一键在 Manus 中运行任何 Skill

growth-engine

星标6

分支1

更新时间2026年7月24日 20:13

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.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

agentik-os

agentik-os/OmegaOS

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

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)

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/.
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.
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-5), 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/.

同仓库更多 Skills

同仓库

agent-ecosystem-watch

agentik-os/OmegaOS

Agent-Ecosystem Watch — a daily autonomous intelligence pass over the Claude and AI-agent ecosystem on X. Reads a topic watchlist via last30days/ScrapeCreators, extracts CONCRETE improvements that make Claude / Claude Code / OmegaOS better (new features, prompting techniques, MCP servers, subagent/orchestration tricks, hooks, eval methods, model updates), scores each for integratability into OmegaOS, writes an HTML report + Telegram alert for the operator to decide, and (only when ARMED, behind an adversarial quality gate + daily cap + dedup) auto-publishes vetted best-practice tweets to @Agentik_os via omega-zernio. Use when the user says '/omg-ecosystem-watch', '/ecosystem-watch', 'veille Claude', 'veille agents IA', 'watch the Claude ecosystem', 'run the ecosystem watch', or wants to inspect/arm/disarm the daily watch. NOT a live web research primitive for one question (that is last30days / deep-research) and NOT a general social scheduler (that is the marketing suite): this is the standing daily radar tha

2026-07-246

changelog-adopt

agentik-os/OmegaOS

Claude Changelog Adopt — a daily autonomous self-improvement pass that reads the OFFICIAL Claude Code changelog (the authoritative GitHub CHANGELOG for anthropics/claude-code, with @claudecodelog as a secondary mirror), diffs it against the last version OmegaOS already absorbed, and for each NEW entry decides whether it implies a concrete OmegaOS or system-agent improvement — a new primitive, a doctrine change, an agent-behavior shift, a deprecation to unwind. It classifies each entry (opus), proposes a surgical adoption (what to change, in which file, why — like the manual /loop -> R-LOOP native-loop doctrine move), runs an adversarial anti-fabrication gate (opus, default-reject), writes a self-contained HTML report + Telegram alert for the operator to decide, and — only when ARMED — dispatches each vetted proposal to an oracle behind the full quality gate (In-Review handoff, never auto-Done, never force-push). Auto-adoption is scoped to doctrine (rules.rs), agent identities (agents/*.md), skills, and instal

2026-07-246

duo

agentik-os/OmegaOS

Binome Claude (stratège) ⇄ Codex/Sol (coder). Claude planifie, Codex challenge la stratégie puis implémente, Claude relit le diff et rend un verdict — avec bascule automatique sur Claude si le quota Codex est épuisé. Use when the user types /duo, /omg-duo, or says: build/implement/refactor/fix with the binome, code this with Codex, delegate to Codex/Sol, pair Claude and Codex, or FR 'code ça avec Codex', 'délègue à Sol', 'binome Claude Codex', 'fais coder Codex et relis'. NOT for pure questions, reads, or one-liners (Claude handles those directly — no need to burn the Codex quota).

2026-07-246

llm-council

agentik-os/OmegaOS

Convene a multi-model Claude COUNCIL for a high-stakes, ambiguous, or irreversible decision — or whenever you want a genuine second opinion. Four different Claude models (Opus 5, Sonnet 4.6, Haiku 4.5, Fable 5) answer the SAME question independently and in parallel, then peer-review each other ANONYMOUSLY (answers shown as Response A/B/C, model identity hidden, so no model is favored by name), and an Opus 5 president synthesizes the final verdict WHILE surfacing the dissent. Inspired by Karpathy's LLM Council, re-implemented on the OmegaOS Workflow primitive. 100% Claude Code-native — NO API KEYS, no OpenRouter, no external provider, no extra cost: the members run as in-process Workflow sub-agents through your EXISTING Claude Code session. Use when the user says "llm council", "convene the council", "ask the council", "@council", "/llm-council", "second opinion", "deliberate", "multiple models", or faces a "high-stakes decision" / architecture choice / contradictory verification verdicts / a pre-commit design

2026-07-246

stax

agentik-os/OmegaOS

Convert ANY project fully to Stax — the panels-inside-panels dashboard grammar (Miller columns, evolved): one mechanic (open-right), one action zone (the footer), one way back (close / breadcrumb). No pages, no modals, no tabs — the whole UI derives from a single serializable panel-workspace state (URL-synced, pinnable references, per-type sizing). Use when the user says "/stax", "/omg-stax", "convert to stax", "panelize this app", "make this a panel stack", "stax layout", "miller columns", "panels inside panels", "dashboard vision structure", or in French "convertis en stax", "passe en panneaux", "structure de dashboard". This is the OmegaOS dashboard vision structure — tracks github.com/agentik-os/stax main.

2026-07-236

linear-setup

agentik-os/OmegaOS

Complete Linear feedback system setup wizard (v2.1). Installs widget with priority selector + page-aware Scope labels, API routes with hardcoded label IDs and default CTO assignee, Linear label GROUPS (FEEDBACK / SOURCE / optional AGENTS), public feedback page, and MCP integration. Auto-detects dashboard pages from sidebar to generate Scope labels. Use when user says "/linear-setup", "setup linear", "add feedback system", or "install Linear widget". One-time setup. After setup, use /linear-fix to resolve tickets.

2026-07-206

name

growth-engine

description

Growth Engine

Why not full auto like/comment/follow

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)

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/.
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.
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-5), 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/.