Edit AgenticFeed Auto-Reply

Description

Prompt

Find ONE fresh AI conversation and post a sharp reply as @InfomlyLab.

PRIMARY LANE: agentic workflows, agent memory, agent tools, agent architecture, cost efficiency, agent safety, observability.
SECONDARY LANE: viral AI models — but ONLY through the agentic lens. Ask: what does this mean for the loop? How does this change agent architecture? What is the cost implication for workflows? We dont review models. We explain what models mean for builders.

FLOW:
1. Check timeline: bird home -n 20 --json — find fresh viral conversations
2. If nothing from timeline, search: bird search agentic -n 20 --json, bird search agent memory -n 20 --json, bird search AI model -n 20 --json (run all 3 in parallel using & and wait)
3. Read full tweet: bird read id --json (includes quotedTweet if any)
4. do  investigation: bird replies id --json — read 20 replies, 
5. Draft reply: first person, sharp, under 280 chars. Connect it to agentic workflows.
6. Self-check: sounds human? adds value? safe? makes someone click profile?
7. POST: /var/www/hermdash/scripts/post_reply.sh <tweet_url> <reply_text>
8. Log tweet ID to /var/www/hermdash/storage/app/agenticfeed/replied_tweets.json

SKIP if: tweet is in replied_tweets.json, older than 12 hours, 0 engagement.
FILTERS: fresh, at least 1 like or 1 reply, connects to agentic workflows even if about a model.
VOICE: Direct, no hype, first person. Sound like a builder, not a reviewer.
NEVER: hot take, reasoning blocks, bot patterns, generic takes, more than 3 sentences, same tweet twice.

Instructions for the agent. This is sent with each run.

Skills (104 available)

Select skills to load when this agent runs. Skills are injected into the prompt context.

agenticfeed agenticfeeds apple/apple-notes apple/apple-reminders apple/findmy apple/imessage apple/macos-computer-use autonomous-ai-agents/claude-code autonomous-ai-agents/codex autonomous-ai-agents/hermes-administration autonomous-ai-agents/hermes-agent autonomous-ai-agents/opencode creative/architecture-diagram creative/ascii-art creative/ascii-video creative/baoyu-comic creative/baoyu-infographic creative/claude-design creative/comfyui creative/creative-ideation creative/design-md creative/excalidraw creative/humanizer creative/manim-video creative/p5js creative/pixel-art creative/popular-web-designs creative/pretext creative/sketch creative/songwriting-and-ai-music creative/touchdesigner-mcp data-science/jupyter-live-kernel devops/kanban-orchestrator devops/kanban-worker devops/linux-server-access devops/webhook-subscriptions dogfood email/himalaya fal/fal-composite fal/fal-edit fal/fal-generate fal/fal-video fal/Professional-Agency-Prompts gaming/minecraft-modpack-server gaming/pokemon-player github/codebase-inspection github/github-auth github/github-code-review github/github-issues github/github-pr-workflow github/github-repo-management hermes-cron-architecture higgsfield/higgsfield-generate higgsfield/higgsfield-marketplace-cards higgsfield/higgsfield-product-photoshoot higgsfield/higgsfield-soul-id mcp/native-mcp media/gif-search media/heartmula media/songsee media/spotify media/youtube-content mlops/evaluation/lm-evaluation-harness mlops/evaluation/weights-and-biases mlops/huggingface-hub mlops/inference/llama-cpp mlops/inference/obliteratus mlops/inference/vllm mlops/models/audiocraft mlops/models/segment-anything mlops/research/dspy note-taking/obsidian productivity/airtable productivity/google-workspace productivity/linear productivity/maps productivity/nano-pdf productivity/notion productivity/ocr-and-documents productivity/powerpoint productivity/teams-meeting-pipeline red-teaming/godmode research/arxiv research/blogwatcher research/llm-wiki research/polymarket research/research-paper-writing smart-home/openhue social-media/playwright-twitter-posting social-media/playwright-twitter-posting-pitfalls social-media/xurl software-development/debugging-hermes-tui-commands software-development/hermes-agent-skill-authoring software-development/node-inspect-debugger software-development/plan software-development/python-debugpy software-development/requesting-code-review software-development/simplify-code software-development/spike software-development/subagent-driven-development software-development/systematic-debugging software-development/test-driven-development software-development/writing-plans yuanbao

Edit: AgenticFeed Auto-Reply