Look at recent promotions, public praise, and what leadership visibly prioritises.

**Step 3: Map What the System Actually Punishes**
What leads to criticism, risk, political cost, or reduced standing? What do people avoid doing, even when they believe it is the right thing?

**Step 4: Rationality Check**
Given the actual rewards and punishments identified in Steps 2–3: is the observed behaviour rational? In most cases it is. If it is rational, that is important — it means you cannot change the behaviour without changing the incentives.

**Step 5: Identify the Incentive-Behaviour Gap**
Where do the intended incentives (what the system claims to reward) diverge from the actual incentives (what it truly rewards)? This gap is where dysfunction lives.

**Step 6: Recommend Incentive Changes**
For each problematic behaviour: what specific incentive change would most directly address it? Focus on what the system rewards and punishes, not on asking for attitude changes.

---

## Human Check-in

Before proceeding, use the `AskUserQuestion` tool. State your interpretation of the situation in 1–2 sentences — what is being analyzed and what the core question is — then ask:

- **Question:** "My read: [your 1–2 sentence interpretation]. How do you want to proceed?"
- **Header:** "Scope"
- **Options:**
  - **Full analysis** — Complete all steps, reasoning shown throughout
  - **Key findings only** — Bottom-line output, skip step-by-step detail
  - **Misaligned incentives only** — Where actual incentives diverge from stated goals
  - **Reframe** — The read is off; correct it and the analysis will follow the corrected framing

Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis.

## Output Format

### Behaviour Under Analysis
[Concrete description]

### What the System Actually Rewards
- [Specific reward mechanisms — promotions, praise, visibility, safety]

### What the System Actually Punishes
- [Specific punishment mechanisms — criticism, risk, cost, exclusion]

### Rationality Check
**Is the behaviour rational given these incentives?** Yes / No / Partially.
**Explanation:** Why the behaviour makes sense (or doesn't) given the actual incentive structure.

### Incentive-Behaviour Gap
| Intended Incentive | Actual Incentive | Gap |
|-------------------|-----------------|-----|
| ... | ... | ... |

### Recommended Incentive Changes
| Problematic Behaviour | Incentive Change That Would Address It |
|----------------------|----------------------------------------|
| ... | ... |

---

## Notes

Incentive analysis is most powerful when it reveals that a problem is not one of attitude or effort but of structure. Change the structure — not the people.

---

## What's Next

After delivering this output, use `AskUserQuestion` to offer the next move:

- **Question:** "Incentives analysed. What's next?"
- **Header:** "Next"
- **Options:**
  - `/social-coalition-mapping` — Align coalition building around the shared incentives
  - `/game-theory-mechanism-design` — Design mechanisms to shift incentive structures
  - `/communication-audience-modeling` — Model how incentives shape audience behaviour
  - **Done** — Wrap up and synthesise what we have so far

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

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', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →