← Search

Twitter/X algorithm optimizer for tweet drafts
Marketing 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit be2a406
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: a tweet draft (or account content strategy) to…

Twitter/X algorithm optimizer for tweet drafts

Analyze, rewrite and debug tweet drafts using Twitter's open-source algorithm insights — Real-graph, SimClusters, TwHIN, Tweepcred, engagement signals

Version:

Quick answer

This ComposioHQ skill analyzes, rewrites and debugs your tweet drafts using insights from X/Twitter's open-sourced recommendation algorithm. It maps your draft to the ranking models and engagement signals the algorithm tracks, then applies documented optimization strategies — treating them as hypotheses to test against your own analytics, as its own caveats insist.

At a glance

What it isA playbook for your own posts: an explanation of how the open-sourced algorithm ranks content (Real-graph, SimClusters, TwHIN, Tweepcred, positive and negative engagement signals), plus six rewrite strategies and a four-step optimization process.
Who it's forPeople who post on X and want a principled way to improve a draft before publishing — their own content, not spam; the skill says so itself.
What you give itYour tweet drafts, and the core message you want each one to carry.
What you getAn analysis of the draft against the documented signals, a rewrite following the strategies with before/after reasoning, and a check against the negative signals — blocks, mutes, quick skips — before you post.
Works withMuse, installed from this page with the copy-paste install prompt. Its tactics are grounded in the open-sourced version of the algorithm; X's live ranking may have drifted since.
CostFree
TimeA few minutes to install. Optimizing one draft is one short pass: message, strategy, signals, negative check.

Example — workshopping a product announcement draft

An example of the process the skill documents, on a hypothetical draft — a method, not a promised result:

  • You paste a draft announcing a new feature and name its core message in one line, as step one of the process requires.
  • The skill maps the draft to a strategy — say, community resonance through SimClusters — and rewrites it so the post speaks to the community that would carry it, following its before/after pattern.
  • Before you post, it runs the negative-signal check: nothing that reads as engagement bait, nothing off-brand, nothing likely to earn a mute — and reminds you to judge the change against your own analytics afterwards.
⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit be2a406

Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a tweet draft (or account content strategy) to optimize; your own X/Twitter analytics to validate the strategies against; check the license terms yourself — the skill declares AGPL-3.0 in its frontmatter but the repo manifest declares no license Install "Twitter/X algorithm optimizer for tweet drafts" for me. It gives my agent @composiohq's playbook: the open-source ranking models (Real-graph, SimClusters, TwHIN, Tweepcred), the engagement signals tracked (explicit, implicit, negative), the feed pipeline, six optimization strategies with before/after rewrite examples, a 4-step optimization process, best practices and pitfalls — with the caveat that X's live algorithm has likely drifted from the open-sourced version, so validate against my own analytics. For optimizing my own content only. Repository: https://raw.githubusercontent.com/composiohq/awesome-claude-skills/be2a406907dbc61b73e6827ded415c96139d13a2/twitter-algorithm-optimizer/SKILL.md Pinned version: install the code at commit be2a406907dbc61b73e6827ded415c96139d13a2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "twitter-algorithm-optimizer". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. nothing — it is a strategy guide; hand the agent a tweet draft and ask for the optimization with the reasoning). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit be2a406 · 2026-10-13
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : files.pythonhosted.org, pypi.org
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
be2a406 · 2026-10-13
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: files.pythonhosted.org, pypi.org
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.