Platform Specs And Validation

Organization

social-media-skills

platform-specs-and-validation

Platform specs and publish validation — per-platform requirements and the validate-before-publish step for multi-platform fan-out. Use when fanning a post out to multiple platforms, when a post is getting rejected, when mapping per-platform postType/required fields, or to run the validate-before-publish step. Encodes the per-platform postType enums, required-field matrices, and media rules from the OpenAPI spec, and runs POST /posts/validate so a post lands correctly on every target. Uses the CHECK framework. The keystone the per-platform format skills point to. WoopSocial validates + publishes atomically and has no update endpoint; the agent maps fields and fixes spec violations, but human-judgment calls (disclosure truthfulness, privacy intent) stay with the person; metrics never fabricated. Distinct from the per-platform format skills (one platform's content) and scheduling-and-queue (timing).

Overview

Publisher	social-media-skills
Repository	`skills`
Skill name	`platform-specs-and-validation`
Stars	215
Forks	44
Bundled files	5
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by social-media-skills on GitHub. Read the source before you install it.

Installation

Install the Platform Specs And Validation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/social-media-skills/skills/tree/main/skills/platform-specs-and-validation
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/social-media-skills/skills/tree/main/skills/platform-specs-and-validation

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/social-media-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/platform-specs-and-validation .claude/skills/platform-specs-and-validation

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Platform Specs And Validation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Platform Specs And Validation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Platform Specs And Validation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

platform-specs-and-validation

The cross-cutting publish-readiness skill — make a post correct on every target (required fields, media rules, limits) and run the validate-before-publish loop. It's the keystone the format skills point to. The agent maps fields + fixes spec violations + validates; WoopSocial validates and publishes; content craft and human-judgment calls stay elsewhere.

The POV: publish-ready, atomically, the first time

WoopSocial validates and publishes atomically — POST /posts checks every target together, and if any one fails, nothing is created. There's no update endpoint, so a post that publishes wrong can't be patched (edit = delete + recreate). That makes getting every target's fields right before publish the whole game: the right postType, the required per-platform fields, the media rules, and account-specific values (Pinterest board, TikTok privacy) resolved from platform-inputs — then POST /posts/validate to catch what's left. This skill is where the format skills come to make sure it will actually go through.

The framework: CHECK

(Depth: references/the-check-framework.md.)

C — Collect the targets + project: list the social accounts; confirm they're in the same project; note each platform's field set.
H — Hydrate per-platform required fields: fill each target's required fields (FB/IG postType; TikTok's eight; YouTube title+privacy; Pinterest pinterestBoardId); resolve account values from GET /social-accounts/{id}/platform-inputs.
E — Enforce media + content rules: FB no image+video mix; IG Stories need media; Pinterest single media; TikTok PHOTO/VIDEO field applicability; use contentOverride or separate posts where fan-out conflicts; respect text limits.
C — Confirm truthful declarations: isBrandedContent/isYourBrand/madeForKids are truthful declarations, not validation knobs — never flip them to clear an error; these stay with the person.
K — Knock it through validation: POST /posts/validate → fix all errors, review warnings → create (atomic). No update → delete + recreate (only while NOT_STARTED).

The spec (ground truth — verify-quarterly)

Per-platform postType enums + required-field matrices + media rules + the platform-inputs discovery endpoint + lifecycle facts (atomic create, no update, delivery status, schedule types): references/woopsocial-publish-spec.md. The validate-then-create loop, the full ValidationField code table + CreatePostErrorCode list + worked examples: references/validation-reference-and-recipes.md. (The live OpenAPI spec / tools/integrations/woopsocial.md are the source of truth; enums and limits move.)

Honest scope (never violate)

This skill ensures publish-READINESS (fields/media/spec correct + validated) — it doesn't write or improve the creative (the format/content skills do) and can't guarantee performance.
WoopSocial validates + publishes atomically; one failing target fails the whole post. No update → delete + recreate (only while NOT_STARTED).
Disclosure/compliance declarations stay truthful (isBrandedContent/isYourBrand/madeForKids) — never flipped to pass validation; privacy intent + disclosure truthfulness stay with the person.
Resolve account values (board, privacy) from platform-inputs — don't guess. Never fabricate metrics — native analytics only. (Scope, distinctions + connections: references/scope-and-connections.md.)

Distinct from its siblings (route correctly)

platform-specs-and-validation (this) = the cross-platform field/media/validation layer that makes a post publish-ready on every target · the per-platform format skills (tiktok-photo-mode, tiktok-video-publishing, threads-post, youtube-publishing-and-metadata, carousel-writer, …) = craft one platform's content and point here for validation · scheduling-and-queue = timing/cadence, not correctness · tools/integrations/woopsocial.md = the shared integration guide this applies post-level.

Where this connects

Receives from: every format skill (crafted content + chosen postType) and content-calendar (the plan). Resolves with: GET /social-accounts/{id}/platform-inputs (boards, privacy options) + the integration guide. Hands to: scheduling-and-queue → WoopSocial (POST /posts after isValid), then webhooks/delivery status for confirmation. Supports: cross-platform-repurposing (per-target contentOverride), analytics-and-reporting (native delivery readout), experimentation (valid variants). Content craft + truthful declarations stay with the format skills + the person.

Definition of done

Every target collected and confirmed in one project; each target's required fields hydrated (postType / privacy / board / disclosure / title as applicable) with account-specific values resolved from platform-inputs; media + content rules enforced (no FB mix, IG-Story media, single Pinterest media, TikTok field applicability) with contentOverride or separate posts where fan-out conflicts; disclosure/madeForKids declarations left truthful (never flipped to pass); POST /posts/validate run with all errors resolved and warnings reviewed before an atomic create; edits handled via delete+recreate, nothing fabricated and no promised performance; correctly distinguished from the per-platform format skills and scheduling-and-queue.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Platform Specs And Validation AI skill do?

Why use Platform Specs And Validation on TypingMind?

Because you install it once and use it with any model. Platform Specs And Validation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Platform Specs And Validation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/platform-specs-and-validation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Platform Specs And Validation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Platform Specs And Validation?

As many as you like. As long as a model supports skills, you can use Platform Specs And Validation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Platform Specs And Validation AI skill free?

Yes. It is published on GitHub by social-media-skills under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Distributed Triage

pytorch

OrganizationPopular

Sub-triages issues in the oncall:distributed queue by assigning distributed module labels, routing to sub-oncalls, and marking triaged. Use when an issue has been routed to oncall:distributed and…

Hyperframes

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video…

Audio Jingle

Audio generation skill — jingles, beds, voiceover, and sound effects. Routes music requests to Suno V5 / Udio / Lyria, speech to MiniMax TTS / FishAudio / ElevenLabs V3, and SFX to ElevenLabs SFX or…

Proof Video

Add subtitles, captions, narration cues, or zoom to a proof video or PR recording using repo-local capture helpers and a system ffmpeg renderer.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

platform-specs-and-validation

The POV: publish-ready, atomically, the first time

The framework: CHECK

The spec (ground truth — verify-quarterly)

Honest scope (never violate)

Distinct from its siblings (route correctly)

Where this connects

Definition of done

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now