Ask Why

Trust Score 85/100

A planning skill that turns vague requests into traceable decision rounds, producing PLAN.md, DECISIONS.md and FINAL_PLAN.md to guide complex, iterative work.

triggers:plandecision roundsAsk WhyPLAN.mdDECISIONS.md

GitHub SKILL.md

What it does

Ask Why guides agents through structured planning sessions for ambiguous or high-rework tasks. It enforces an entry gate, runs iterative P2A decision rounds, and maintains durable state files (PLAN.md, DECISIONS.md, OPEN_QUESTIONS.md) so planning is traceable and reviewable. The skill provides templates and runbooks for ambiguity mapping, round structure, and convergence criteria.

When to use it

Use Ask Why when a task is open-ended, has multiple reasonable directions, or early choices cause substantial rework — e.g., product strategy, PRDs, workflow design, research planning, or skill/agent design. Do not use for simple factual Q&A, one-shot fixes, or routine translation tasks.

What's included

Scripts: none bundled, this skill is primarily a process/template authoring skill.
References: includes references/formats.md and other template artifacts in the repo to structure outputs.
Instructions: detailed operating rules, entry gate, runbook, and file conventions to create and maintain PLAN.md/DECISIONS.md/OPEN_QUESTIONS.md.

Compatible agents

Intended for codex-style planning agents and human-in-the-loop workflows; works well with Claude Code or any agent runtime that can present rounds and write files to a workspace.

Audit Summary

Ask Why is a planning skill that turns vague requests into iterative decision rounds, producing PLAN.md, DECISIONS.md, and FINAL_PLAN.md. No scripts were present to test. The SKILL.md is well-structured with clear triggers, a language contract, and a detailed runbook for ambiguity mapping and decision rounds. Purely declarative with no executable content.

Watch Out

Requires references/formats.md template file which is referenced but not bundled in the audit data
State files (PLAN.md, DECISIONS.md, etc.) are written to p2a-session/ directory

Notes

Clean skill with no security concerns. Pure text/process skill with no scripts, network calls, or destructive commands. Well-documented operating rules and clear entry gate criteria.

Information

Repository: ask_why
Stars: 110
Installs: 0

Trust Score

Overall85

Security95

Code Quality72

Architecture78

Usefulness65

Related Skills

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Maestro Orchestrate

Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.

Cost Tracker

Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.

FastAPI Project Templates

Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.

Chinese Software Copyright Application

Generate complete Chinese software copyright application materials (application form, code documentation, user manual, design docs) and export them to PDF from

Execution Plan Splitter

Break large goals into 30/60/90-day execution plans with milestones, resource needs, and stop/go criteria for practical roadmaps.

CTF Write-up Generator

Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.

Verifying Markdown Formatting

Checks Markdown files for structural and stylistic formatting issues (headings, lists, code blocks, links) and applies deterministic fixes.

Back to Skills