mcpField
C
content-audit

content-audit

github.com/social-media-skillsMarketing & growth210707 installsUpdated 2w ago
Repository

About content-audit

A retrospective social-content audit skill for teams reviewing an existing account. It turns analytics and brand or strategy context into a keep, kill, or refresh roadmap, while leaving decisions and actions to people and other skills.

Key features

  1. 01Audits roughly 90 days of content
  2. 02Scores saves, shares, replies, and KPIs
  3. 03Finds gaps in content pillars
  4. 04Checks voice and profile fundamentals
  5. 05Creates a keep, kill, refresh roadmap

Use cases

  1. 01Review a social account quarterly
  2. 02Find content patterns beyond likes
  3. 03Identify gaps in planned content pillars
  4. 04Prioritize updates to older posts

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/social-media-skills/skills --skill content-audit

After installing, type/content-auditin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

evals/
evals.json
references/
content-audit-2026-reality.md
scope-and-connections.md
the-audit-framework.md
triage-and-recipes.md

Details

From the project README

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

  1. brand-profile + voice-builder — the voice/brand standard to audit against.
  2. content-pillars + social-strategy — the intended plan (the audit checks execution of it).
  3. 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.

Comments

Markdown supported