WeChat Article Search
zjp1997720/wechat-article-search
Searches WeChat public account articles by keyword through Sogou WeChat Search and returns titles, summaries, dates, source accounts and links.
Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and…
Install Content Factory
$ npx skills add huytieu/COG-second-brain --skill content-factory -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install huytieu/COG-second-brain content-factory --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/huytieu/COG-second-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/content-factory .claude/skills/content-factory && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "content-factory" agent skill from https://github.com/huytieu/COG-second-brain/tree/main/skills/content-factory into .claude/skills/content-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-factory", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/huytieu/COG-second-brain/tree/main/skills/content-factoryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add huytieu/COG-second-brain --skill content-factory -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install huytieu/COG-second-brain content-factory --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/huytieu/COG-second-brain.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/content-factory .agents/skills/content-factory && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "content-factory" agent skill from https://github.com/huytieu/COG-second-brain/tree/main/skills/content-factory into .agents/skills/content-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-factory", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add huytieu/COG-second-brain --skill content-factory -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install huytieu/COG-second-brain content-factory --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/huytieu/COG-second-brain.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/content-factory .cursor/skills/content-factory && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "content-factory" agent skill from https://github.com/huytieu/COG-second-brain/tree/main/skills/content-factory into .cursor/skills/content-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-factory", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/huytieu/COG-second-brain.git --path skills/content-factory--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add huytieu/COG-second-brain --skill content-factory -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install huytieu/COG-second-brain content-factory --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/huytieu/COG-second-brain.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/content-factory .gemini/skills/content-factory && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "content-factory" agent skill from https://github.com/huytieu/COG-second-brain/tree/main/skills/content-factory into .gemini/skills/content-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-factory", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install huytieu/COG-second-brain content-factoryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add huytieu/COG-second-brain --skill content-factory -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/huytieu/COG-second-brain.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/content-factory .github/skills/content-factory && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "content-factory" agent skill from https://github.com/huytieu/COG-second-brain/tree/main/skills/content-factory into .github/skills/content-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-factory", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add huytieu/COG-second-brain --skill content-factory -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install huytieu/COG-second-brain content-factory --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/huytieu/COG-second-brain.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/content-factory .opencode/skills/content-factory && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "content-factory" agent skill from https://github.com/huytieu/COG-second-brain/tree/main/skills/content-factory into .opencode/skills/content-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-factory", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
content-factory- GitHub stars
- 1.3k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 857 words
- Files
- 1
- Skills in repo
- 37
- Repo updated
- First seen
- Licence
- MIT
At a glance
Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and…
- Works in 5 steps: SCOUT (every run) → TRIAGE (score, don't vibe) → PRODUCE (format ladder — decide by… → …
- Productivity & Automation work in your project
- SKILL.md covers Purpose, When to Invoke, Prerequisites and State Files (read FIRST,…, plus 8 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Content Factory is an agent skill from huytieu/COG-second-brain. Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and screenshot-verified publishing
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Productivity & Automation. The repository describes itself as: Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework… The licence is MIT.
When your agent uses it
- Productivity & Automation work in your project
Example prompts
- “/content-factory”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 36ac9d7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Content Factory loads about 1.6k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 857 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from huytieu/COG-second-brain at commit 36ac9d7, republished under its MIT licence (© huytieu). 857 words, ~1,552 tokens.
Download SKILL.mdSave it as
.claude/skills/content-factory/SKILL.md (or your agent's skills folder).- name
- content-factory
- description
- Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and screenshot-verified publishing
- roles
- all
- integrations
- web-search, web-fetch
COG Content Factory Skill
Purpose
Act as the user's autonomous content creator: scout what just happened in their field, pick what is genuinely trending, and turn it into content in their voice — with zero duplicates, hard volume caps, and verification before anything counts as published. Designed to run unattended on a schedule (nightly) and to be safely re-runnable: an empty run is a valid run; a low-quality post is not.
When to Invoke
/content-factory/ "run the content factory"- Scheduled runs (e.g. 2-4 times a night via cron/launchd)
- "Turn today's news into content"
Prerequisites
Reads the user's voice and beats from 00-inbox/MY-PROFILE.md and topics from 00-inbox/MY-INTERESTS.md. Publishing targets come from 00-inbox/MY-INTEGRATIONS.md — skip disabled channels silently.
State Files (read FIRST, update LAST — this is the dedup backbone)
04-projects/content-factory/ledger.md— everything ever covered/published (topic slug, source URL, formats, links, date). NEVER cover a topic or source URL already in the ledger unless there is genuinely NEW news (a follow-up release counts; rephrasing the same launch does not).04-projects/content-factory/tonight-<YYYY-MM-DD>.md— tonight's run log (create on first run of the night). Records what earlier runs scouted, parked, produced, and published, plus the remaining volume budget.04-projects/content-factory/sources.md— the watchlist. Add sources you find valuable; prune dead ones.
Volume Budget (across ALL runs of one night, hard caps)
| Channel | Max/night | Notes |
|---|---|---|
| Short social posts/threads | 2 | the volume channel; a thread counts as 1 |
| Blog post | 1 | only when substance justifies it |
| Short video | 1 | only if the idea is visual/demo-able |
| Long-form professional post | 1 | only for a strong professional angle |
| Long video / deep essay | 0 | never autonomous; propose in the run log |
Track the budget in the tonight file. Later runs inherit what is left. Adjust caps to taste — the invariant is that caps exist and are enforced across runs, not per run.
Phase 1 — SCOUT (every run)
- Web-search for last-24h announcements across the user's watchlist topics, plus anything already trending.
