Content Audit

Organization

social-media-skills

content-audit

Audit an existing social media account and its content — the retrospective reality-check of what's working and what isn't. Use when someone wants to "audit my content/account," "what's working and what isn't," "clean up my profile/feed," "I post a lot but it's not working," or to triage an existing account before replanning. Produces a keep/kill/refresh triage, maps pillar coverage, catches voice drift, and fixes profile fundamentals — then a quick-wins-vs-long-term roadmap. Uses the AUDIT framework. Reads brand-profile + content-pillars + social-strategy (the plan) and analytics-and-reporting (the data) first. It reads WoopSocial post analytics on covered platforms and native dashboards otherwise, scores on signal not vanity, recommends rather than auto-deletes, and never fabricates. Feeds content-recycling, content-pillars, profile-optimization, voice-builder, and social-strategy. Distinct from analytics-and-reporting (ongoing measurement) and competitor-analysis (rivals).

Overview

Publisher	social-media-skills
Repository	`skills`
Skill name	`content-audit`
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 Content Audit 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/content-audit
Enable the skill in any chat where you want it available.

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/content-audit .claude/skills/content-audit

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

Use it in TypingMind

Enable Content Audit 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 Content Audit 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 Content Audit 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.

content-audit

The retrospective bridge — read how an existing account has performed and turn it into a keep/kill/ refresh roadmap that feeds the forward plan. It reads (via analytics-and-reporting) and recommends; the human and other skills act.

The POV: activity isn't progress

Plenty of accounts look busy — daily reels, carousels, likes trickling in, followers inching up — while nothing actually moves. A content audit finds the signal under the busy-ness: what gets saved and shared (not just liked), which pillars are starved or bloated, where the voice has drifted (or where your winners say it should evolve), and which profile fundamentals quietly leak followers. Strategy is forward-looking; the audit is the retrospective reality-check that informs it.

Read these first

brand-profile + voice-builder — the voice/brand standard to audit against.
content-pillars + social-strategy — the intended plan (the audit checks execution of it).
analytics-and-reporting — the performance data source (WoopSocial post analytics for TikTok, LinkedIn, Facebook, Instagram, Pinterest, YouTube, and Bluesky; native dashboards otherwise).

The framework: AUDIT

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

A — Assemble the inventory: ~90 days of output by platform/format/pillar/time + native metrics; pull the plan you're auditing against.
U — Uncover the signal: score on saves/shares/replies + the goal-mapped KPI (not vanity); surface top/bottom performers + patterns by format/time/pillar.
D — Diagnose pillars, voice & profile: pillar whitespace (→ content-pillars); voice drift both ways (→ voice-builder); profile fundamentals + cadence (→ profile-optimization).
I — Iterate: keep / kill / refresh: scale winners (→ content-recycling), cut chronic/off-brand/ non-native, refresh good-but-dated. Refresh before kill; human approves kills.
T — Turn into a roadmap: strengths/weaknesses/opportunities; quick wins vs long-term; owners + timelines; hand off. No spreadsheet graveyard.

The method (verify specifics quarterly)

Audit = retrospective (vs forward strategy); signal-over-vanity; keep/kill/refresh; pillar whitespace; voice drift both ways; profile fundamentals; ~90-day window; quarterly deep + monthly light; run after major changes: references/content-audit-2026-reality.md. Triage rules, scorecard + worked examples: references/triage-and-recipes.md.

Honest scope (never violate)

Retrospective, not strategy — triages the past; social-strategy plans the future.
Reads WoopSocial post analytics for the covered platforms, and native dashboards otherwise, via analytics-and-reporting; interprets numbers the user provides — never fabricates a metric or a coverage map.
Signal not vanity — low likes is not a kill criterion.
Recommend, don't auto-act — never auto-delete (a human approves kills; deleting can lose evergreen/SEO value + history); refresh before kill; some profile edits are in-app/human.
Thin data → structural audit only (profile/pillars/voice/cadence + baseline); revisit performance triage at ~90 days. (Scope, bridge role + connections: references/scope-and-connections.md.)

Distinct from its siblings (route correctly)

content-audit (this) = periodic retrospective triage of YOUR account · analytics-and-reporting = ongoing measurement (the data source) · competitor-analysis = rivals' public side · social-strategy = the forward plan this informs · content-recycling = scales/refreshes the winners this surfaces · profile-optimization = executes the profile fixes this flags.

Where this connects

Reads first: brand-profile, voice-builder, content-pillars, social-strategy, analytics-and-reporting. Hands findings to: content-recycling, content-pillars, profile-optimization, voice-builder, social-strategy, experimentation. Benchmark context: competitor-analysis, goals-and-kpis. Per-platform format/native expectations: the per-platform *-growth skills. No publishing/tool surface — a diagnostic + planning skill.

Definition of done

A ~90-day inventory scored on signal (not vanity) from native analytics the user provided (nothing fabricated); pillar whitespace, voice drift (both ways), profile fundamentals, and cadence diagnosed; a keep/kill/refresh triage (refresh before kill; kills human-approved, none auto-deleted); a strengths/ weaknesses/opportunities roadmap split into quick wins vs long-term with owners + timelines, handed to content-recycling/content-pillars/profile-optimization/voice-builder/social-strategy; thin-data accounts get a structural audit + baseline instead; correctly distinguished from analytics-and-reporting, competitor-analysis, and social-strategy.

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 Content Audit AI skill do?

Why use Content Audit on TypingMind?

Because you install it once and use it with any model. Content Audit 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 Content Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/content-audit. 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 Content Audit?

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 Content Audit?

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

Is the Content Audit 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

Serving Llms Vllm

NousResearch

OrganizationPopular

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Huggingface Hub

HuggingFace hf CLI: search/download/upload models, datasets.

Pytorch Lightning

Clean training loops with built-in distributed support.

Troubleshoot

Investigate unexpected behavior in the current Copilot agent session by analyzing its event log. Use when the user asks why something happened, why a request was slow, why a tool was or was not used,…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

content-audit

The POV: activity isn't progress

Read these first

The framework: AUDIT

The method (verify specifics 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