agentleFS
Sign inStart free
mpaaratingmpaarating/ai-workflow-kit/skills/watchlist/SKILL.md

watchlist

Skill2 starsChanged 8 months agoMITView on GitHub

Track movies and shows — add, rate, and get recommendations

4 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

12 rules. 0 are common, 12 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user mentions a movie or show they want to watch:

    line 22
  2. Distinctive:

    Ask for or infer genre tags: Action, Comedy, Drama, Horror, Sci-Fi, Documentary, Thriller, Animation, Romance

    line 25
  3. Distinctive:

    Add to watchlist with status "To Watch"

    line 26
  4. Distinctive:

    When the user says they finished or watched something:

    line 31
  5. Distinctive:

    Update status to "Watched" with today's date

    line 34
  6. Distinctive:

    Ask for a rating (1-5) and optional one-line review

    line 35
  7. Distinctive:

    If no rating given, prompt: "How was it?

    line 36
  8. Distinctive:

    When the user rates something not yet in the list:

    line 41
  9. Distinctive:

    Add it as "Watched" with the rating

    line 43
  10. Distinctive:

    When asked "what should I watch" or "show my watchlist":

    line 51
  11. Distinctive:

    If the user mentions a mood, map it to genres and filter:

    line 54
  12. Distinctive:

    If no matches or list is empty, offer to add something

    line 60

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Watchlist

Track what you want to watch, rate what you've seen, and get suggestions based on your taste.

Trigger Phrases

  • "want to watch"
  • "add to watchlist"
  • "watching [title]"
  • "finished [title]"
  • "rate [title]"

Workflow

Adding to watchlist

When the user mentions a movie or show they want to watch:

  1. Identify the title (and whether it's a movie or show)
  2. Ask for or infer genre tags: Action, Comedy, Drama, Horror, Sci-Fi, Documentary, Thriller, Animation, Romance
  3. Add to watchlist with status "To Watch"
  4. Confirm: Added: "Severance" (Sci-Fi, Thriller) — To Watch

Marking as watched

When the user says they finished or watched something:

  1. Find the title in the watchlist
  2. Update status to "Watched" with today's date
  3. Ask for a rating (1-5) and optional one-line review
  4. If no rating given, prompt: "How was it? (1-5)"
  5. Confirm: Updated: "Severance" — Watched (4/5) "Incredible world-building"

Rating

When the user rates something not yet in the list:

  1. Add it as "Watched" with the rating
  2. Accept optional review text
  3. Confirm the entry

Rating scale: 5 (loved it), 4 (really good), 3 (decent), 2 (disappointing), 1 (skip it)

Listing and suggestions

When asked "what should I watch" or "show my watchlist":

  1. Show unwatched items grouped by genre
  2. If the user mentions a mood, map it to genres and filter:
    • "something light" → Comedy, Animation, Romance
    • "something intense" → Thriller, Horror, Drama
    • "something smart" → Sci-Fi, Documentary, Drama
    • "something fun" → Action, Comedy, Animation
  3. Suggest 1-3 matching titles from their list
  4. If no matches or list is empty, offer to add something

Storage

Using {{notes}}: Store as a database with fields: Title, Type (Movie/Show), Genre, Status (To Watch/Watching/Watched), Rating, Review, Date Added, Date Watched.

Markdown fallback: Store in ~/.ai-workflow/watchlist.md:

## To Watch
- **Severance** (Show) — Sci-Fi, Thriller — Added Mar 19

## Watched
- **The Brutalist** (Movie) — Drama — 4/5 — "Ambitious and gorgeous" — Mar 15

Examples

Add to watchlist:

want to watch The White Lotus

Added: "The White Lotus" (Show) — Comedy, Drama — To Watch

Finish and rate:

finished Severance, it was incredible. 5/5

Updated: "Severance" — Watched (5/5) "Incredible"

Get suggestion:

what should I watch tonight? something light

From your watchlist:
1. The White Lotus — Comedy, Drama
2. Poker Face — Comedy, Mystery

Both are lighter shows. Want to start one?

Quick rating for something not on the list:

rate Oppenheimer 4/5 — stunning visuals but long

Added: "Oppenheimer" (Movie) — Drama — Watched (4/5) "Stunning visuals but long"

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.

Check your setup, free