fk-writing-kit
v2.1.3by furkankoykiran · author: Furkan Köykıran
fk-writing-kit is an Agent Plugin published by furkankoykiran. It packages 4 skills. We fetched the plugin.json from GitHub on 2026-11-13 and checked it against the official Agent Plugins 1.0.0 schema.
Turn raw material into publishable writing: strip AI tells from drafts, and build blog posts or LinkedIn copy from a chat, a URL, or a GitHub profile.
Package we checked
The manifest we fetched is skills/fk-writing-kit/plugin.json in furkankoykiran/.claude. The plugin root is the directory that holds that file. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists 4 skills (blog-from-chat, github-profile-blog, humanizer, linkedin-post) and no MCP servers. Extension keys: com.openai.
- Skills
- 4
- MCP servers
- 0
- Stars
- 5
- License
- MIT
- Repo created
- 2026-04-26
- Last pushed
- 2026-11-12
- Publisher type
- User
- Version
- 2.1.3
Links
Skills · 4
- blog-from-chat
- Turn a chat log, conversation or discussion summary into a publishable blog post, in one or more languages. Use for "blog from this chat" or "write up our conversation".
- github-profile-blog
- Write an educational blog post analysing a GitHub profile's public activity. Use for "blog about my GitHub" or a write-up of someone's open-source work.
- humanizer
- Strip the tells of AI-generated writing: inflated symbolism, promotional phrasing, vague attribution, em-dash and rule-of-three overuse. Use when text should read as human-written, or the user says it "sounds like AI".
- linkedin-post
- Turn a blog post, URL or chat context into a formatted LinkedIn post. Use to share an article on LinkedIn or repurpose content as LinkedIn copy.
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
writing · blogging · editing · linkedin · content
Related by publisher and keywords
Four focused subagents, researcher, planner, code-reviewer, debugger, for deep codebase research, dependency-aware planning, pre-commit review, and root-cause debugging. Adds no skill-listing context cost.
End-to-end GitHub workflow: find issues worth working on, solve one into a pull request, follow up on review feedback, and write comments that read like a human wrote them.
Operate the toolkit itself: check for and apply toolkit updates, wire MCP servers into Claude Code, and use Codex-native ImageGen when available with a clear optional API fallback boundary.
Audits a codebase's user-facing copy, layouts and metadata for AI-written tells and factual errors, such as a privacy policy that misses the trackers the code loads, reviews a web, iOS or Android screen for AI-generated design and fixes it in ordered passes once you approve a direction, rewrites a file or pasted text to remove AI writing patterns, prunes code comments that narrate the code or excuse a workaround, and rebuilds a feature an agent just wrote as a simpler second version, keeping the first until you choose
Write, edit, and reshape content for human readers, copy, long-form, technical documentation, and voice consistency. Turn rough drafts into clear, publishable prose.
Find and fix canned AI writing while preserving the facts, voice, and format.
[](https://agentpluginsdirectory.com/plugins/fk-writing-kit)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.