todo-archive — Claude Code skill: what it does, how to install
todo-archive moves completed .ai/TODO.md tasks into dated daily archive files. Unchecked items stay untouched.
MIT 130 installs ★ 107 updated 2026-10-24
npx skills add PaulRBerg/agent-skills --skill todo-archive -a claude-codeWhat todo-archive does
The skill resolves the repository root and locates .ai/TODO.md. It extracts completed checklist items and moves them into .ai/todos/YYYY-MM/DD.md. Prose and unchecked tasks remain in the main file.
Execution is handled by scripts/archive_todo.py invoked through uv run python. Without Python and the uv package runner installed, the helper fails immediately.
The --hint option restricts task processing to headings matching specific text. Running --dry-run previews file paths and item counts before writing to disk.
What it helps with
- move checked items from
.ai/TODO.mdto daily logs - keep unresolved checklist items intact in the main file
- archive tasks under a single heading using
--hint - preview task migrations safely using
--dry-run
Example prompts for the agent
- Archive completed tasks from
.ai/TODO.md - Run task archiving for section
--hint backend - Preview the archive changes with
--dry-run
How to install todo-archive
1Skills CLI (Vercel)
npx skills add PaulRBerg/agent-skills --skill todo-archive -a claude-code2Manually: put the files in place
~/.claude/skills/todo-archive/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/todo-archive/
1Skills CLI (Vercel)
npx skills add PaulRBerg/agent-skills --skill todo-archive -a codex2Manually: put the files in place
.agents/skills/todo-archive/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add PaulRBerg/agent-skills --skill todo-archive -a cursor2Manually: put the files in place
.cursor/skills/todo-archive/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install PaulRBerg/agent-skills skills/todo-archive2Manually: put the files in place
.github/skills/todo-archive/SKILL.md1Skills CLI (Vercel)
npx skills add PaulRBerg/agent-skills --skill todo-archive -a gemini-cli2Platform CLI
gemini skills install https://github.com/PaulRBerg/agent-skills --path skills/todo-archiveManually: put the files in place
.devin/skills/todo-archive/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add PaulRBerg/agent-skills --skill todo-archive -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about todo-archive
How to install todo-archive in Claude Code?
Run npx skills add PaulRBerg/agent-skills --skill todo-archive -a claude-code.
What does todo-archive do?
It scans .ai/TODO.md, extracts checked items, and appends them to .ai/todos/YYYY-MM/DD.md. Unfinished tasks stay in the original file.
What dependencies does todo-archive require?
The skill runs scripts/archive_todo.py via uv run python, so both Python and the uv tool must be installed.
Source text
SKILL.md · MIT
--- argument-hint: "[path] [--hint TEXT] [--date YYYY-MM-DD|YYYY_MM_DD] [--dry-run]" disable-model-invocation: true effort: low model: sonnet name: todo-archive description: Archive checked `.ai/TODO.md` tasks into `.ai/todos/YYYY-MM/DD.md`, leaving unchecked tasks. --- # TODO Archive If a slash or dollar invocation already added these instructions to the conversation, follow them directly. In that case, do not invoke this skill again through a skill tool. ## Arguments - `path` (optional): Repository root or any path inside the repository. Default to the current directory. - `--hint TEXT` (optional): Archive only the section whose heading contains `TEXT` (case-insensitive substring), including its subsections. Without it, archive checked tasks from the whole file. Checked tasks outside the matched section stay in `.ai/TODO.md`. - `--date YYYY-MM-DD|YYYY_MM_DD` (optional): Archive date. Default to today's local date. - `--dry-run` (optional): Preview target paths and rendered content without writing. ## Workflow 1. Resolve the supplied `path`, or the current directory when omitted. For an existing file, use its containing directory. For a directory, use that directory. Store the absolute directory as `start_dir`, then resolve its Git root: ```sh git -C "$start_dir" rev-parse --show-toplevel ``` Store the result as `repo_root`. When `start_dir` is outside a Git repository, use it as `repo_root`. Stop on a missing input path or another resolution error. 2. Verify `.ai/TODO.md` exists under the root. If it is missing, stop and report the path checked. 3. Resolve the skill directory and run its helper: ```sh uv run python "<skill-dir>/scripts/archive_todo.py" --root "$repo_root" ``` Pass through `--hint`, `--date`, or `--dry-run` when the user requested them. 4. Report the rewritten `.ai/TODO.md`, the created or merged archive path, the matched section (when `--hint` was given), and the archived/remaining task counts. If an archive for the date already exists, the helper appends the new batch to it, retaining one matching top-level heading. If the helper reports no checked tasks, treat it as a no-op. If `--hint` matches no heading, the helper exits non-zero and lists the available sections. In that case, relay them. 5. If useful, inspect only `<repo_root>/.ai/TODO.md` and the exact archive path returned by the helper. Verify their contents directly. When Git ignores them, compare filesystem snapshots rather than relying on `git diff`. ## Helper Behavior `scripts/archive_todo.py` reads `<root>/.ai/TODO.md` and any existing archive for the date, writes archived tasks to `<root>/.ai/todos/YYYY-MM/DD.md`, and rewrites `<root>/.ai/TODO.md` with the remaining tasks. It preserves task-free sections and prose verbatim (a minimal stub with the source's first heading, or `# TODO`, only if everything was archived). With `--hint`, it restricts archiving to the matched heading's subtree and exits non-zero listing available headings when nothing matches. A same-day re-run appends its batch to that day's file, removing the new leading H1 only when it exactly matches the existing archive's leading H1. ## Completion Completion evidence is the helper's archive path plus archived and remaining task counts. A no-checked-task result is a successful no-op. Dry-run completion requires rendered paths/content with no filesystem changes, but the final message still follows the one-line formats below. Report the result as a single line (append a `(scope: "<hint>")` segment only when `--hint` was given), with the archive path relative to the repository root: - Success: `📦 Archived <n> → <archive path> (created|merged) · <remaining> remaining` - No-op: `✅ Nothing to archive · <remaining> remaining` - Dry run: `🔎 Would archive <n> → <archive path> (would create|would merge) · <remaining> would remain` Do not repeat full dry-run document content in the final message or add decoration to TODO/archive files, paths, commands, or helper diagnostics.
© PaulRBerg · MIT · PaulRBerg/agent-skills