SkillAgentSearch skills...

x-keyword-comment

X (Twitter) keyword-based reply posting: search tweets by keyword, read each tweet's content, generate contextual replies from a configured brand persona, and post replies to the reply area

Install / Use

npx skills add browser-act/skills --skill x-keyword-comment

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

96/100

Category

Marketing

Supported Platforms

Universal

Tags

Our assessment of x-keyword-comment

x-keyword-comment scores 96/100 on our quality scale, 57th of 642 Marketing skills we index (top 9%).

Its SKILL.md is 16 KB long, well organised into 23 sections with 14 code examples: a thorough specification that gives an agent plenty to work with.

With 6,001 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
16/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 3 months ago, so x-keyword-comment is actively maintained.
  • Our last check on 2026-11-15 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

x-keyword-comment compared with similar skills

All 4 of these similar skills score higher than x-keyword-comment; compare them before choosing.

SkillScoreStarsUpdatedFormat
x-keyword-comment (this skill)by browser-act966.0k3mo agoSKILL.md
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md
pptxby anthropics100177.9k55d agoSKILL.md
designby nextlevelbuilder100149.0k6d agoSKILL.md

Frequently asked questions

How do I install x-keyword-comment?
Run npx skills add browser-act/skills --skill x-keyword-comment. The install tabs above show the steps for each supported agent.
Which AI agents does x-keyword-comment work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is x-keyword-comment safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is x-keyword-comment still maintained?
The repository was last updated about 3 months ago, so x-keyword-comment is actively maintained.

name: x-keyword-comment description: "X (Twitter) keyword-based reply posting: search tweets by keyword, read each tweet's content, generate contextual replies from a configured brand persona, and post replies to the reply area. Use when user wants to batch reply to X tweets by keyword, auto-comment on X topic tweets, drive traffic via X comments, X comment outreach, search X tweets and leave comments, bulk reply to Twitter search results, keyword comment on Twitter, post replies on X search page, Twitter keyword comment marketing, X reply campaign, engage with X discussions, or comment on tweets matching a topic."

X — Keyword Comment

keyword + reply intent → search X tweets → read tweet content → generate contextual replies → post to reply area

Language

All process output to user (progress updates, process notifications) follows the user's language.

Objective

Search X by keyword, read each tweet's content, generate contextual replies based on a configured brand persona, and post them — all within a browser-act session.

Prerequisites

  • config/keyword-comment-config.json has been filled in with actual product, persona, and tone values (all YOUR_* placeholders replaced before first run)

Session Rule

{SESSION} is a temporary, per-run session name used in all browser-act --session {SESSION} commands below. It is generated at execution start (e.g., xkc-{timestamp}) and not persisted across runs.

Pre-execution Checks

1. Tool Readiness

If browser-act has been confirmed available in the current conversation → skip this step.

Invoke browser-act via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.

2. Load Config

python -c "
import json, pathlib, sys
for base in ['.claude/skills/x-keyword-comment', 'output/x-keyword-comment']:
    cfg = pathlib.Path(base) / 'config/keyword-comment-config.json'
    if cfg.exists():
        print(json.dumps(json.loads(cfg.read_text(encoding='utf-8')), ensure_ascii=False, indent=2))
        sys.exit(0)
print('ERROR: config/keyword-comment-config.json not found', file=sys.stderr)
sys.exit(1)
"

Hold product.*, persona.*, tone.* fields in working memory for reply composition.

3. Browser Selection

List available browsers:

browser-act browser list
  • If browsers exist → present the list to the user and let them choose which browser to use for this X session.
  • If no browsers exist → guide the user to create one (e.g., browser-act browser create --type stealth --headed), then repeat the list step.

Once the user selects a browser, record its ID as {BROWSER_ID} for this run.

4. Open Session

Generate a unique session name (e.g., xkc-{timestamp}) as {SESSION}. Open the browser:

browser-act --session {SESSION} browser open {BROWSER_ID} https://x.com/ --headed

If the browser is already open with an active session, list sessions and reuse:

browser-act session list

Pick the session associated with {BROWSER_ID} and assign its name to {SESSION}.

5. Login Verification

If X login status has been confirmed in the current conversation → skip this step.

Otherwise: browser-act --session {SESSION} get markdown and check:

  • Sidebar bottom shows @username, top navigation shows Home / Explore → logged in, continue
  • Page shows a "Sign in" button with no logout entry → not logged in; inform the user that login is required and assist the login flow

User refuses or cannot log in → terminate execution.

Capability Components

This Skill's operational boundary = what the user can manually do in their browser. It only reads data already displayed to the logged-in user, never bypassing authentication or access controls. JS code is encapsulated in Python files under scripts/, invoked via browser-act --session {SESSION} eval "$(python scripts/xxx.py {params})". $(...) is bash syntax; use the bash tool for execution.

Below are all atomic capabilities discovered and verified during the exploration phase, listed by command template with parameters. Simply invoke them as needed — no need to read scripts/*.py source code or re-verify. Only inspect scripts when execution fails for troubleshooting. Combine freely as needed during execution.

AI Workflow: Pre-reply Warmup

Warm up the account before posting replies to simulate organic browsing behavior.

Skip condition: warmup already performed today and less than 4 hours ago, or user says "fast mode".

Step 1 — Check notifications and messages (2–3 min)

browser-act --session {SESSION} navigate "https://x.com/notifications"
browser-act --session {SESSION} wait stable
browser-act --session {SESSION} get markdown
sleep $((RANDOM % 31 + 60))   # 60–90 s
browser-act --session {SESSION} navigate "https://x.com/messages"
browser-act --session {SESSION} wait stable
browser-act --session {SESSION} get markdown
sleep $((RANDOM % 31 + 30))   # 30–60 s

Step 2 — Browse feed and like (3–5 min)

browser-act --session {SESSION} navigate "https://x.com/home"
browser-act --session {SESSION} wait stable
browser-act --session {SESSION} get markdown

Randomly pick 3–5 tweets from the feed. For each:

browser-act --session {SESSION} navigate "{tweet URL}"
browser-act --session {SESSION} wait stable
sleep $((RANDOM % 26 + 15))   # 15–40 s
# If content is relevant → like it:
browser-act --session {SESSION} state
browser-act --session {SESSION} click {Heart index}   # element with aria-label containing "Like"
browser-act --session {SESSION} wait stable
sleep $((RANDOM % 8 + 8))     # 8–15 s
browser-act --session {SESSION} navigate "https://x.com/home"
sleep $((RANDOM % 16 + 10))   # 10–25 s

Target: like 1–3 tweets; daily cap 20–30 likes (avoid fast bulk likes that trigger rate limits).

Step 3 — Keyword search browsing (2–3 min)

browser-act --session {SESSION} navigate "https://x.com/search?q={KEYWORD_ENCODED}&f=live"
browser-act --session {SESSION} wait stable
browser-act --session {SESSION} get markdown

Open 2–3 results, spend 25–60 s each reading the full tweet (as reply material).

Pre-action pause

sleep $((RANDOM % 61 + 60))   # 60–120 s — simulate "browse first, then reply"

DOM: Scan Replyable Tweets on Current Page

After navigating to the X search results page, scan all tweets with their reply button indices and content.

  1. Navigate: browser-act --session {SESSION} navigate "https://x.com/search?q={KEYWORD_ENCODED}&src=typed_query&f=live"
    • {KEYWORD_ENCODED} is URL-encoded (spaces as %20)
    • f=live returns newest tweets; omit for Top tweets
  2. Wait: browser-act --session {SESSION} wait stable --timeout 30000
  3. (Optional) Scroll to load more: browser-act --session {SESSION} scroll down --amount 1500 → browser-act --session {SESSION} wait stable --timeout 10000 → re-scan
  4. Scan: browser-act --session {SESSION} eval "$(python scripts/scan-search-tweets.py --limit {N})"

Parameters:

  • --limit: max tweets to return, default 10

Output example:

{
  "totalReplyBtns": 8,
  "tweets": [
    {
      "i": 0,
      "tweetSnippet": "Breaking: Alibaba just killed the browser automation stack...",
      "authorHandle": "@AIGuideHQ",
      "authorUrl": "https://x.com/AIGuideHQ",
      "tweetUrl": "https://x.com/AIGuideHQ/status/2051969984847286536",
      "replyBtnIdx": 0
    }
  ]
}

replyBtnIdx note: This is the reply button's position index among all [data-testid="reply"] buttons currently on the page. After posting a reply, the DOM partially updates (new reply inserts), shifting subsequent indices — re-run scan-search-tweets.py after each reply to get fresh indices before the next one.

DOM: Click Reply Button (Open Editor)

Click the reply button for a specific tweet to open the reply input box.

browser-act --session {SESSION} eval "$(python scripts/click-reply.py {replyBtnIdx})"

Parameters:

  • {replyBtnIdx}: the tweet's reply button index (positional argument, from scan-search-tweets.py)

Output example (success):

{
  "ok": true,
  "replyBtnFound": true,
  "totalReplyBtns": 8
}

Output example (out of range):

{
  "ok": false,
  "reason": "reply_btn_out_of_range",
  "total": 8
}

DOM: Type Reply Text and Submit (Operation)

Architecture note: X uses the Draft.js editor (public-DraftEditor-content). document.execCommand('insertText') only updates the DOM without triggering React internal state — the submit button stays disabled. You must use browser-act's native input command to simulate real keyboard input to activate the submit button. This is the only reliable method.

After clicking the reply button (click-reply.py), complete text input and submission:

  1. Wait for editor mount: browser-act --session {SESSION} wait --selector '[data-testid="tweetTextarea_0"]' --state attached --timeout 10000
  2. Get editor index: browser-act --session {SESSION} state → find aria-label=Post text role=textbox → note {EDITOR_IDX}
  3. Input reply text: browser-act --session {SESSION} input {EDITOR_IDX} '{reply_text}'
  4. Get submit button index: browser-act --session {SESSION} state → find button labeled Reply → note {REPLY_BTN_IDX}
  5. Submit: browser-act --session {SESSION} click {REPLY_BTN_IDX}
  6. Wait: browser-act --session {SESSION} wait stable --timeout 10000

Success signal: browser-act --session {SESSION} network requests --filter CreateTweet --method POST --status 200 returns at least 1 record.

Closing the editor: If the editor is empty, pressing Escape dismisses it directly with no dialog. If text has been typed and Escape is pressed (or the modal is otherwise closed), X shows a "Save post?" confirmation dialog (Save / Discard). To discard: browser-act --session {SESSION} state → find Discard button index → browser-act --session {SESSION} click {DISCARD_IDX}

Composite: Full Keyword Reply Flow

All operations remain on the X search page — no navigation to individual tweet detail pages required.

Config: Load config/keyword-comment-config.json and hold product.*, persona.*, tone.* fields in working memory before proceeding:

python -c "
import json, pathlib, sys
for base in ['.claude/skills/x-keyword-comment', 'output/x-keyword-comment']:
    cfg = pathlib.Path(base) / 'config/keyword-comment-config.json'
    if cfg.exists():
        print(json.dumps(json.loads(cfg.read_text(encoding='utf-8')), ensure_ascii=False, indent=2))
        sys.exit(0)
print('ERROR: config/keyword-comment-config.json not found', file=sys.stderr)
sys.exit(1)
"
  1. browser-act --session {SESSION} navigate "https://x.com/search?q={KEYWORD_ENCODED}&src=typed_query&f=live" → browser-act --session {SESSION} wait stable --timeout 30000
  2. Initial scan: browser-act --session {SESSION} eval "$(python scripts/scan-search-tweets.py --limit {N})" → candidate tweet list
  3. If not enough candidates → browser-act --session {SESSION} scroll down --amount 1500 → browser-act --session {SESSION} wait stable --timeout 10000 → re-scan, merge results
  4. Filter candidates by authorUrl / tweetSnippet (skip promotional or low-relevance tweets)
  5. For each target tweet:
    • a. Generate reply: Use intent (caller-provided) + tweetSnippet + authorHandle + loaded config (product.*, persona.*, tone.*) to compose a 60–180 character ASCII reply. See references/quality-checklist.md (7-item checklist) and references/reply-composition.md (3 recommendation scenarios A/B/C).
    • b. browser-act --session {SESSION} eval "$(python scripts/click-reply.py {replyBtnIdx})" → open reply box
    • c. browser-act --session {SESSION} wait --selector '[data-testid="tweetTextarea_0"]' --state attached --timeout 10000
    • d. browser-act --session {SESSION} state → get editor index {EDITOR_IDX} → `brows

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars6.0k
CategoryMarketing
Updated2mo ago
Forks304

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions