Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Growth Engine

ASecurity

Growth Engine — a bounded, gated X growth system for @Agentik_os aimed at real follower growth (north star 10k) by being genuinely useful in the right conversations, never by spam automation. A daily Reply Radar finds high-leverage AI-agents/Claude threads via last30days/ScrapeCreators, drafts genuine on-voice replies, passes them through an adversarial anti-spam gate, then (only when ARMED with a valid X session) posts a LOW-CAPPED number of replies + likes via Playwright driving the operato...

2 stars
0 votes
0 copies
0 views
Added 10/2/2026
ai-agentsgobashrailsapi

Works with

cliapi

Security Analysis

A100/100

Pro scans all 11 files and shows the line behind each finding

Scanned 10/2/2026

$npx -y skills add agentik-os/claude-code-skills --skill growth-engine --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Growth Engine?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Growth Engine
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/agentik-os-growth-engine/badge)](https://www.skillsdirectory.com/skills/agentik-os-growth-engine)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: growth-engine
description: "Growth Engine — a bounded, gated X growth system for @Agentik_os aimed at real follower growth (north star 10k) by being genuinely useful in the right conversations, never by spam automation. A daily Reply Radar finds high-leverage AI-agents/Claude threads via last30days/ScrapeCreators, drafts genuine on-voice replies, passes them through an adversarial anti-spam gate, then (only when ARMED with a valid X session) posts a LOW-CAPPED number of replies + likes via Playwright driving the operator's logged-in session, with human pacing, dedup, and a kill-switch. Use when the user says '/omg-growth-engine', '/growth-engine', 'growth X', 'gagner des followers', 'reply radar', 'engager sur X', 'arm/disarm the growth engine'. NOT a mass like/follow/DM bot (that gets the account suspended and is refused), NOT the content publisher (that is agent-ecosystem-watch): this is the engagement layer, deliberately small-volume and quality-gated."
---

# Growth Engine

Durable follower growth is content plus genuine presence in the right conversations, not
automation X detects and suspends. This engine automates the HARD part (finding the best
threads, drafting excellent replies) and keeps the action layer deliberately small: a few
quality replies and light likes a day from @Agentik_os, gated and human-paced. The 10k
followers goal is the north star of a bounded loop (R-LOOP), measured weekly, never a
"spam until it works" loop.

## Why not full auto like/comment/follow

Mass automated engagement is the number-one pattern X spam-detection nukes. The realistic
outcome is a shadowban or suspension of the brand account, not growth. Bought/botted
followers are dead weight. So this engine refuses mass follow/unfollow, auto-DM, and
spray-reply. It does bounded, genuine, gated engagement only.

## Pipeline

```
cron (daily) → [1] RADAR   find threads → last30days --search x (ScrapeCreators)
             → [2] DRAFT   genuine on-voice replies (claude, sonnet)
             → [3] GATE    adversarial anti-spam/anti-cringe (claude, opus) — default reject
             → [4] QUEUE   dedup vs seen, cap replies + likes
             → [5] EXECUTE (armed + valid session) Playwright → bounded replies + likes, human-paced
             → [6] REPORT  HTML in ~/.omega/artifacts + Telegram alert
```

## Safety rails (non-negotiable)

- `armed` flag (`~/.omega/state/growth-engine/armed`) — kill-switch. Absent = drafts only.
- valid X session at `~/.omega/secrets/x-session.json` (else nothing posts, alert fires).
- gate `keep=true`, fingerprint unseen, under `EG_REPLIES_CAP` (6) and `EG_LIKES_CAP` (15).
- human pacing (22-75s between actions), per-char typing delay, skip already-liked.
- no em/en dash, <=280 chars, no @-spam (enforced in gate + queue, R-NODASH).

## Setup (one-time)

1. Bun runtime with Playwright: `mkdir -p ~/.omega/lib/growth-engine && cd $_ && bun add playwright`,
   then copy the executor: `cp scripts/playwright-engage.mjs ~/.omega/lib/growth-engine/`.
2. X session cookies (drives @Agentik_os): log into x.com, DevTools → Application → Cookies →
   copy `auth_token` and `ct0`, then:
   `bash scripts/x-session-setup.sh <auth_token> <ct0>` → writes ~/.omega/secrets/x-session.json.
3. Verify: `bun ~/.omega/lib/growth-engine/playwright-engage.mjs --check` → `check_ok`.

## Run

```
bash scripts/engage-run.sh                 # full run (drafts unless armed + session)
EG_MOCK=1 bash scripts/engage-run.sh       # fixtures, never posts (smoke test)
```

Env: `EG_REPLIES_CAP` (6), `EG_LIKES_CAP` (15), `EG_DAYS` (2), `EG_ANALYZE_MODEL`
(claude-sonnet-5), `EG_GATE_MODEL` (claude-opus-4-8), `EG_TOPICS_FILE`.

## Arm / disarm

```
touch ~/.omega/state/growth-engine/armed    # bounded auto-engagement on
rm    ~/.omega/state/growth-engine/armed     # kill-switch: drafts only
```

## Config & state

- `config/engage-topics.txt` — thread-finding queries.
- `~/.omega/state/growth-engine/seen.jsonl` — engaged fingerprints (never engage twice).
- `~/.omega/state/growth-engine/runs/<date>/` — radar, queue, results, screenshots.
- `~/.omega/artifacts/growth-engine-<date>.html` — daily report.

## Requires

- `SCRAPECREATORS_API_KEY` in ~/.omega/secrets/ (thread finding).
- `claude` CLI, `bun` + Playwright + chromium, a valid X session (setup above).
- last30days checkout at ~/.omega/repos/last30days-skill/.

Attribution

agentik-osagentik-os
View sourceSee grades on GitHubMore from agentik-os →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →