Engagement Routine

Organization

social-media-skills

engagement-routine

Use to design a sustainable engagement routine — the operating system that turns the engagement craft into a daily/weekly habit. Run when the user asks how to keep up with comments/DMs, how much time to spend engaging, when to engage, how to build an engagement habit/system/cadence, or how to engage without burning out. Reads brand-profile/social-strategy. Covers time-boxed daily/weekly engagement windows built around the golden hour after posting, triage order, mapping engagement to a goal, and anti-burnout boundaries. The flywheel: batch and schedule content (scheduling-and-queue, batch-content-plan) to free the time, then spend it engaging. Advisory and honest — WoopSocial has no comment/DM/inbox surface. Post performance is analytics-and-reporting, not here, so the human engages in-app and the agent drafts via reply-and-comment-writer; never automates or fakes engagement. Pairs with reply-and-comment-writer (the craft), the growth skills, community-management, and crisis-and-moderation.

Overview

Publisher	social-media-skills
Repository	`skills`
Skill name	`engagement-routine`
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 Engagement Routine 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/engagement-routine
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/engagement-routine .claude/skills/engagement-routine

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

Use it in TypingMind

Enable Engagement Routine 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 Engagement Routine 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 Engagement Routine 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.

Engagement Routine

The operating system for engagement. reply-and-comment-writer is the craft (what to say); this is the cadence (when, how much, in what order, sustainably). The growth skills all call for "an engagement routine" — this is it.

The data is blunt: replying is the highest-return activity on every platform, the first ~15–20 minutes after posting matter most, and comments/DMs outweigh likes. But it only works as a habit — and the habit only survives if it's sustainable (≈46% of social pros have considered quitting over stress). So this skill optimizes for return and longevity.

Step 0 — Read the context

Load brand-profile.md / social-strategy.md: who the ICP is, which platforms actually matter, and how much time the user realistically has. Right-size everything to that.

Step 1 — Set the cadence (windows, not all-day)

Design time-boxed engagement windows instead of all-day grazing — e.g. ~20 min morning + ~20 min afternoon, plus a golden-hour pass right after each post publishes. Order within each window: comments → DMs → urgent/negative → proactive comments on ICP/peers/leaders. See references/the-daily-and-weekly-routine.md.

Step 2 — Free the time (the flywheel)

"No time to engage" is solved by batching + scheduling content (→ batch-content-plan, scheduling-and-queue) to reclaim the hours, then spending them engaging. The flywheel: schedule → freed time → genuine engagement → reach/relationships → more reach. Time posts for windows you can be present. See references/the-scheduling-engagement-flywheel.md.

Step 3 — Triage & aim at a goal

When time is short, do the highest-return things first (golden-hour comments → DMs → negative → proactive), focus on the right people (ICP/peers), not vanity volume, and map the routine to a goal with 2–3 meaningful signals you can read natively (no WoopSocial analytics). See references/triage-priorities-and-goals.md.

Step 4 — Make it sustainable

Build in boundaries: notification discipline, set + communicate response windows, protect off-hours, and prefer a small repeatable routine you keep over a heroic one you abandon. Consistency at a holdable pace beats sprints. See references/sustainability-and-boundaries.md.

How it runs (advisory + honest)

WoopSocial has no inbox. It publishes/schedules (the flywheel's first half); it cannot pull comments/DMs or post replies. Post performance for the covered platforms is analytics-and-reporting, not this skill, and it cannot name a best time. The human engages in-app via native notifications; the agent drafts replies/comments (→ reply-and-comment-writer).
Genuine only. No automation, bots, mass auto-comments, or bought/fake engagement — detected, penalized, self-defeating. The agent assists by drafting; the human does the real interacting.

Quality bar — self-check

Did I design a concrete, time-boxed daily + weekly cadence, centered on the golden hour?
Did I use the flywheel (schedule to free the time) and right-size to the user's time/platforms?
Did I give a triage order, aim at a goal with native signals (no fabricated analytics), and focus on the right people?
Did I make it sustainable (boundaries, response windows, not always-on)?
Did I keep it advisory (human engages in-app, agent drafts) and genuine (no automation/fake)?

Edge cases & pushback

"Auto-reply / mass-comment for me" → refuse automation/fake; genuine routine + draft-for-review.
"WoopSocial: pull my comments + tell me the best time" → no inbox, and post analytics are not a timing model; native inbox + agent drafts.
"No time to engage" → batch + schedule to free time (the flywheel); don't engage less.
"Reply to everyone everywhere" → triage + the right people; done beats perfect.
"I'm burning out checking all day" → windows + notification discipline + response boundaries.
"How do I know it's working?" → goal + native signals (comment depth, DM convos); no vanity, no fabricated numbers.

reply-and-comment-writer — the craft this schedules (drafts the replies/comments/DMs).
scheduling-and-queue, batch-content-plan — the flywheel's first half (free the time).
instagram-growth, tiktok-growth, linkedin-growth — call for this routine; strategic commenting.
community-management — deeper community; crisis-and-moderation — real crises; social-strategy — the goals.

References

references/the-daily-and-weekly-routine.md — the concrete cadence: windows, the golden hour, order of operations, weekly rhythm, scaling.
references/the-scheduling-engagement-flywheel.md — freeing time by scheduling, the flywheel, and the honest WoopSocial boundary.
references/triage-priorities-and-goals.md — what to do first, the right people, and goal/signals without analytics.
references/sustainability-and-boundaries.md — anti-burnout boundaries, consistency at a holdable pace, genuine-only.

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 Engagement Routine AI skill do?

Why use Engagement Routine on TypingMind?

Because you install it once and use it with any model. Engagement Routine 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 Engagement Routine in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/engagement-routine. 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 Engagement Routine?

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 Engagement Routine?

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

Is the Engagement Routine 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

Brand Guidelines

anthropics

OrganizationPopular

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual…

Solid

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

Canvas

Present hosted widget documents on a connected macOS panel and control panel visibility or navigation.

Diagram Maker

Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.

Engagement Routine

Overview