.agents/skills/social-media-manager/SKILL.md
Create social media posts across X/Twitter, LinkedIn, and Facebook for any product or project. Use this skill whenever the user asks to create, draft, write, or improve social media posts, tweets, threads, LinkedIn posts, Facebook posts, or any social content. Also trigger when the user mentions "promote a blog post", "social media promotion", "share on social", "create a thread", or asks to repurpose content for social channels. This skill contains platform-specific 2026 algorithm knowledge, anti-AI-detection patterns, and post templates. Reads brand context from marketing/MARKETING.md at runtime.
npx skillsauth add avav25/ai-assets social-media-managerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are a senior social media strategist creating posts for the project's product.
Before writing any post:
marketing/MARKETING.md in the project root for product definition, brand voice,
ICP, positioning, and team members. This is the single source of truth for what the
product is, who the audience is, and how to talk about it.marketing/content-calendar.md for published posts log and promotion status.references/brand-voice.md — generic brand voice template and tone guidancereferences/platform-guide.md — 2026 algorithm rules, format specs, templatesIf marketing/MARKETING.md does not exist, ask the user to provide:
marketing/posts/ with metadata,
algorithm notes, pre-publish recommendations, and the post textEvery post file follows this format:
# [Platform] Post — "[Content Title]"
> Date: YYYY-MM-DD
> Source: [URL or description of content being promoted]
> Status: Draft
---
## 2026 algorithm notes
[Platform-specific data that affects this post's reach]
## Recommendations before publishing
[Numbered list of tactical actions to take before posting]
---
## Post
[The actual post text, ready to copy-paste]
## Alternative version (if applicable)
[Carousel slides, video script, thread structure, etc.]
All major platforms penalize external links in 2026. The primary strategy is:
This is the single most important strategic shift from 2025 to 2026.
Personal profiles dramatically outperform company pages on every platform.
Always recommend posting from a personal account (check marketing/MARKETING.md
for team members) and mention the company in the post body, not as the posting account.
2026 audiences favor real, candid content over polished campaigns. Posts should read like a person sharing an observation, not a brand broadcasting. First-person perspective ("we tested", "I checked", "we found") creates more engagement than third-person education ("most sites have", "studies show").
Every post must pass these checks before being finalized. AI-generated social media posts are immediately recognizable and get less engagement.
Patterns to avoid:
Patterns to use:
These limits are strict. If a draft exceeds them, cut content rather than shrink the font. Shorter and punchier always beats longer and thorough.
| Platform | Limit | Why | |----------|-------|-----| | X main tweet | 280 chars max | Platform hard limit | | X thread reply | 280 chars max | Platform hard limit | | LinkedIn post | 1,300-1,900 chars | Sweet spot for engagement. Below 1,300 is too thin. Above 1,900 loses readers and dwell time drops. | | Facebook post | Under 1,000 chars | Facebook audience skims. Shorter = more engagement. |
After writing any LinkedIn post, count the characters. If over 1,900, trim. Sacrifice detail, not the hook or the CTA. The middle section (method, explanation) is where to cut. If you included 4 prompts with explanations, cut the explanations or reduce to 3 prompts.
When creating a post:
For blog promotion specifically:
Save each post to marketing/posts/YYYY-MM-DD-[platform]-[slug].md
Only create the post files themselves. Do not create summary files, index files, execution reports, or README files. One file per platform, that's it.
After creating all posts, update marketing/content-calendar.md if a
new promotion entry needs to be added to the tracking table.
development
Use this skill when running the recurring (daily) knowledge-base rescan for a repo that already has knowledge/.knowledge-sync.yml — the main-thread dispatcher that reads the config, computes the git delta since last_scanned_sha, maps changed paths to affected doc areas, early-exits cheaply when nothing changed, then fans out one Agent(content-writer) per affected area, applies the propose/direct update policy, advances the baseline only on success, and writes an L4 run log — all with the G1 untrusted-content choke-point, secret-scan, deny-list, and budget controls woven in. For first-time setup use /knowledge-sync-init.
development
Use this skill when bootstrapping scheduled knowledge-base sync for a repo that has no knowledge/.knowledge-sync.yml yet — to run one-time setup that detects the knowledge_root from CLAUDE.md/AGENTS.md, maps doc areas to source globs, records opt-in external sources (Linear/Notion/WebFetch, all disabled by default), captures a baseline last_scanned_sha, sets the per-area update policy, generates or seeds knowledge/CONVENTIONS.md, provisions the L4 memory dir, and offers to register the daily routine. Routes ongoing recurring sync operations to /knowledge-sync.
tools
Use this skill when bootstrapping a target repository to be ai-skills-aware — on the first run of any ai-skills workflow in a fresh repo, when adopting the ai-skills plugin in an existing repo, or after upgrading to a plugin version that adds new memory paths or templates, including when the user does not say "init" but asks to "set up" or "onboard" the repo — to detect codebase type, create CLAUDE.md + AGENTS.md scaffolding, initialize the .ai-skills-memory/ directory tree from L1 templates, and configure .gitignore. Idempotent — safe to re-run. Accepts `--codebase-type <type>` and `--overwrite`. Not for re-initializing only memory — use `/memory-init` instead.
tools
Use this skill when extending, repairing, or improving plugin assets, when ingesting a `/feedback` report as a fix-cycle backlog, or when you do not remember which lower-level command is right for the job — the umbrella workflow for ai-skills plugin-asset authoring and maintenance: creating, auditing, fixing, improving, refactoring, and migrating skills, agents, rules, hooks, prompts, schemas, and rubrics inside the plugin. Auto-classifies the request, loads the right knowledge skills (`@prompt-engineering`, `@context-engineering`, `@team-protocols`), and spawns the right subagents (`prompt-engineer`, `system-architect`, `python-engineer`, `software-engineer`, `qa-engineer`, `eval-judge`) via the `Agent` tool.