fetch-tweets

type	Skill
name	Fetch Tweets
category	basics
description	Search and curate X/Twitter behind one selector - keyword, topic roundup, a single or tracked-account digest, an X list, or the AI-agent buzz preset - clustered into signal-scored sub-narratives.
var
tags	["social"]
requires	["XAI_API_KEY?"]

${var} — <source>:<arg> where <source> ∈ keyword | topic | account | list | agent-buzz. The <arg> is source-specific (a query, a topic, a handle, comma-separated list IDs, or an optional focus). If no source: prefix is given, the source is inferred from the shape of <arg> (see Source selector). Required for keyword and list; optional for topic, account, and agent-buzz.

Today is ${today}. This skill fetches X/Twitter content along one of five source axes and produces a curated digest — clustered by sub-narrative, ranked by signal, one insight per item — never a flat chronological dump.

Source selector

Parse ${var} into SOURCE and ARG before doing anything else.

Explicit form (recommended): <source>:<arg>

• keyword:$SOL OR solana OR "solana network" — raw X search query, passed to Grok verbatim (OR/AND honored).
• topic:brain-computer interfaces — a single topic roundup. topic: (empty arg) → resolve a topic list from MEMORY.md, then built-in defaults.
• account:vitalikbuterin — one account's recent tweets. account: (empty arg) → digest every handle in memory/topics/tracked-accounts.yml.
• list:1953536336675365173,1937207796270829766 — one or more numeric X list IDs. Append |<topic> for a topic booster: list:195...,193...|AI agents.
• agent-buzz — the curated AI-agent-ecosystem preset. agent-buzz:MCP protocol prioritizes a project/topic within the preset.

Implicit form (back-compat with migrated bare-var configs): when ${var} has no recognized source: prefix, infer SOURCE in this order:

1. ${var} is empty → topic (default multi-topic roundup).
2. ${var} is all-digits, or comma-separated all-digits (optionally with a |<topic> suffix) → list.
3. ${var} is @handle or matches ^[A-Za-z0-9_]{1,15}$ (a bare handle) → account.
4. Anything else → keyword.

Note: agent-buzz has no distinct implicit shape (its arg looks like a keyword/topic), so it is only selectable via the explicit agent-buzz / agent-buzz:... prefix.

Once SOURCE and ARG are set, jump to the matching branch below. Only one branch runs per invocation.

Shared preamble (all branches)

1. Read memory/MEMORY.md for context and the recent memory/logs/ (each branch specifies its lookback window — 2 or 3 days) to dedup already-reported tweets.

2. Load the dedup set SEEN_TWEETS by unioning two sources:

   • The branch's persistent seen-file (per-mode path below), if it exists — read all URLs.
   • The branch's log lookback window — grep each memory/logs/*.md file in range for lines matching https://x.com/.

   Per-mode seen-files (kept at their legacy paths so dedup history survives the merge):

   mode	seen-file	log lookback
   keyword	memory/fetch-tweets-seen.txt	3 days
   topic	memory/tweet-roundup-seen.txt	3 days
   account	(logs only — see branch)	2 days
   list	memory/list-digest-seen.txt	2 days
   agent-buzz	(logs only — 3-day status/<id> set)	3 days

3. Formatting invariants shared by every branch's notification:

   • Use x.com/handle (never @handle) so Telegram doesn't ping/tag users. (Exception: the account-digest and agent-buzz formats below historically use @handle in-body; keep their documented format but prefer x.com/handle when practical.)
   • Every surviving tweet gets a tappable Markdown link — [View](url) / [View tweet](url). If a URL is unavailable, drop the link and say "(link unavailable)".
   • Never fabricate engagement counts. Missing → 0, not a guess.
   • Notify only on signal. A legitimately empty or all-duplicate run logs its status and sends nothing.

Voice

Used by the account and agent-buzz branches for one-line takes/insights. If soul/SOUL.md and soul/STYLE.md are populated, read both and match the operator's voice. If they are empty templates or absent, write in a clear, direct, neutral tone — state what the tweet says, no hedging or editorializing beyond the tweet itself.

---

Branch: keyword (source:keyword)

Search X for tweets matching ARG and produce a curated digest grouped by sub-narrative.

Seen set: memory/fetch-tweets-seen.txt + last 3 days of logs (loaded in preamble).

