agentleFS
HHC225HHC225/Japanese-Client-Breaker/.claude/skills/04_decision-analysis/skill.md

decision-analysis

Skill2 starsChanged 7 months agoMITView on GitHub

Identifies undecided/pending items in deliverables and provides structured option analysis with recommendations. Handles 要検討, ?, 未確定, TBD markers. Use when deliverables contain unresolved decision points that should be analyzed separately from defects.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read analyst items and preprocessed input

    line 22
  2. Very specific:

    Not assign HIGH/MEDIUM/LOW severity to undecided items

    line 38
  3. Distinctive:

    Instead reference the UNDECIDED-XXX id for the decision advisor's analysis

    line 39

≈ “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

Decision Analysis Skill

{WORKSPACE} = timestamped run directory provided by the orchestrator.

Purpose

Separate decision points from defects. Undecided items (要検討, ?, 未確定) are not failures — they are choices that need to be made. This skill analyzes each decision point and recommends a direction.

When to Use

  • Deliverable contains 要検討, ?, 未確定, TBD markers
  • Items need option analysis rather than criticism
  • Decision dependencies need to be mapped

Process

  1. Read analyst items and preprocessed input
  2. Scan for undecided markers using detection patterns from agent definition
  3. For each undecided item:
    • Extract the decision point
    • Identify available options from context
    • Analyze pros/cons for each option
    • Recommend a direction based on project context
    • Assess urgency and dependencies
  4. Map decision chains (which decisions block which)
  5. Output structured recommendations

Integration with Pipeline

  • Runs at: Phase 1.5 (after Analyst, before Critic)
  • Critic interaction: The critic receives the decision advisor's output and MUST:
    • Tag findings that overlap with undecided items as "is_undecided": true
    • Not assign HIGH/MEDIUM/LOW severity to undecided items
    • Instead reference the UNDECIDED-XXX id for the decision advisor's analysis
  • QA interaction: QA validates decision recommendations through all 5 consulting lenses
  • Report: Undecided items appear in a dedicated section with option comparison UI

Quality Checklist

  • All 要検討/?/未確定 markers identified
  • Each has minimum 2 options with pros/cons
  • Decision chains mapped (blocking relationships)
  • Urgency levels assigned with rationale
  • Recommendations have confidence levels
  • Impact of delay stated for each

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.