clip-tweetlisted

# /clip-tweet — Tweet Ingestion > **Tool references in this skill** (`shell`, `WebFetch`) describe **intent**, not Claude-specific tool calls. Each harness should map them to its native equivalent — Claude Code uses its built-in tools as named; Codex CLI uses `apply_patch` / shell / `--search` etc. as appropriate. Ingests a Twitter/X tweet URL into `inbox/tweets/`, fetches the content via `fetch-tweet.sh`, and generates an organized version in `_organized/`. A skill that runs `rill clip` + `/distill` Phase 2 (tweet) in one shot. ## Arguments $ARGUMENTS — Tweet URL (e.g. `https://x.com/user/status/12345`) ## Steps ### Step 1: URL Validation and Normalization 1. If the argument is empty, display "Please specify a tweet URL" and exit 2. Confirm the URL matches the pattern `https://(x.com|twitter.com)/*/status/*` 3. Strip tracking parameters (`?s=`, `&t=`, `&ref_src=`, etc.) 4. Extract `screen_name` and `tweet_id` from the URL ### Step 2: Create File in inbox/tweets/ 1. If a file with the same `tweet-id` already exists in `inbox/tweets/`, report the duplicate and skip 2. Create the file with `rill mkfile` (to guarantee timestamp accuracy): ```bash rill mkfile inbox/tweets --slug {screen_name} --field "source-type=tweet" --field 'url="{normalized URL}"' --field 'tweet-id="{tweet_id}"' ``` 3. Use the output path in subsequent steps ### Step 3: Fetch Tweet Data (Script Execution) Run the following in a shell: ``` bash plugins/twitter/fetch-tweet.sh "{normalized URL}" `