Skip to content

docs: add TweetClaw source option for x-content-intelligence#29

Open
kriptoburak wants to merge 3 commits into
MSApps-Mobile:mainfrom
kriptoburak:codex/add-tweetclaw-x-content-source
Open

docs: add TweetClaw source option for x-content-intelligence#29
kriptoburak wants to merge 3 commits into
MSApps-Mobile:mainfrom
kriptoburak:codex/add-tweetclaw-x-content-source

Conversation

@kriptoburak

Copy link
Copy Markdown

Summary

  • Add TweetClaw as an optional reviewed source path for x-content-intelligence.
  • Keep Apify as the default scrape path.
  • Clarify that TweetClaw outputs are evidence for analysis, while this plugin keeps responsibility for content generation and review.
  • Bump the plugin metadata from 0.1.0 to 0.1.1.

Validation

  • git diff --check
  • python3.11 -m json.tool .claude-plugin/marketplace.json
  • python3.11 -m json.tool plugins/x-content-intelligence/.claude-plugin/plugin.json
  • npx --yes markdown-link-check plugins/x-content-intelligence/README.md plugins/x-content-intelligence/skills/x-insights/SKILL.md
  • bash scripts/package-plugin.sh x-content-intelligence /tmp/tweetclaw-msapps-dist
  • bash scripts/sosa-lint.sh .

Link Notes

  • The changed x-content-intelligence README links pass.
  • The changed x-insights skill has no links.
  • A root README link check also surfaced pre-existing target-owned blockers outside this PR: https://claude.ai returns 403 to curl and https://x.com/MSAppsMobile returns 404.

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces support for an optional TweetClaw source path (via OpenClaw or MCP) to the x-content-intelligence plugin, allowing the analysis of reviewed X/Twitter source data alongside the default Apify scraper. The changes update metadata, documentation, and workflows across several files. The review feedback suggests specifying how the TweetClaw data should be retrieved in the workflow instructions to prevent agent confusion, and simplifying the SOSA agents metadata string in plugin.json for better conciseness.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

Run the Actor using `call-actor` with Actor name `apidojo/tweet-scraper`, then retrieve results with `get-actor-output`.

### Step 3: Analyze the Results
If using reviewed TweetClaw source data instead, skip the Apify Actor call and move directly to analysis.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The instructions tell Claude to skip the Apify Actor call and move directly to analysis when using TweetClaw, but they do not specify how Claude should actually retrieve or access the TweetClaw data. Adding explicit guidance to either use the available TweetClaw MCP tools or read a local export file provided by the user will prevent Claude from getting stuck or asking redundant questions.

Suggested change
If using reviewed TweetClaw source data instead, skip the Apify Actor call and move directly to analysis.
If using reviewed TweetClaw source data instead, retrieve the data using the available TweetClaw MCP tools or by reading the local export file provided by the user, skip the Apify Actor call, and move directly to analysis.

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Addressed in e7cc1a8 by telling the skill to use available TweetClaw MCP tools or a user-provided local export before skipping the Actor call.

Validation:

  • git diff check
  • plugin manifest JSON parse
  • changed-diff public-hygiene scan

"agents": "R=x-content-intelligence, T=Apify+X-API, M=content-analysis, P=scrape-analyze-generate-review"
"orchestrated": "Scrape or import reviewed source data, analyze, generate, then review content before use",
"secured": "Apify Actor or reviewed TweetClaw output for source data, no direct X API credentials in plugin",
"agents": "R=x-content-intelligence, T=Apify or reviewed TweetClaw source data, M=content-analysis, P=scrape-or-import-analyze-generate-review"

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The T (Tools) and P (Process) values in the SOSA agents metadata string are quite verbose. Keeping them concise and aligned with standard SOSA shorthand (e.g., listing tool names/APIs for T and hyphenated steps for P) improves readability and consistency with other plugins.

Suggested change
"agents": "R=x-content-intelligence, T=Apify or reviewed TweetClaw source data, M=content-analysis, P=scrape-or-import-analyze-generate-review"
"agents": "R=x-content-intelligence, T=Apify+TweetClaw, M=content-analysis, P=import/scrape-analyze-generate-review"

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Addressed in e7cc1a8 by switching the SOSA agent metadata to concise tool, method, and process shorthand.

Validation:

  • git diff check
  • plugin manifest JSON parse
  • changed-diff public-hygiene scan

@kriptoburak

Copy link
Copy Markdown
Author

Addressed the Gemini review by adding explicit TweetClaw source-data retrieval guidance and shortening the SOSA agents metadata. Re-ran git diff --check, JSON parsing, plugin README and skill link checks, package-plugin, SOSA lint, and added-line hygiene checks.

@kriptoburak

Copy link
Copy Markdown
Author

Optional visibility note: if this is useful and you merge it after checks pass, feel free to share the PR on X/Twitter and tag https://x.com/burakbayir. I can repost it to my 24k followers so more developers and power users can discover this repo.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant