repo-native-alignment: Skill for Claude Code

oh-plan

Creates well-structured GitHub issues ready for oh-task agents. Works in two modes:

1. Task mode: Investigates codebase, asks clarifying questions, creates issues
2. Session mode: Reads existing .oh/<session>.md context, skips investigation, creates issues

Invocation

# Task mode - investigate from scratch
/oh-plan "Add dark mode support to the dashboard"

# Session mode - use existing context from skills workflow
/oh-plan auth-refactor

Mode Detection

At the start, check if the argument matches an existing session file:

If .oh/<arg>.md exists AND contains ## Solution Space:
    → Session mode (skip investigation, use context)
Else:
    → Task mode (investigate, ask questions)

Session Mode Flow

Shared setup for both session and task mode, before creating any issue:

gh label create oh-planned --description "Created via oh-plan skill" --color "0E8A16" 2>/dev/null || gh label view oh-planned >/dev/null

When .oh/<session>.md exists with solution-space context:

1. Read session file and extract:

   • ## Aim → Goal for issues
   • ## Problem Space → Constraints, terrain, assumptions
   • ## Solution Space → Selected approach, trade-offs accepted
   • ## Problem Statement → Framing (if present)

2. Skip investigation - context already gathered by grounding skills

3. Skip clarifying questions - decisions already made during solution-space

4. Decompose the selected solution into right-sized issues:

   • Use the Solution Space recommendation as the starting point
   • Apply standard decomposition heuristics (see below)
   • Aim for 1-4 hours of work per issue

5. Create GitHub issues with enriched context from session:

   gh issue create --title "<title>" --label "oh-planned" --body "$(cat <<'EOF'
   ## Goal
   
   <from Aim section>
   
   ## Context
   
   <from Problem Space: constraints, terrain>
   <from Solution Space: selected approach>
   
   ## Acceptance Criteria
   
   - [ ] <derived from solution trade-offs>
   - [ ] <derived from aim feedback signals>
   
   ## Trade-offs Accepted
   
   <from Solution Space>
   
   ## Notes
   
   <from Problem Space assumptions>
   EOF
   )"