1. Build the search prompt. Pass ARG to Grok verbatim as the query — do NOT narrow it to a single angle; broad coverage is the goal. Ask for at least 15–20 candidate tweets (you'll cull to ~7–10). Always require explicit engagement counts (likes, retweets, replies) so ranking is data-driven.

2. Fetch tweets. Record SOURCE_PATH=api|websearch for the log.

   Path A — X.AI API (primary; see the Fetching (all branches) contract — attempt this, set the Bash tool timeout ≥180000, capture the HTTP status):

   FROM_DATE=$(date -u -d "yesterday" +%Y-%m-%d 2>/dev/null || date -u -v-1d +%Y-%m-%d)
   TO_DATE=$(date -u +%Y-%m-%d)
   PROMPT="Search X for tweets about: ${ARG}. Date range: ${FROM_DATE} to ${TO_DATE}. Return at least 15-20 candidate tweets — mix of high-engagement posts and smaller accounts that add a distinct angle. For each tweet include: @handle, the full text, date posted, exact engagement counts (likes, retweets, replies — never N/A; if unknown, say 0), and the direct link (https://x.com/handle/status/ID). Return as a numbered list."
   jq -n --arg p "$PROMPT" '{model:"grok-4.3", input:[{role:"user",content:$p}], tools:[{type:"x_search"}]}' > /tmp/xai-ft-keyword.json
   HTTP=$(./secretcurl -s -o /tmp/xai.json -w '%{http_code}' --max-time 150 -X POST "https://api.x.ai/v1/responses" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer {XAI_API_KEY}" \
     -d @/tmp/xai-ft-keyword.json)
   echo "xai http=$HTTP bytes=$(wc -c </tmp/xai.json)"
   

   On HTTP=200, parse /tmp/xai.json with: jq -r '.output[] | select(.type == "message") | .content[] | select(.type == "output_text") | .text' and mark SOURCE_PATH=api.

   Path B — WebSearch fallback (only if the key is KEY_UNSET, or Path A gave a non-2xx / empty / timeout per the contract): use the built-in WebSearch tool with site:x.com "<query terms>" after:${FROM_DATE}. Note at the top of the log the true reason (http-<code> / timeout / empty, never "unavailable" when the key was set) and "results compiled via WebSearch — quality lower than usual". WebSearch favours high-engagement older tweets — prioritise results dated within the last 48 hours. Mark SOURCE_PATH=websearch.

3. Empty vs. error handling (distinguish):

   • Legitimate empty (0 tweets): log and .

Status codes: FETCH_TWEETS_OK (notified) | FETCH_TWEETS_EMPTY | FETCH_TWEETS_ERROR | FETCH_TWEETS_NO_NEW.

---

Branch: topic (source:topic)

Gist of the latest X chatter on one or more configurable topics.

Seen set: memory/tweet-roundup-seen.txt + last 3 days of logs.

1. Resolve the topic list (priority order):

   1. ARG set → TOPICS=("$ARG") (single-topic mode).
   2. Else if MEMORY.md has a ## Tweet Roundup Topics section → use its bulleted lines, one query per line.
   3. Else built-in defaults:
      • artificial intelligence OR AI agents OR LLM
      • crypto OR bitcoin OR DeFi
      • technology OR startups OR open source

2. Fetch per topic — track SOURCE ∈ {api, websearch, failed} per topic.

   Path A — direct X.AI curl (primary): for each topic, call Grok's x_search.

   FROM_DATE=$(date -u -d "yesterday" +%Y-%m-%d 2>/dev/null || date -u -v-1d +%Y-%m-%d)
   TO_DATE=$(date -u +%Y-%m-%d)
   PROMPT="Search X for recent tweets about: ${TOPIC}. Date range: ${FROM_DATE} to ${TO_DATE}. Return up to 8 substantive tweets. For each: @handle, full text, date, exact engagement counts (likes, retweets, replies; 0 if unknown), and the direct link https://x.com/handle/status/ID."
   jq -n --arg p "$PROMPT" '{model:"grok-4.3", input:[{role:"user",content:$p}], tools:[{type:"x_search"}]}' > /tmp/xai-ft-topic.json
   ./secretcurl -s -o /tmp/xai-topic-out.json -X POST "https://api.x.ai/v1/responses" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer {XAI_API_KEY}" \
     -d @/tmp/xai-ft-topic.json
   

   Parse with the standard jq extractor. If it yields text, SOURCE=api. Extract each tweet's @handle, text, engagement counts, and permalink.

   Path B — WebSearch fallback (only if XAI_API_KEY unset, or Path A errors/empty): site:x.com "<topic keywords>" after:<YESTERDAY>. Always include the word "today" and ${today} to force fresh results. Discard any result whose visible date is older than 48h. Collect up to 5 candidates per topic. Mark SOURCE=websearch. If both paths return nothing, mark SOURCE=failed.

3. Score and filter. Require: a known @handle; a https://x.com/<handle>/status/<id> URL (if missing, keep but mark "link unavailable"); posted within 48h; URL not in SEEN_TWEETS. Compute signal_score = likes + 2×retweets + replies (on WebSearch path with no counts, use result rank as a weak proxy). : replies to a parent tweet; near-duplicates of a higher-scoring tweet (>70% text overlap or same linked URL).

Constraints: never notify an empty roundup (silence beats filler); never @handle anyone; never report a URL already in SEEN_TWEETS. Status codes: TWEET_ROUNDUP_OK | TWEET_ROUNDUP_EMPTY.

---

Branch: account (source:account)

Two sub-modes: single handle (decision-ready gist of one account) vs. all tracked accounts (theme-grouped digest of a watchlist). Choose by ARG.

Seen set: last 2 days of logs — extract every https://x.com/ URL under a prior ### fetch-tweets account entry into SEEN_URLS.

account — single handle (ARG is one @handle)

1. Normalize ARG. Strip leading @, https://x.com/, https://twitter.com/, https://nitter.net/, trailing slash / /status/.... Lowercase. Reject if empty, contains whitespace, or >15 chars. On reject → REFRESH_X_NO_VAR: send ./notify "fetch-tweets: REFRESH_X_NO_VAR — set an X handle" and exit 0. Store the cleaned handle as ACCOUNT.

2. Load tweets:

   • Path A — X.AI API (primary): search this account's recent tweets via Grok's x_search.

     PROMPT="Search X for the latest tweets, replies, and quote tweets from @${ACCOUNT} in the last 2 days. Return each with full text, timestamp, type (original|reply|quote), what it replies to/quotes if any, exact engagement counts (likes, retweets, replies; 0 if unknown), and the permalink https://x.com/${ACCOUNT}/status/ID. Skip retweets of others. Return chronological."
     jq -n --arg p "$PROMPT" '{model:"grok-4.3", input:[{role:"user",content:$p}], tools:[{type:"x_search"}]}' > /tmp/xai-ft-account.json
     ./secretcurl -m 30 -s -o /tmp/xai-account-out.json -X POST "https://api.x.ai/v1/responses" \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer {XAI_API_KEY}" \
       -d @/tmp/xai-ft-account.json
     

     Parse with the standard jq extractor. Record source=api.
   • Path B — WebFetch fallback (only if XAI_API_KEY unset, or Path A errors / parsed text has zero x.com status URLs): WebFetch https://x.com/${ACCOUNT} with prompt: "List every tweet, reply, and quote tweet visible on this profile with its full text, timestamp, engagement counts (likes/retweets/replies) if shown, and the permalink https://x.com/handle/status/ID. Return a chronological list." Record source=webfetch.
   • Path C — degraded: if XAI_API_KEY unset and WebFetch returns nothing → skip to step 8 with status REFRESH_X_NO_API_KEY (key missing) or REFRESH_X_ERROR (key set but both paths failed).

3. Parse into structured tweets: url, text, timestamp, type (original/reply/quote), reply_to, quoted_text, , , . Drop retweets of others. Missing counts → 0. Compute .

Constraints: never fabricate engagement; never include a SEEN_URLS URL; an insight that only paraphrases is not an insight (drop the cluster); MEMORY.md updates are one line each. Status codes: REFRESH_X_OK | REFRESH_X_EMPTY | REFRESH_X_NO_NEW | REFRESH_X_NO_API_KEY | REFRESH_X_ERROR | REFRESH_X_NO_VAR.

account — all tracked accounts (ARG empty)

Use this to answer "what did these specific people post" across a watchlist.

1. Read config memory/topics/tracked-accounts.yml. If missing or accounts: [] → log TWEET_DIGEST_NO_CONFIG and exit (no notification). Schema:

   accounts:
     - handle: vitalikbuterin
       why: ethereum core thinking      # optional — grouping/context label
     - handle: balajis
       why: macro + tech narratives
   

2. Fetch recent tweets per account. For each handle:

   • Path A — live curl (primary, XAI_API_KEY is injected and set):

     PROMPT="Search X for the latest tweets from:${HANDLE} in the last 3 days. Return the 5 most interesting or substantive tweets. For each: full text, date, direct link (https://x.com/${HANDLE}/status/ID). Skip retweets of others."
     jq -n --arg p "$PROMPT" '{model:"grok-4.3", input:[{role:"user",content:$p}], tools:[{type:"x_search"}]}' > /tmp/xai-ft-acct1.json
     ./secretcurl -m 30 -s -o /tmp/xai-acct1-out.json -X POST "https://api.x.ai/v1/responses" \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer {XAI_API_KEY}" \
       -d @/tmp/xai-ft-acct1.json
     

     Parse with the standard jq extractor. If XAI_API_KEY is unset, log TWEET_DIGEST_NO_KEY: skill requires XAI_API_KEY and exit (no notification). Dedup: drop any candidate URL already in SEEN_URLS (last 2 days of logs).

3. Group by theme, not by account. Walk the full candidate set; identify 2–4 themes (e.g. "L2 design decisions", "macro / rates", "AI model releases", "regulation"). Each tweet maps to one theme; a why: label can seed theme naming for single-topic feeds.

4. Write a one-sentence take per notable tweet — what the tweet says, not your opinion of it. Voice per the Voice section.

5. Notify via ./notify:

   *Tweet Digest — ${today}*
   
   *Theme: <theme>*
   @handle: <one-sentence summary> — [link](url)
   @handle: <one-sentence summary> — [link](url)
   
   *Theme: <theme>*
   ...
   

   If no notable tweets across all accounts: log TWEET_DIGEST_OK and end (no notification).

Status codes: TWEET_DIGEST_OK (notified or clean) | TWEET_DIGEST_NO_CONFIG | TWEET_DIGEST_NO_KEY.

---

Branch: list (source:list)

Cross-list narrative resonance + signal-scored top tweets from tracked X lists in the past 24h. Lists are curator signal — the value is cross-list resonance + insight + a verdict, not a flat top-N-per-list dump.

Seen set: memory/list-digest-seen.txt + last 2 days of logs.

1. Parse and validate ARG.

   if [ -z "$ARG" ]; then
     echo "LIST_DIGEST_NO_CONFIG: var must contain at least one X list ID" \
       >> "memory/logs/$(date -u +%Y-%m-%d).md"
     exit 0
   fi
   IDS_PART="${ARG%%|*}"
   TOPIC_FILTER=""
   [ "$ARG" != "$IDS_PART" ] && TOPIC_FILTER="${ARG#*|}"
   for LIST_ID in $(echo "$IDS_PART" | tr ',' ' '); do
     if ! [[ "$LIST_ID" =~ ^[0-9]+$ ]]; then
       echo "LIST_DIGEST_NO_CONFIG: invalid list ID '$LIST_ID' (must be numeric)" \
         >> "memory/logs/$(date -u +%Y-%m-%d).md"
       exit 0
     fi
   done
   

   If XAI_API_KEY is unset, fall back to Path B. If no path returns data, log LIST_DIGEST_NO_CONFIG: XAI_API_KEY required and stop without notifying.

2. Fetch each list's top tweets (past 24h) — API primary, WebSearch fallback. Path A — X.AI Responses API (primary):

   FROM_DATE=$(date -u -d "yesterday" +%Y-%m-%d 2>/dev/null || date -u -v-1d +%Y-%m-%d)
   TO_DATE=$(date -u +%Y-%m-%d)
   PROMPT="Look at X list https://x.com/i/lists/${LIST_ID}. Step 1: report the list name and a one-line description. Step 2: identify the most engaging tweets posted by members of this list between ${FROM_DATE} and ${TO_DATE} UTC. Return the top 12 tweets ranked by engagement (likes, retweets, replies). For EACH tweet you MUST return: (a) @handle, (b) the full tweet text (not a paraphrase), (c) explicit engagement counts as separate fields — likes:N, retweets:N, replies:N, views:N if available, (d) the direct permalink in the form https://x.com/<handle>/status/<id>, (e) media type (image|video|none), (f) one-line context if it's a reply or quote tweet (who/what). Skip retweets of accounts NOT on this list. If a tweet has an image and you can analyze it, include a one-line image description."
   jq -n --arg p "$PROMPT" --arg fd "$FROM_DATE" --arg td "$TO_DATE" \
     '{model:"grok-4.3", input:[{role:"user",content:$p}], tools:[{type:"x_search", from_date:$fd, to_date:$td, enable_image_understanding:true}]}' \
     > /tmp/xai-ft-list.json
   ./secretcurl -s -o /tmp/xai-list-out.json --max-time 180 -X POST "https://api.x.ai/v1/responses" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer {XAI_API_KEY}" \
     -d @/tmp/xai-ft-list.json
   

