菜单
File a bug report or feature request for the odd-pipeline itself, with auto-gathered context from the current project and session. Use when the user says "/file-issue", "file a bug", "report an issue", "this is a pipeline problem", or encounters a pipeline defect during daily use.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Interactive skill that helps users define desired outcomes for the next phase through Socratic grilling. Produces a PHASE_PLAN.md with concrete goals, scope boundaries, and success criteria. Uses grill-me + first-principle thinking to question priorities and foundations before committing to a plan. This is the recommended step before `/drive-outcomes`, especially when goals are still vague. Use when the user says "/define-outcomes", "define the outcomes", "clarify what we want", "what should the next phase achieve", "plan the next phase", or wants to decide what the next phase should accomplish before implementing.
Merged Stage 1+2 — define success criteria, explore against real fixtures, validate, implement, and produce a forensic record. One continuous session with a checkpoint in the middle. Use when the user says "/drive-outcomes <plan-path>", "drive the outcomes for this phase", after /define-outcomes completes, or when a phase plan is already ready for ODD-driven implementation.
Stage 0 — grill the user to settle the repo constitution: architecture, coding patterns, domain language, dependency choices, and tooling configuration. Produces CONTEXT.md (domain glossary + tooling config) and ADRs (architectural decisions). MUST be run before `/drive-outcomes` on any project. Use when the user says "/init-project", "set up the project constitution", "initialize the repo for the pipeline", or on a fresh project checkout before any planning begins.
Review implemented changes against TASKS.md, produce review.md and fix-tasks.md for any defects found. Accepts a TASKS.md path and progressively loads group sections for validation. Use when the user says "/make-judgement <tasks-path>", "review the implementation", "judge the changes", or after /drive-outcomes completes for complex multi-group changes.
Debug an existing fixture-anchored system that passes its acceptance test but produces wrong output. Classifies prior investigation notes, establishes external anchor criteria, applies upstream-audit rule, implements fix with discriminator-value tests, and captures resolution. Use when the user says "/debug-outcomes", "debug this failure", "the test passes but the output is wrong", or describes a symptom in a system that already has fixture files and a passing (but loose) acceptance test.
Scans a project's existing test suite for placebo test patterns (vacuous assertions, circular round-trip, unbounded thresholds, synthetic-only data). Produces a migration report to help projects adopt the Outcome-Driven Development (ODD) pipeline. Use when migrating from the old TDD pipeline, auditing test quality, or when the user says "/diagnose-tests", "audit my tests", "find placebo tests", or "how healthy are my tests?".
| name | file-issue |
| description | File a bug report or feature request for the odd-pipeline itself, with auto-gathered context from the current project and session. Use when the user says "/file-issue", "file a bug", "report an issue", "this is a pipeline problem", or encounters a pipeline defect during daily use. |
Gathers context from the current project and session to file a structured issue on the TonyWu20/odd-pipeline repository. Lowers friction for reporting pipeline defects encountered during daily use.
/file-issue
No arguments. The skill prompts the user for issue details interactively.
The pipeline uses pluggable agents. Determine which agent to use for context gathering:
--agent-griller=<agent-name>, use that agent. CLI args override everything.AGENT_CONFIG.md from the project root. If it exists, parse **griller:** <agent-name>. Apply if not already set by CLI args.griller defaults to general-purpose.griller.Throughout this skill, whenever a subagent is launched, use the resolved agent name.
Launch the griller subagent (resolved in Step 0) to collect relevant context:
Agent: {griller} (subagent, discardable context)
Task: Gather context for a pipeline issue report.
Collect the following:
Current pipeline state:
ls skills/*/SKILL.md 2>/dev/nullPipeline version:
git log --oneline -5Current project context (from the working directory where the issue was encountered):
pwd git remote -v 2>/dev/null git log --oneline -3 2>/dev/nullOutput the gathered context as structured data for the issue template.
Format the issue using the GitHub issue template:
---
title: "[pipeline]: <short description>"
---
## Description
{User's description of the problem or feature request}
## Context
- **Pipeline version**: {commit hash from git log}
- **Project**: {current project URL or path}
- **Session**: {what skills were being used when the issue occurred}
## Reproduction Steps
{User-provided or auto-detected steps}
## Expected vs Actual
- **Expected**: {what should happen}
- **Actual**: {what actually happened}
## Environment
- **Pipeline branch**: {current branch}
- **OS**: {auto-detected}
- **Claude Code version**: {if available}
## Relevant Artifacts
{Paths to relevant plan files, directions.json, execution reports, etc.}
Present the formatted issue to the user for review and editing:
"Here's the draft issue for
TonyWu20/odd-pipeline:
{ISSUE_BODY}
Please review and edit the description above, then confirm to file the issue. Type 'confirm' to file, or provide changes."
Once the user confirms, file the issue:
gh issue create --repo TonyWu20/odd-pipeline --title "<title>" --body "<body>"
Report the resulting issue URL to the user.
Will:
gh CLIWill not: