LaunchKit · 2026
Back to Skills

kirk-content-pipeline

Create KSVC-validated Twitter content from research PDFs.

0
440 downloads
by @lukerspace

Setup & Installation

openclaw skills install @lukerspace/kirk-content-pipeline

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install kirk-content-pipeline

What This Skill Does

Produces Twitter content from analyst research PDFs through a structured pipeline covering PDF extraction, cross-document synthesis, KSVC holdings verification, claim auditing, voice stylization, and draft publishing. Each published number is traced to a specific PDF page and verified by a fresh-context subagent before saving.

Mandatory subagent auditing separates the writer from the verifier, catching hallucinated numbers and misattributions that self-review typically misses.

When to use it

  • Writing a Twitter thread from a newly released Goldman Sachs sector report
  • Cross-referencing three broker PDFs to find where analysts disagree on price targets
  • Checking KSVC portfolio holdings before framing a post as a personal position vs industry observation
  • Posting a victory lap when a held stock confirms the original thesis
  • Screening 20 PDFs from the week to identify the single best content angle

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: create a thread from this week's analyst PDFs in /Users/Shared/ksvc/pdfs/20260314/

AGENT
  1. 1Symlink PDFs into project directory and spawn parallel Explore agents to screen all PDFs for relevant content angles
  2. 2Run RLM deep extraction on the top 2-3 PDFs, building a structured extraction cache with source attribution and context labels
  3. 3Check all 7 KSVC models (USA 1-5, TWSE 1-2) for holdings matching tickers found in the reports
  4. 4Write data-backbone draft, then spawn fresh Explore subagents to audit every published claim against source PDFs
  5. 5Apply kirk-mode stylization and humanizer pass, then save draft with audit manifest and source-traced charts to assets folder
OUTPUT

Verified Twitter thread saved to content-pipeline/draft/YYYY-MM-DD-topic-assets/ with audit report, holdings check, and chart files ready for approval

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

Gemini CLI with API access (used for Step 4a.5 web cross-validation via gemini -p command)Access to kicksvc.online KSVC holdings API