comments
Work the comments under published posts in one pass: list unanswered ones, reply only where a reply is genuinely expected (at most three per pass), name top commenters as warm-DM candidates, and prepare reply drafts on approval. Triggers: "/comments", "unanswered comments", "who
Install
npx skills add https://github.com/tonydzi/second-brain-starter-kit/tree/master/skills/comments
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install tonydzi-second-brain-starter-kit@llmmart
git clone https://github.com/tonydzi/second-brain-starter-kit.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole tonydzi/second-brain-starter-kit collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
/comments — comments under our content (show · reply · grow into a DM)
🧒 End the report to a non-technical owner with a short "In plain words" recap. (memory
eli5-always)
One pass: show the comments and reply surgically where a reply is actually expected. It collects and displays; it sends replies only on the owner's explicit "+". A thin layer (AK-47) over the engines in $IMPORTS_ROOT/content-factory\registry\.
🔴 BATTLE LESSON 2026-07-15 (memory
bulk-replies-cringe-one-offer-converts). The goal "zero unanswered" is CANCELLED: a batch of 16 replies to old comments was deleted by the owner in full ("my batch went out… I'm embarrassed myself"), comment auto-posting was turned off, and one of our accounts lost access to a third-party group. In the same night ONE public call-to-action post landed a partner within 30 hours. → Default = stay silent. Reply only if: it is addressed to us OR the thread is alive (younger than ~a week) OR a person is personally waiting for an answer. Older than that — skip, and that is NOT a debt. → Ceiling ≤3 replies per pass, never as a back-to-back series inside someone else's group: pace and volume read as a bot regardless of how good the text is. → Value is measured in people who moved, not in the unanswered counter.
Boundaries: this is about comments under OUR published posts (pubmetrics.db). The separate club corpus has its own skill (/sostav-comments). Facebook comments will be pulled in once the Graph token is live — for now the source is Telegram.
1. Fresh collection (0 tokens)
First refresh the database so you don't reply to stale material:
python tg_comments_collect.py(idempotent; exit 3 = the sending rail is busy → say "retry later", don't crash).
2. Show the state
python pub_metrics.py status— how many unanswered in total.python pub_comments_report.py— digest of the unanswered ones (spam bots fromspam_authors.txtare already flagged 🤖 and filtered out).python pub_metrics.py top-commenters --n 15— who comments most often.
Show it to the owner compactly: N unanswered per platform · top-5 commenters · link to the dashboard _Dashboards\Pub-Registry-Metrics.html.
3. If the owner asks for replies ("answer the comments" / "+")
Draft-first, sending by hand or on "+":
- RECALL the author before every reply to a human:
/find <name>(namesearch) + grep the vault + the Telegram profile (get_full_userby author_id from comments). Know who you are writing to. - Tone per channel ([[short-text-when-unreviewed]]): Telegram = a meaningful on-topic reply with context (NOT a 5-word Facebook joke). The owner's voice = the top-tier model.
- What to skip: spam bots 🤖 (no reply); old threads where a reply is no longer appropriate (decide explicitly).
- Show the batch as a table "comment → draft → which account sends it" and wait for "+". After sending —
pub_metrics.py mark-replied --cid <id>(or the nexttg_comments_collect.pywill setrepliedby itself).
4. Top commenters → a public call in the group, a DM on top
An active commenter with no CRM card = a candidate. Create the card (CRM), run a RECALL. ⭐ The offer (testers/a call/early access) goes publicly into the group, not by DM — a DM only as a personal nudge AFTER the public call (canon: the house rulebook offer-to-active-people-publicly-not-by-dm, memory public-offer-in-group). Don't send a DM without a "+" ([[telegram-account-identities]]). Clan members are not leads.
Boundaries / safety
- READ by default. Mass back-dated replying = a hard stop: batch only, and only with a "+".
- Spam filter: add a new bot wave to
spam_authors.txt(author_id # reason). - Nothing private from the comments leaks into other channels.
Related
The morning auto-ping of unanswered items into the fleet log chat (05:35, task "Pub-Comments-Morning") and the nightly collection (03:40, collect_pub_metrics.cmd) — this skill is the manual, on-demand twin of those routines. Canon: 00-System\Pub-Metrics-Registry.md, memory content-pub-registry.
Like this skill? It is part of second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.
Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).
Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_
Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.
Files (second-brain-starter-kit)
-
SKILL.md 5.5 KB
--- name: comments description: >- Work the comments under published posts in one pass: list unanswered ones, reply only where a reply is genuinely expected (at most three per pass), name top commenters as warm-DM candidates, and prepare reply drafts on approval. Triggers: "/comments", "unanswered comments", "who is commenting". license: MIT --- # /comments — comments under our content (show · reply · grow into a DM) > 🧒 End the report to a non-technical owner with a short "In plain words" recap. (memory `eli5-always`) One pass: show the comments and reply **surgically** where a reply is actually expected. It collects and displays; it **sends replies only on the owner's explicit "+"**. A thin layer (AK-47) over the engines in `$IMPORTS_ROOT/content-factory\registry\`. > 🔴 **BATTLE LESSON 2026-07-15** (memory `bulk-replies-cringe-one-offer-converts`). The goal "zero unanswered" is **CANCELLED**: a batch of 16 replies to old comments was deleted by the owner in full ("my batch went out… I'm embarrassed myself"), comment auto-posting was turned off, and one of our accounts lost access to a third-party group. > In the same night ONE public call-to-action post landed a partner within 30 hours. > → **Default = stay silent.** Reply only if: it is addressed to us OR the thread is alive (younger than ~a week) OR a person is personally waiting for an answer. Older than that — skip, and that is NOT a debt. > → **Ceiling ≤3 replies per pass**, never as a back-to-back series inside someone else's group: pace and volume read as a bot regardless of how good the text is. > → Value is measured in people who moved, not in the unanswered counter. **Boundaries:** this is about comments under OUR published posts (pubmetrics.db). The separate club corpus has its own skill (`/sostav-comments`). Facebook comments will be pulled in once the Graph token is live — for now the source is Telegram. ## 1. Fresh collection (0 tokens) First refresh the database so you don't reply to stale material: - `python tg_comments_collect.py` (idempotent; exit 3 = the sending rail is busy → say "retry later", don't crash). ## 2. Show the state - `python pub_metrics.py status` — how many unanswered in total. - `python pub_comments_report.py` — digest of the unanswered ones (spam bots from `spam_authors.txt` are already flagged 🤖 and filtered out). - `python pub_metrics.py top-commenters --n 15` — who comments most often. Show it to the owner compactly: N unanswered per platform · top-5 commenters · link to the dashboard `_Dashboards\Pub-Registry-Metrics.html`. ## 3. If the owner asks for replies ("answer the comments" / "+") Draft-first, sending by hand or on "+": 1. **RECALL the author** before every reply to a human: `/find <name>` (namesearch) + grep the vault + the Telegram profile (`get_full_user` by author_id from comments). Know who you are writing to. 2. **Tone per channel** ([[short-text-when-unreviewed]]): Telegram = a meaningful on-topic reply with context (NOT a 5-word Facebook joke). The owner's voice = the top-tier model. 3. **What to skip:** spam bots 🤖 (no reply); old threads where a reply is no longer appropriate (decide explicitly). 4. Show the batch as a table "comment → draft → which account sends it" and wait for "+". After sending — `pub_metrics.py mark-replied --cid <id>` (or the next `tg_comments_collect.py` will set `replied` by itself). ## 4. Top commenters → a public call in the group, a DM on top An active commenter with no CRM card = a candidate. Create the card (CRM), run a RECALL. ⭐ The offer (testers/a call/early access) goes **publicly into the group**, not by DM — a DM only as a personal nudge AFTER the public call (canon: the house rulebook `offer-to-active-people-publicly-not-by-dm`, memory `public-offer-in-group`). Don't send a DM without a "+" ([[telegram-account-identities]]). Clan members are not leads. ## Boundaries / safety - READ by default. Mass back-dated replying = a **hard stop**: batch only, and only with a "+". - Spam filter: add a new bot wave to `spam_authors.txt` (`author_id # reason`). - Nothing private from the comments leaks into other channels. ## Related The morning auto-ping of unanswered items into the fleet log chat (05:35, task "Pub-Comments-Morning") and the nightly collection (03:40, `collect_pub_metrics.cmd`) — this skill is the manual, on-demand twin of those routines. Canon: `00-System\Pub-Metrics-Registry.md`, memory `content-pub-registry`. <!--kit-footer--> --- **Like this skill?** It is part of [second-brain-starter-kit](https://github.com/tonydzi/second-brain-starter-kit): the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with `npx skills add tonydzi/second-brain-starter-kit`. Everything is open source and free, so take what you need. Flagships worth a look on their own: [secondop-panel](https://github.com/tonydzi/secondop-panel) (a second opinion from a panel of external models), [claude-memory-tidy](https://github.com/tonydzi/claude-memory-tidy) (stop your agent's memory from rotting), [telegram-mcp-kit](https://github.com/tonydzi/telegram-mcp-kit) (your own Telegram over MCP in about 15 minutes). Author: **Anton Dziatkovskii**, Palo Alto AI Research Lab. Telegram [@tonydzi](https://t.me/tonydzi) - WhatsApp [+1 341 222 9178](https://wa.me/13412229178) - X [@Tony_Stef_](https://x.com/Tony_Stef_) **Engineers: want to test-drive this setup?** Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.