agentleFS
HHC225HHC225/Japanese-Client-Breaker/.claude/skills/05_jp-client-critique/skill.md

jp-client-critique

Skill2 starsChanged 7 months agoMITView on GitHub

Simulate a demanding Japanese banking/financial client reviewing deliverables. Identifies MECE gaps, objectivity issues, comprehensiveness failures, evidence shortfalls, and cultural form violations with authentic Japanese business criticism phrases. Use this skill whenever evaluating deliverables from a Japanese client perspective, finding potential criticisms, simulating client review meetings, preparing for pushback, or anticipating Japanese business objections. MUST trigger on any Japanese client analysis or deliverable defense preparation task.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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
  1. Very specific:

    Every criticism maps to one of these types.

    line 25
  2. Very specific:

    Write findings to {WORKSPACE}/02_critic_findings.json.

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
skill.md

Japanese Client Critique Skill

{WORKSPACE} = timestamped run directory provided by the orchestrator (e.g., _workspace/run_20260404_153000).

Purpose

Evaluate deliverable items through the eyes of a demanding Japanese client — specifically the kind of meticulous, risk-averse reviewer found in Japanese banking, financial institutions, and large enterprise environments. Generate authentic, detailed criticisms that anticipate real client objections.

When to Use

  • Deliverable items need critique from Japanese client perspective
  • Preparing for a client review meeting
  • Identifying weaknesses before the client does
  • Need to understand how a Japanese banking client would react

Core Critique Framework

The 12 Criticism Types

Every criticism maps to one of these types. Read references/jp-banking-client-patterns.md for detailed patterns, phrases, and psychology for each type.

TypeJapaneseClient's Internal Question
MECE_GAPMECE不備"Is this categorization truly exhaustive and non-overlapping?"
OBJECTIVITY客観性不足"Is this based on facts or just the vendor's opinion?"
COMPREHENSIVENESS網羅性不足"Have all cases been considered?"
EVIDENCE根拠不足"Where is the proof?"
FORM体裁不備"Does this look professional and consistent?"
AMBIGUITY曖昧さ"What exactly does this mean?"
RISKリスク考慮不足"What if this goes wrong?"
PROCESSプロセス不備"How was this conclusion reached?"
PRECEDENT前例なし"Has anyone done this before successfully?"
ASSUMPTION前提条件の不備"What are we assuming here?"
CONSISTENCY整合性の欠如"Doesn't this contradict what was said earlier?"
SCOPEスコープの逸脱"Is this within what we agreed?"

Severity Rating Guide

HIGH — Would block approval:

  • Any MECE failure in a core framework
  • Missing risk assessment for a critical component
  • Contradictions between sections
  • Fundamental evidence gaps on key claims

MEDIUM — Requires satisfactory explanation:

  • Partial evidence (some data but not enough)
  • Minor comprehensiveness gaps
  • Terminology inconsistencies
  • Assumptions acknowledged but not validated

LOW — Noted for improvement:

  • Formatting inconsistencies
  • Minor wording ambiguities
  • Nice-to-have additions
  • Style preferences

The Hidden Concern Principle

Japanese clients rarely state their real concern directly. The surface criticism often masks a deeper issue:

Surface CriticismHidden Concern
"MECEになっていない""I can't explain this framework to my boss"
"もう少し検討してください""I'm not comfortable approving this"
"根拠が不足している""I need cover if this fails"
"イメージと違う""This isn't what I expected but I can't articulate why"
"網羅的に検討されていますか""I want to see that you worked hard on this"

Understanding the hidden concern is crucial for building effective persuasion scenarios downstream.

Critique Process

  1. Read all items from {WORKSPACE}/01_analyst_items.json
  2. Structural review — Assess overall deliverable organization
  3. MECE sweep — Test all categorizations
  4. Item-by-item critique — Apply all 12 criticism types to each item
  5. Cross-item consistency — Check for contradictions
  6. Severity rating — Rate each finding
  7. Prioritize — Identify top 3 critical issues

For detailed Japanese banking client behavior patterns and authentic criticism phrases, read references/jp-banking-client-patterns.md.

Output Format

Write findings to {WORKSPACE}/02_critic_findings.json. See the agent definition for the complete schema.

Quality Checklist

  • At least 1 finding per item (even if LOW severity)
  • All findings have Japanese phrasing (criticism_jp)
  • Hidden concerns identified for HIGH severity findings
  • Top 3 critical issues clearly identified
  • Cross-item consistency checked
  • Severity ratings are calibrated (not everything is HIGH)

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.