persuasion-scenarios
Skill2 starsChanged 7 months agoMITView on GitHub
Build multi-level counter-argument trees (minimum 3 levels) for defending deliverables against Japanese client criticism. Creates culturally calibrated debate scenarios with escalating persuasion techniques, Japanese business phrasing, and practical preparation notes. Use this skill when creating defense arguments, building counter-argument scenarios, preparing for Japanese client pushback, developing persuasion strategies, or rehearsing difficult client conversations. MUST trigger on any persuasion scenario generation or argument tree building task.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- jp-client-defenderSkill
- file-preprocessingSkill
- deliverable-analysisSkill
- gap-analysisSkill
- decision-analysisSkill
- jp-client-critiqueSkill
- consulting-qaSkill
- html-report-generationSkill
- quality-gateSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Every argument tree has at least 3 levels.
- Very specific: line 82
Read findings from {WORKSPACE}/02_critic_findings.json
- Distinctive: line 86
Write Japanese business phrases for each level
- Distinctive: line 87
Create preparation notes including nemawashi strategy
- Very specific: line 93
Write scenarios to {WORKSPACE}/03_strategist_scenarios.json.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Persuasion Scenarios Skill
{WORKSPACE}= timestamped run directory provided by the orchestrator (e.g.,_workspace/run_20260404_153000).
Purpose
Transform each criticism into a structured, multi-level debate tree. Each tree has minimum 3 rounds of back-and-forth, using escalating persuasion techniques calibrated for Japanese business culture.
When to Use
- Criticisms need defense scenarios
- Preparing counter-arguments for client meetings
- Building persuasion strategies for Japanese contexts
- Need rehearsal scripts for difficult conversations
Argument Tree Architecture
The 3-Level Minimum Rule
Every argument tree has at least 3 levels. Each level follows a pattern:
Level 1 (Foundation): Acknowledge + Initial Defense
→ Client Rebuttal (anticipated)
Level 2 (Reinforcement): Stronger Evidence + Broader Context
→ Client Pushback (anticipated)
Level 3 (Resolution): Strongest Argument + Face-Saving Bridge + Path ForwardTechnique Selection Matrix
Select techniques based on criticism type and severity. Read references/argument-tree-patterns.md for detailed examples.
| Severity | Level 1 | Level 2 | Level 3 |
| HIGH | ACKNOWLEDGE_THEN_REDIRECT | RISK_QUANTIFICATION + INDUSTRY_BENCHMARK | ALTERNATIVE_COMPARISON + FACE_SAVING_BRIDGE |
| HIGH | EVIDENCE_FIRST | EXPERT_AUTHORITY + PROCESS_TRANSPARENCY | STAKEHOLDER_ALIGNMENT + MUTUAL_COMMITMENT |
| MEDIUM | SCOPE_CLARIFICATION | COST_BENEFIT_ANALYSIS | PHASED_APPROACH |
| MEDIUM | PRECEDENT_CITATION | INDUSTRY_BENCHMARK | FACE_SAVING_BRIDGE |
| LOW | EVIDENCE_FIRST | PRECEDENT_CITATION | FACE_SAVING_BRIDGE |
Cultural Calibration Rules
These are non-negotiable in Japanese business contexts:
- Never contradict directly — "That's incorrect" → "I appreciate that perspective. If I may add some context..."
- Always acknowledge first — Validate their concern before any counter-argument
- Use humble language — "弊社としましては..." (From our company's perspective...), not assertive claims
- Reference their authority — "○○様のご指導を踏まえまして..." (Based on your guidance...)
- Offer, don't demand — "ご検討いただけますでしょうか" (Would you consider...), not "You should..."
- Show exhaustive effort — "X件の代替案を検討した結果..." (After examining X alternatives...)
- Quantify obsessively — Every claim should have a number attached if possible
The Face-Saving Bridge
The most critical technique. Japanese clients will reject even valid arguments if accepting means losing face. Always provide an "off-ramp":
Pattern: Frame your argument as an extension of the client's own thinking.
- "○○様が以前ご指摘されたように..." (As you previously pointed out...)
- "ご要件を踏まえた上で..." (Building on your requirements...)
- "○○様のご方針に沿って検討した結果..." (Having considered this in line with your policy...)
This allows the client to accept without admitting they were wrong.
Nemawashi (根回し) Strategy
For HIGH severity findings, direct meeting defense often isn't enough. The preparation_notes should include a nemawashi strategy:
- Who to contact before the meeting — Identify the key decision-maker and their trusted advisor
- What to share informally — Give them a preview of your argument so they're not surprised
- When to do it — At least 2-3 business days before the formal meeting
- How to frame it — "ご相談がございまして..." (I have something I'd like to consult you about...)
Process
- Read findings from
{WORKSPACE}/02_critic_findings.json - For each finding, identify the hidden concern behind the surface criticism
- Select opening strategy based on severity and type
- Build 3-level argument tree with escalating techniques
- Write Japanese business phrases for each level
- Create preparation notes including nemawashi strategy
For detailed argument patterns and examples, read references/argument-tree-patterns.md.
Output Format
Write scenarios to {WORKSPACE}/03_strategist_scenarios.json. See the agent definition for the complete schema.
Quality Checklist
- Every finding has a scenario with minimum 3 levels
- No two consecutive levels use the same technique
- All levels include Japanese phrasing
- HIGH severity findings include nemawashi strategy
- Face-saving bridge present in every Level 3
- Evidence is specific (not "data shows" but "Q3 2024 report shows 15% reduction")
- Fallback strategy defined for every scenario
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

