Turn a raw technical idea into coordinated, publish-ready content for LinkedIn, Substack, and Medium. Seven chained skills: explore (assumptions, clarification, lock the thesis and master content), write-linkedin, write-substack, write-medium (HTML), refine, design-brief (per-section images plus a LinkedIn PDF, for Claude Design), and distribute. Content-first: approve before generating posts; if content changes, regenerate every platform.
Design hand-off — after the content is locked, produce ONE artifact a design tool (e.g. Claude Design) can execute: a concise title + description for every section (inline images + a shared hero) for Substack and Medium, and a slide-by-slide PDF brief for LinkedIn. Use whenever someone wants graphics or visuals for their post, a carousel/PDF design spec, a hero/cover image, per-section images, asks 'should I make graphics for this?', or is handing content to a design tool and needs direction. Produces a brief, not the images themselves.
Posting & distribution — decide when to post for maximum reach, generate hashtags/topics and an SEO description, write a Substack launch Note, plan Medium tags/publications/Boost and canonical cross-posting, clean tracking-laden links, and coordinate cross-posting across LinkedIn + Substack + Medium. Use whenever someone asks when to post, wants hashtags/tags or a meta/SEO description, needs a launch Note or announcement, asks about getting reach or views or Boost, or is ready to publish and share. Offer these proactively once content is drafted — reach is won here, not in the writing.
Exploration & content-lock phase — surface assumptions, ask for clarification, sharpen a raw technical idea, and lock both the thesis spine and the master content BEFORE any platform post is written. Run a technical-accuracy pass, find the single strongest framing, strip pedantry-bait, propose a one-line spine, and gate the pipeline on the person's approval. Use whenever someone brings rough notes, a thesis, or a strong opinion and wants to turn it into content, asks 'is this a good angle?', 'help me think through this idea', or 'correct me if I'm wrong' — i.e. before drafting any LinkedIn, Substack, or Medium post. Always explore, lock the framing, and finalize the content before writing platform assets.
Refine, clear confusions & re-sync — fix a rough, long, or confusing draft and keep every platform asset consistent with the locked master content. Restructure walls of text into scannable sections, catch contradictions and duplicate transitions, resolve muddled claims, and run the consistency + change-protocol pass so the LinkedIn carousel, Substack essay, and Medium article all share one framing. Use whenever a draft feels 'too long / rambling / lousy / unclear', when a content change must propagate across pieces, or when checking that multiple assets agree with each other. This is also the loop-back path: a content change re-syncs all platforms.
Writing phase for LinkedIn — draft a publish-ready carousel (slide-by-slide) and the caption that goes above it, from the LOCKED master content. Use whenever someone wants to write a LinkedIn post or carousel, a document/PDF post, or turn a finalized idea into LinkedIn content. LinkedIn is the visual, algorithm-timed channel; the carousel ships as a PDF document. Do not run until the content is locked and approved (see explore); if the framing isn't locked yet, sharpen it first with explore.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude plugin that turns a raw technical idea into coordinated, publish-ready content for LinkedIn, Substack, and Medium — written once as a single locked piece, then faithfully rendered for each platform.
Built for technical writers who cross-post the same thesis everywhere and want the versions to stay in sync.
The whole plugin runs on one rule:
Finalize the content fully and get explicit approval before generating any platform post. If the content changes after posts exist, update the master content first, get re-approval, then regenerate every platform asset — never patch one platform in isolation.
This keeps LinkedIn, Substack, and Medium telling the same story instead of drifting apart after edits.
1. explore → surface assumptions, ask for clarification,
lock the thesis + the master content ── approval gate ──┐
│
2. write-* → render the locked content per platform: │
write-linkedin · write-substack · write-medium │
│
3. design-brief → one design hand-off artifact for Claude Design: │
per-section images (Substack/Medium) + PDF slides (LinkedIn)
│
4. distribute → timing, tags, SEO, launch Note, canonical cross-posting │
│
refine → restructure / fix any asset AND re-sync all platforms ────┘
(also the loop-back path when content changes)
Phase 1 is a gate. Nothing in Phases 2–4 starts until the person says the content is good.
Change protocol (the loop-back arrow): a content change at any later point sends you back to Phase 1 — update the master, re-approve, then regenerate all platform assets so they stay coordinated.
| Skill | Phase | Does |
|---|---|---|
explore | 1 | States assumptions up front, asks clarifying questions, runs an accuracy + framing pass, and locks the thesis spine and master content. The approval gate lives here. |
write-linkedin | 2 | Carousel (slide-by-slide) + caption, from the locked content. Posted as a PDF document. |
write-substack | 2 | Long-form essay in Markdown, native to Substack's reading/email format. |
write-medium | 2 | Medium article as clean semantic HTML (Medium doesn't render pasted Markdown). |
refine | 2–4 | Restructures rough drafts, clears confusions, and runs the cross-asset consistency + change-protocol re-sync. |
design-brief | 3 | Produces a single Claude Design hand-off artifact: concise title + description per section (Substack/Medium images) and a slide-by-slide PDF brief (LinkedIn). |
distribute | 4 | Posting timing, hashtags/tags, SEO description, Substack launch Note, Medium Boost/publications, canonical cross-posting, link hygiene. |
Copy this folder into your Claude plugins directory (or install from your marketplace). The plugin is defined by .claude-plugin/plugin.json; each skill lives under skills/<name>/SKILL.md.
design-brief outputs one artifact you paste straight into Claude Design:
##/** show up literally.MIT — see LICENSE.
npx claudepluginhub gokul-kulkarni/content-studio-pluginToken analysis and optimization plugin for Claude Code. Provides skills for analyzing context window usage, compressing token-heavy content, and displaying quick token dashboards.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.