Typefully Agent Skill
Lets your AI agent draft, schedule, and manage posts on X, LinkedIn, Threads, Bluesky, Mastodon, and Substack Notes through Typefully.
Least privilege: allowed-tools is only Bash(./scripts/typefully.js); irreversible public publishing explicitly requires user confirmation; auth failures forbid credential hunting or web-UI fallback; destructive flags like --force-overwrite-comments require explicit confirmation in a separate turn; API key storage and data flows are disclosed; MIT license with clear attribution. Deductions: publish confirmation relies on instruction-following rather than technical enforcement; the script is truncated in evidence so all external calls cannot be fully audited.
Zero-dependency CLI, JSON output, errors with hints/actions, --use-default ambiguity guard, and clear quota/auth failure feedback; repository includes a vitest suite and CI covering key paths. Deductions: static review without execution; script truncated in evidence; environment inconsistency (SKILL.md says Node 18+, package. requires >=20).
Trigger conditions are explicit (drafting/scheduling/publishing social content, dropped Typefully draft URLs), with clear platform boundaries, non-fit cases (x_article standalone, substack single-post) and character limits, plus a phrase-to-action table. Deductions: core function depends entirely on the overseas Typefully API with no assessed mainland-China reachability or fallback; no Chinese-language support declared.
Well-layered docs (SKILL.md plus on-demand references), Keep-a-Changelog format CHANGELOG, freshness check, update paths, license, troubleshooting, and clear maintenance ownership (Typefully's official repo). Deductions: Node version inconsistency (18+ vs >=20), README version badge 1.0.0 without a matching semantic versioning mechanism, and incomplete script visibility.
Goal is clear (agent-side drafting/scheduling/management of social posts), output is structured JSON with abundant directly usable command examples and a phrase-action mapping; marginal value over manual work is evident. Deductions: static review cannot verify real output quality; effectiveness ultimately depends on the Typefully API and paid quota; no real execution output samples.
Repository contains a CI workflow (Node 20/22 matrix running vitest) and committed tests covering key paths such as analytics and comments; claims are locally reproducible via npm test, and changelog entries can be cross-checked against code. Deductions: single-source (official repo self-tests), no independent third-party verification, test files truncated in evidence, no execution performed, limiting static confidence.
- Core function depends entirely on the overseas Typefully API (api.typefully.com); mainland-China network reachability is unverified — test connectivity before use.
- Publishing is irreversible and public; ensure the agent obtains explicit user confirmation before drafts:publish / --schedule now.
- SKILL.md claims Node.js 18+ but package. requires >=20; install Node 20+ to avoid incompatibility.
- API keys are stored in plaintext (environment variable or .typefully/config. / ~/.config/typefully/config.); avoid committing them to version control.
- --force-overwrite-comments resolves and strips uncovered comment threads server-side and is unrecoverable via the API; use only after per-item user confirmation.
- This is a static source review without execution; confidence is low.
What does this skill do, and when should you use it?
This is the official Typefully Agent Skill, handing social media writing and scheduling workflows to an AI agent. It ships a zero-dependency Node.js CLI script that talks to the Typefully API to manage drafts, scheduling, the queue, tags, media, and X analytics. One draft can target multiple platforms with identical or per-platform content. It fits creators and teams already using — or willing to adopt — Typefully, used by 200k+ creators.
Runs scripts/typefully.js (Node.js 18+, no dependencies) inside skills/typefully/ to call the Typefully API: create and edit drafts (drafts:create/update), schedule or publish immediately (drafts:schedule/publish), view the queue timeline (queue:get), manage tags and media uploads, query X analytics, and resolve pasted Typefully draft URLs (?a=<social_set_id>&d=<draft_id>) straight into draft data. All commands output JSON. Drafts support --scratchpad internal notes, --tags, --media; link preview cards auto-generate on LinkedIn/Threads/Bluesky/Substack and can be suppressed with --hide-link-preview.
- A solo creator asks their agent in the IDE or terminal to draft tweets and threads, then decide whether to schedule.
- A social media manager posts one announcement to X and LinkedIn in a single multi-platform draft, or tailors copy per platform via drafts:update.
- A content team 'plans' posts onto the calendar without arming auto-publish, confirming later with drafts:schedule.
- A marketer checks a date-range queue (queue:get) for free slots and the publishing quota before scheduling.
- A user pastes a Typefully draft URL so the agent fetches the draft and continues editing or handles its comments.
- Before attaching images, media:upload gets a ready media_id to attach via --media.
What are this skill's strengths and limitations?
- Officially maintained, built on the Typefully API, covering six platforms from one install.
- Zero-dependency CLI needing only Node.js 18+; all commands output JSON for easy agent parsing.
- Strong safety design: publish confirmation, plan-vs-schedule separation, explicit auth-failure handling.
- Thorough documentation with platform guides (X analytics, LinkedIn mentions, X Articles) and comment workflows.
- Requires a Typefully account and API key; publishing is subject to the platform's publishing_quota.
- Publishing is irreversible and public, relying on the agent correctly following the confirmation rule.
- Frontmatter uses the Claude Code-specific allowed-tools Bash(...) syntax, needing edits for other clients.
- No automated test suite or per-platform real-world evidence shown in the README; Substack Notes supports neither threads nor video media.
How do you install this skill?
- Install: npx skills add typefully/agent-skills (works with Claude Code, Cursor, Windsurf, and others). Claude Code can also use /plugin marketplace add typefully/agent-skills then /plugin install typefully@typefully-skills; Cursor users can add a GitHub remote rule or manually copy skills/typefully/ into .cursor/skills/ or .claude/skills/. 2. Get an API key at https://typefully.com/?settings=api. 3. Run ./scripts/typefully.js setup to configure the key and default social set, or export TYPEFULLY_API_KEY=your_key_here. Requires Node.js 18+.
How do you use this skill?
After setup, prompt your agent with things like "Draft a tweet about X", "Create a LinkedIn post announcing [news]", "Schedule my draft for tomorrow morning", "Show my scheduled posts". You can also paste a Typefully draft URL for direct retrieval. The agent is instructed to confirm with you before publishing; creating drafts is safe.