agentleFS
PaulRBergPaulRBerg/dot-agents/skills/todo-archive/SKILL.md

todo-archive

Skill6 starsChanged 6 days agoMITView on GitHub

Archive checked `.ai/TODO.md` tasks into `.ai/todos/YYYY-MM/DD.md`, leaving unchecked tasks.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If a slash or dollar invocation already added these instructions to the conversation, follow them directly.

    line 12
  2. Very specific:

    Verify .ai/TODO.md exists under the root.

    line 37
  3. Very specific:

    If --hint matches no heading, the helper exits non-zero and lists the available sections.

    line 50
  4. Very specific:

    If useful, inspect only <repo_root>/.ai/TODO.md and the exact archive path returned by the helper.

    line 52
  5. Distinctive:

    Do not repeat full dry-run document content in the final message or add decoration to TODO/archive files, paths, commands, or helper …

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

    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:

    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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.