   Parse with the standard jq extractor. Path B — WebSearch fallback (only if XAI_API_KEY unset, OR Path A errors / returns nothing): site:x.com "i/lists/${LIST_ID}" OR list:${LIST_ID} after:${FROM_DATE}. Lower quality; mark this list's source as websearch. Per-list outcome: ok (≥3 tweets) | quiet (1–2) | empty (0, list found but no posts) | (API/access failure — note reason).

Exit taxonomy: LIST_DIGEST_NO_CONFIG (var empty/invalid OR no fetch path — log only) | LIST_DIGEST_EMPTY (every list 0 tweets OR all candidates already seen — log only) | LIST_DIGEST_PARTIAL (some lists succeeded/some failed — notify survivors, surface failures) | LIST_DIGEST_OK (≥1 fresh tweet — notify).

---

Branch: agent-buzz (source:agent-buzz)

A topic-filtered preset: a curated, narrative-aware read on what the AI-agent scene on X talked about in the last 24h. Curation, not aggregation — 6 high-signal tweets in 2 clusters beats 10 of mixed noise. ARG (optional) is a project/topic to prioritize.

Seen set: last 3 days of logs — extract every https://x.com/.../status/<id> already posted by this skill; treat those IDs as the dedup set.

1. Fetch candidates:

   FROM_DATE=$(date -u -d "1 day ago" +%Y-%m-%d 2>/dev/null || date -u -v-1d +%Y-%m-%d)
   TO_DATE=$(date -u +%Y-%m-%d)
   

   Path A — X.AI API (primary; the response for each tweet must include explicit engagement counts + follower count, or step 3 scoring can't run):

   PROMPT="Search X from ${FROM_DATE} to ${TO_DATE} for tweets in the AI-agents conversation: autonomous agents, agent frameworks, MCP / agent protocols, agent products, agent benchmarks, agent research papers. Return up to 40 candidates. For EACH candidate you MUST return: @handle, follower_count (integer or null), role_guess (builder|founder|researcher|investor|commentator|anon), one-line claim (what they actually said — not a paraphrase, the thesis), likes (int), retweets (int), replies (int), posted_at (ISO), direct_link (https://x.com/username/status/ID). Prefer builders/founders/researchers. Skip obvious engagement-farming threads (\"RT if you agree\", reply-guy pileons, giveaways)."
   jq -n --arg p "$PROMPT" --arg fd "$FROM_DATE" --arg td "$TO_DATE" \
     '{model:"grok-4.3", input:[{role:"user",content:$p}], tools:[{type:"x_search", from_date:$fd, to_date:$td}]}' \
     > /tmp/xai-ft-buzz.json
   ./secretcurl -s -o /tmp/xai-buzz-out.json -X POST "https://api.x.ai/v1/responses" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer {XAI_API_KEY}" \
     -d @/tmp/xai-ft-buzz.json
   

   Parse with the standard jq extractor. Record source=xai. Path B — WebSearch fallback (only if XAI_API_KEY unset, or Path A errors/empty): forced-fresh query "AI agents twitter today ${today}" — discard anything >48h old, expect degraded metadata. Record source=websearch.

   If ARG is set, also issue a second call constrained to that topic with the same schema; merge results.

2. Skip-gates (before clustering) — drop any candidate matching ANY:

   • Dup: status/<id> already in the 3-day dedup set.
   • Engagement-farming: poll threads, "bookmark this", "drop a 🔥", reply-guy pileons with <follower_count/10 likes.
   • Self-promo only: pure product shill with no claim/benchmark/datapoint. Launch tweets OK IF they include a concrete capability claim or number.
   • Staleness: posted_at older than 30h.
   • Anon + low engagement: role_guess=anon AND (likes+retweets) < 200.

Status codes: AGENT_BUZZ_OK (≥1 cluster notified) | AGENT_BUZZ_EMPTY (fetch succeeded, nothing survived — send Agent Buzz — ${today}: quiet day, no survivors.) | AGENT_BUZZ_ERROR (all sources failed — notify Agent Buzz — ${today}: all sources failed (${error summary}). and log the per-source failure).

---

Log (all branches)

Append ONE entry per run to memory/logs/${today}.md under a single ### fetch-tweets heading (the health loop parses this shape). The first bullet is the discriminator naming the branch/mode that ran; the rest are branch-specific bullets. Always include the reported tweet URLs as bullets (for next-run dedup).

### fetch-tweets
- mode: <keyword|topic|account|list|agent-buzz>
- status: <STATUS_CODE for the branch that ran>
- source: <SOURCE_PATH / per-source counts / per-list outcome, as applicable>
- <branch-specific bullets — carry over each branch's fields:>
    - keyword:     signal one-liner; per-cluster URLs with `likes:N rts:N replies:N` + insight
    - topic:       `topics: [t1: N tweets, t2: 0 (dropped)]`; `source: cache:X websearch:Y failed:Z`
    - account(1):  Verdict + lede; Counts (N tweets, X orig/Y reply/Z quote, T threads, deduped K); Clusters; Threads; Vibe
    - account(all):themes covered; per-account tweet counts
    - list:        Lists tracked; Per-list `list1=ok(N) | list2=quiet(N) | list3=error`; Verdict; Narratives count
    - agent-buzz:  source used; candidates N → kept M; cluster names
- urls:
    - https://x.com/handle1/status/...
    - https://x.com/handle2/status/...

On empty/no-new/error/no-config statuses, write the ### fetch-tweets heading + mode: + status: bullets only (skip the detail sections) so skill-health still observes the run. After logging, update the branch's persistent seen-file where one exists (keyword / topic / list — see the seen-file table).

Output shape note

No chain consumes this skill's output as of this commit (no consume: [fetch-tweets] references). If a downstream chain step starts consuming it, emit a flat list of URLs before the clustered/branch output so consumers aren't broken by cluster or narrative headers.

Fetching (all branches)

XAI_API_KEY is injected into your environment for this skill (declared in requires:). It is present and valid. The primary fetch path in every branch is a direct curl to https://api.x.ai/v1/responses with Authorization: Bearer {XAI_API_KEY}. There is no network sandbox blocking this; earlier versions of this skill claimed there was — that is stale and wrong. Just make the call.

You MUST attempt the direct curl before any fallback. The rules:

1. Check, don't assume. Run [ -n "$XAI_API_KEY" ] && echo KEY_PRESENT || echo KEY_UNSET. If KEY_PRESENT (it will be), you are required to try Path A.
2. Allow enough time. The x_search call typically takes 30–120s (it searches X live). When you invoke the Bash tool for the curl, set the tool's timeout to at least 180000 (180s), and add --max-time 150 to the curl itself so it fails cleanly rather than hanging. A curl that is slow is not a missing key — do not treat a timeout as "key unavailable".
3. Capture the HTTP status so the fallback decision is based on fact, not assumption. Build the JSON body to a fixed file with jq -n first (as each branch above does), then send it with -d @file — every ./secretcurl command must be 100% literal (no $VAR, or the permission layer blocks it):

   HTTP=$(./secretcurl -s -o /tmp/xai.json -w '%{http_code}' --max-time 150 -X POST "https://api.x.ai/v1/responses" \
     -H "Content-Type: application/json" -H "Authorization: Bearer {XAI_API_KEY}" -d @/tmp/xai-ft-keyword.json)
   echo "xai http=$HTTP bytes=$(wc -c </tmp/xai.json)"
   

   Then parse /tmp/xai.json with the standard jq extractor. HTTP=200 with non-empty body → use it (SOURCE_PATH=api).
4. Fall back only on a real failure, and record the true reason — never write "XAI_API_KEY unavailable" when the key was set. Use one of: key-unset (only if step 1 said KEY_UNSET), http-<code> (non-2xx), empty (200 but no tweets parsed), timeout (curl exceeded --max-time).

WebSearch / WebFetch are last-resort fallbacks only — lower quality (WebSearch favours old high-engagement tweets). Never reach for them while the key works.

Environment Variables

• XAI_API_KEY — X.AI API key for Grok's x_search tool. Declared in requires:, so it is injected into this skill's environment and is the primary fetch path for every branch. If it is ever unset, branches degrade to WebSearch/WebFetch at lower quality; the account (all) sub-mode instead hard-exits (TWEET_DIGEST_NO_KEY).