Redo — Rework a Previous Implementation

skills/j-redo/ is the canonical, hand-edited directory for this skill, per CLAUDE.md's "The Canonical Naming Contract" (the E50 reopening of 2026-09-09, which promoted skills/j-redo/ from generated twin to sole canonical form). The j- prefix is there for collision safety — a real directory under a distinct name, so a host tool shipping its own same-named built-in command cannot shadow it (Claude Code's native skill resolution is a literal-string, directory-name-based match; see project/documentation/skill-authoring.md's "Invocation Convention").

⚠️ scripts/generate-j-alias.sh was retired by E50_S14 and no longer exists — there is nothing to run. This file was previously generated from a bare skills/redo/SKILL.md source; E50_S15 deleted that directory. This file is now the sole canonical, hand-edited source for this skill — edit it directly.

Input Format

/redo <identifier> <description>

• identifier — One of:
  • A git commit SHA (full or short, e.g. a1b2c3f)
  • An Epic number (e.g. E01)
  • A Story number (e.g. E02_S03)
• description — What should be redone and, if relevant, why, how, or to what end.

If either part is missing, ask the user to provide it before proceeding.

Instructions

1. Resolve the identifier

Commit SHA:

• Run git --no-pager log --stat -1 <SHA> to retrieve the commit message and changed files.
• Run git --no-pager show <SHA> to inspect the full diff.

Epic / Story number:

• Read the matching file under $(bash "$([ -f scripts/board_resolver.sh ] && echo scripts/board_resolver.sh || echo node_modules/@jenga-ai/agent/scripts/board_resolver.sh)")epics/ or $(bash "$([ -f scripts/board_resolver.sh ] && echo scripts/board_resolver.sh || echo node_modules/@jenga-ai/agent/scripts/board_resolver.sh)")stories/ to understand the scope.
• Use git --no-pager log --all --oneline --grep="<epic or story title>" to locate related commits and their diffs.

Collect the list of files originally changed and the original intent of the implementation.

2. Assess scope

Compare the user's redo description against the original implementation to determine:

• Which files need to change.
• Whether the redo is a partial revision (some files/logic) or a full rewrite.
• Which tests cover the affected code.
• Which documentation files reference the affected code or feature (check project/, documentation/, project/documentation/, README.md, WARP.md).

Summarise scope findings to the user in a brief list before continuing.

3. Plan the redo

Populate skills/j-todo/assets/todo_handoff_template.md with the following pre-collected context:

• Mission title: a short name for the redo work
• Goal / objective: the redo objective — what is changing and the desired outcome
• Affected files or scope: code, tests, and documentation files identified in step 2
• Intended approach: step-by-step changes
• Epic/Story linkage: the identifier resolved in step 1 (e.g. E02_S03), or None if a commit SHA

Then invoke the /todo skill with the populated template. Since the template fields are pre-filled, /todo should skip any questions already answered.

Wait for user approval before executing unless the user explicitly told you to go ahead.

Examples

• /redo a1b2c3f Rewrite the auth middleware to use JWT instead of session tokens
• /redo E02_S03 Replace the REST endpoints with GraphQL — the client team needs a flexible query interface
• /redo E01 Redo the entire onboarding epic using the new design-system components