ワンクリックで
collector
Autonomous intelligence monitor -- continuous web monitoring, change detection, knowledge graph updates, and event alerts
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Autonomous intelligence monitor -- continuous web monitoring, change detection, knowledge graph updates, and event alerts
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Author one loop-harness planning ticket in the format the implement-ticket loop consumes. Use when asked to plan a feature, scope a change, draft a ticket, or turn a described problem into a ticket the loop can run. Writes one ticket file to the configured plans directory.
Run one planning ticket through the loop lifecycle - perceive (ledger + git reconcile), implement tests-first, gate via `loopctl stamp`, self-review, adversarial review, commit, close via `loopctl finish`. Use when asked to implement the next ticket, run the loop, or continue autonomous ticket implementation.
Generate static artwork/illustrations for a repo with Nano Banana Pro (aka "nano banana", Gemini 3 Pro Image) via the bundled generate_art.py — craft a detailed prompt, run the script, view the result, iterate. Use this whenever the user wants to create, generate, or regenerate a visual asset for a project: an architecture diagram, portrait, card/illustration, icon, splash, or any image that lands as a PNG in the repo — even if they don't name the tool or just say "make me an image / a picture of X". Do NOT trigger for application runtime image needs, or for editing source code rather than producing an image file.
Remove a solid background from an image and write a transparent PNG, using the bundled remove_background.py. Use this whenever the user wants to knock out, drop, or make transparent the background of a logo, banner, icon, or other static image asset in a repo, or to trim an asset to its content and pad it. Pairs with generate-art: generate a flat asset, then key its background here. Do NOT trigger for photo cutouts needing subject segmentation, for runtime image processing, or for editing source code rather than an image file.
Teach the user a new codebase, technology, framework, or system by walking through it from high-level architecture down to implementation details using a paginated, layered approach. Use this skill whenever the user wants to understand how something works, needs onboarding onto a new technology, asks you to explain a system end-to-end, or says things like "walk me through", "explain how X works", "I need to learn X", "teach me", or "help me understand". Also use when the user shares documentation and asks to be taught from it.
Write or refactor project documentation — tutorials, how-to guides, reference pages, and explanation articles — using the Diátaxis framework. Enforces strict mode purity (a tutorial is not a how-to is not a reference is not an explanation), Orwell's six rules for clear prose, and a ladder-of-abstraction rhythm where concrete examples open and close each piece. Targets HUMAN readers — not agents — so emphasizes plain, everyday English over jargon. Use whenever the user asks to write, draft, refactor, edit, improve, or polish documentation — phrases like "write a tutorial", "draft a how-to", "turn this into a reference", "document this feature", "rewrite this doc", "improve the README", "add user docs", "document the API", "explain how X works for newcomers", or any task that produces user-facing prose for a software project. Triggers even when the user does not say "Diátaxis" explicitly — any doc-writing or doc-refactoring task gets this lens.
SOC 職業分類に基づく
| name | collector |
| description | Autonomous intelligence monitor -- continuous web monitoring, change detection, knowledge graph updates, and event alerts |
| version | 1.1.0 |
| metadata | {"hermes":{"tags":["productivity","intelligence","monitoring","alerts"],"category":"productivity"}} |
Activate on a schedule to track targets (companies, sectors, instruments, people, technologies), collect data from the web, build knowledge over time, detect changes, and alert when something significant happens.
surface (headlines only), deep (full articles), or exhaustive (multi-hop research). Default: deep.market, business, competitor, technology, or general. Default: market.true.30.true.memex_*). Do not shell out to curl.Use Memex for state and persistence (namespace: app:hermes:collector:*):
memex_kv_get(key="app:hermes:collector:{key}")
memex_kv_write(key="app:hermes:collector:{key}", value="...")
memex_retrieve_notes(query="...") # search existing knowledge
memex_list_entities(query="{topic}") # entity exploration
memex_kv_get(key="app:hermes:collector:last_run")
memex_kv_get(key="app:hermes:collector:known_state")
target_subject and focus_area from configuration.Based on target_subject and focus_area, construct search queries:
Run 5-15 web_search queries depending on collection_depth.
For each search result:
web_fetch on promising URLs to extract: key facts, dates, names, numbers.known_state from Phase 0 -- is this new information?Compare collected facts against the previous known_state:
Score each change:
known_state in KV with the latest facts:memex_kv_write(key="app:hermes:collector:known_state", value="{...updated facts...}")
memex_retain(
title="Collector Report: {target_subject} - {date}",
author="collector",
description="...",
tags=["collector", "intelligence", "{target_subject}"],
markdown_content=$REPORT_MARKDOWN,
vault_id="inbox",
background=True
)
Capture the returned note id into NOTE_ID if you need it later.
memex_kv_write(key="app:hermes:collector:last_run", value="{ISO-timestamp}")
alert_on_changes is enabled AND any CRITICAL or IMPORTANT changes were detected, send via Telegram with the format:COLLECTOR -- {target}: {change_summary}
If no significant changes, do nothing (no Telegram spam on quiet days).
Update KV counters:
memex_kv_write(key="app:hermes:collector:data_points", value="{total}")
memex_kv_write(key="app:hermes:collector:entities_tracked", value="{count}")
memex_kv_write(key="app:hermes:collector:reports_generated", value="{count}")
memex_kv_write(key="app:hermes:collector:last_update", value="{ISO-timestamp}")
known_state before collection so change detection works correctly. Without it, every fact looks new.app:hermes:collector: -- do not use the old app:openfang:collector: prefix.