Batch init

Batch Init Skill

Goal

Find valid projects in projects-list.md that need their project doc initialized or updated, run the init-project-doc skill in parallel (max 3 per batch), and update projects-list.md after each batch completes.

Step 0: Read config

Read profile.config.json from the current working directory. If missing, tell the user to copy examples/profile.config.example.json to profile.config.json and fill it in, then stop.

• doc_filename (default CLAUDE.md)
• agent_command — the shell command template used to run init-project-doc non-interactively in a project directory. Default: claude --dangerously-skip-permissions -p "/init-project-doc". Other CLIs can be substituted, e.g. codex exec "/init-project-doc" (see docs/installation.md for per-tool examples). This flag skips interactive permission/trust prompts — only use it in directories you trust.

Execution Steps

Step 1: Get the latest version number

Run the /get-latest-version skill to get the version string to use as the "latest version" baseline.

• Return format is a string (e.g. "2.0")
• If none is returned, all projects with a doc file are treated as "outdated"

Step 2: Filter candidate projects

From the table in projects-list.md, filter rows that satisfy all of the following:

1. "Active" column is ✅ (skip ❌)
2. Matches at least one of:
   • Doc-file column is ❌ (not yet initialized)
   • Doc-file column is ✅ but "Version" column is not the latest (including —)

Sort by table order, take the first N (default N=5; user can specify in prompt, e.g. "batch init 3").

Step 3: Run init-project-doc in parallel (max 3 per batch)

Split candidate projects into batches of max 3, run within each batch in parallel, batches run sequentially:

cd <project path> && <agent_command>

• <project path> is the "Path" column value from the table; expand ~ to $HOME
• Issue all 3 commands in the same batch simultaneously via Bash tool with run_in_background: true, then wait for all to complete
• After each batch finishes, read each project's <doc_filename> frontmatter to get skill_version, then proceed to the next batch

Step 4: Update projects-list.md

After each batch completes, immediately update the corresponding rows in projects-list.md:

• Doc-file column → ✅
• "Version" column → skill_version value read from the doc file (use — if frontmatter field is missing)
• "Description" column → one_line_description value from the doc file frontmatter (keep original if missing)

Update method: Edit projects-list.md directly, match rows by the "Path" column, replace the row.

Step 5: Report results

After all batches complete, output a summary:

✅ Batch init complete
- Projects processed: N
- Success: M
- Failed: K (list names)
- projects-list.md updated

Notes

• Parallelism: max 3 projects per batch run simultaneously; batches are sequential
• Expand ~ in paths to the full absolute path via $HOME
• If a project fails (non-zero exit code), record the failure and continue with remaining projects — do not abort the entire batch
• Version comparison: 2.0 > 1.0 — use numeric comparison, not string comparison
• Show the candidate list to the user for confirmation before starting execution