agentleFS
edjchapmanedjchapman/claude-code-config/skills/later/SKILL.md

later

Skill8 starsChanged 19 days agoMITView on GitHub

Create a "Later" backlog item (Learn / Research / Do / Read) from a configurable template.

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Create a new "Later" item — a personal backlog entry for things to learn, research, do, or read.

    line 8
  2. Very specific:

    If --category is missing, ask the user to choose one: Learn, Research, Do, Read.

    line 27
  3. Very specific:

    Read LATER_DIR from the environment.

    line 31
  4. Very specific:

    Look for a template file at $LATER_DIR/_template.md.

    line 32
  5. Distinctive:

    If no template file exists, fall back to this inline template:

    line 33
  6. Distinctive:

    Gather content from the user: Ask the user to provide content for each section.

    line 65

≈ “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

Create a new "Later" item — a personal backlog entry for things to learn, research, do, or read.

Backlog location: this command writes to $LATER_DIR (defaults to ~/notes/Later). Set LATER_DIR in your shell if your backlog lives elsewhere.

Arguments

$ARGUMENTS

  • First positional argument is the title (required, can be quoted for multi-word)
  • --category <name> — one of: Learn, Research, Do, Read (if omitted, ask the user)
  • --priority <level> — Low, Medium, or High (default: Medium)
  • Examples: /later "Learn Rust async/await" --category Learn --priority High, /later "Read Designing Data-Intensive Applications", /later "Set up home lab Kubernetes cluster" --category Do

Steps

  1. Parse arguments: Extract the title, --category, and --priority from $ARGUMENTS.

    • The title is everything that is not a flag or flag value. It may be quoted.
    • --priority defaults to Medium if not provided.
    • If --category is missing, ask the user to choose one: Learn, Research, Do, Read.
  2. Resolve the backlog directory and template:

    • Read LATER_DIR from the environment; if unset, default to ~/notes/Later.
    • Look for a template file at $LATER_DIR/_template.md. If it exists, use it.
    • If no template file exists, fall back to this inline template:

      # [Title]
      
      **Added:** YYYY-MM-DD
      **Priority:** Medium
      **Status:** New
      
      ## What
      
      ## Why
      
      ## Resources
      
      ## Notes
  3. Generate filename: Convert the title to kebab-case for the filename.

    Note: the inline-fallback path skips step 2 ("Read the template") since the template is already inlined above.

    • Strip special characters (slashes, colons, quotes, etc.)
    • Example: "Learn Rust Async" → learn-rust-async.md
  4. Fill in metadata: Copy the template and replace:

    • # [Title] → # <the provided title>
    • **Added:** YYYY-MM-DD → today's date
    • **Priority:** Medium → the chosen priority
    • **Status:** New → leave as New
  5. Gather content from the user: Ask the user to provide content for each section. Ask all at once or in a natural flow:

    • What — brief description of the item
    • Why — why it's worth pursuing
    • Resources — any links, books, courses (optional — skip if user has none)
    • Notes — additional context (optional — skip if user has none)
  6. Write the file: Save the completed file to $LATER_DIR/<Category>/<filename>.md (creating subdirectories as needed).
  7. Confirm: Show the user the final file path and the rendered contents.

Output

Display the created file path and its full contents so the user can verify everything looks correct.

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.