- Fetch the watchlist blogs/changelogs in
sources.md. - If a browser integration is available, skim the user's social feeds for engagement signals — raw engagement numbers are the best trend signal.
- Timebox scouting to ~20 minutes of work.
Phase 2 — TRIAGE (score, don't vibe)
Score each candidate 1-5 on:
- (a) trend momentum — are major accounts and aggregators talking about it NOW?
- (b) beat fit — does it fit one of the user's beats (from MY-PROFILE.md)?
- (c) unique angle — can we add something ONLY this user can add (an experiment, a practitioner take, a contrarian read) — not a summary anyone could write?
Sum ≥11 → produce. 8-10 → park in the tonight file for a later run to re-score. <8 → ignore.
Dedup check before producing: topic slug + source URL against the ledger AND against the user's recent published posts (last ~20) if reachable.
Phase 3 — PRODUCE (format ladder — decide by substance, not ambition)
- Default: one short post or thread — hook line, media attached, link last, minimal hashtags.
- Blog post only when there are ≥3 original things to say or a real proof-of-concept with artifacts. If the user has a PoC beat: actually build the tiny PoC (timebox ~45 min) and publish the REAL result, including failures. Never fabricate PoC outcomes; "it broke here" is good content.
- Short video when the idea is visual or demo-able in ≤60s.
- Cross-link everything (video ↔ blog ↔ thread reference each other).
Show full SKILL.md (313 more words)Show less
Phase 4 — PUBLISH (safety gates)
- Environment gate: if the publishing surface is unavailable, or the user appears to be actively using the browser/machine — DO NOT publish. Write finished bundles to
04-projects/content-factory/out/<date>/and let a later run (or the user) publish. - Post-condition check (mandatory): after every publish, observe the artifact — screenshot the live post, curl the live URL — before recording it as published. Never report success from the publish call alone.
- Never engage in arguments, never quote-dunk, never reply to strangers. The factory only creates original posts on the user's own surfaces.
- Any screenshot must pass a credentials check (no account emails, tokens, or internal URLs visible).
- Never delete an already-engaged post; edit in place if a fix is needed.
Phase 5 — LEDGER + LOG (always, even for empty runs)
- Append published items to
ledger.md:| date | slug | beat | formats | source URL | published links |. - Update
tonight-<date>.md: scouted list, scores, parked items, budget left, what the next run should look at first. - If a big announcement deserves long-form treatment the user should shape, write it as a proposal in the tonight file with a suggested outline — do not attempt it autonomously.
Voice Checklist (delete the draft if any fail)
- Sounds like a builder sharing, not a news bot ("I tried", "I broke", "here's what surprised me")
- Contains at least one thing only this user could say (their setup, their numbers, their PoC, their lens)
- No AI-slop vocabulary ("game-changer", "revolutionary", "unleash"), no emoji walls, hashtags within caps
- Media attached; link present; nothing confidential
- Not a duplicate (ledger + recent posts checked)
The Loop (see /loop-engineering)
Each night is a scan-until-budget-dry loop across runs: the tonight file is the shared loop state, the ledger is the dedup verifier, the volume budget is the hard cap, and the voice checklist is the quality gate. Termination: budget exhausted, nothing scores ≥11, or the environment gate blocks publishing.
© huytieu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/content-factory of huytieu/COG-second-brain.
Open the folder on GitHubat commit 36ac9d7
Compare with similar skills
Content Factory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Content Factory this skillhuytieu/COG-second-brain | 1.3k | — | ~1.6k | Automated safety check: Pass | MIT | |
| WeChat Article Searchzjp1997720/wechat-article-search | 269 | 1 repos | ~730 | Automated safety check: Notes | MIT | |
| Openpost CLIgetopenpost/openpost | 661 | — | ~1.3k | Automated safety check: Pass | AGPL-3.0 | |
| WeChat Article Publisheriamzifei/wechat-article-publisher-skill | 157 | — | ~2.6k | Automated safety check: Notes | MIT | |
| Sc Summaryremix-run/react-router | 57k | — | ~405 | Automated safety check: Pass | MIT | |
| Outlooksigcli/sigcli | 293 | — | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Openpost CLI
getopenpost/openpost
Operate a running OpenPost instance through the openpost CLI.
WeChat Article Publisher
iamzifei/wechat-article-publisher-skill
Publishes Markdown or HTML articles as drafts to a WeChat Official Account through an API client, with a first-time user walkthrough.
Sc Summary
remix-run/react-router
Summarize React Router Steering Committee meeting notes from a user-provided location in GOVERNANCE.md.
Outlook
sigcli/sigcli
Interact with Outlook email — read inbox, send emails, search messages, reply/forward, manage folders, download attachments.
Wechat Content Pipeline
843645440/wechat-skill
编排中文微信公众号文章。两条入口：用户成稿只排版推草稿（去 AI 味可关，不卡字数）；或给主题由 AI 写（去 AI 味强制开）。可降级配图、封面、随机主题，写入指定账号草稿箱。默认不扫热点、不公开发布。
More from huytieu/COG-second-brain
All 37 skills in this repoVoice Baseline
huytieu/COG-second-brain
Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style.
Daily Journal
huytieu/COG-second-brain
A passive daily work journal that Claude keeps FOR you so you never have to write it yourself.
Editorial Illustrations
huytieu/COG-second-brain
Generate meaning-carrying editorial data-illustrations in the monotykamary / Linear aesthetic (near-black grayscale, Inter display + mono labels, hairline framed figures) with a single coral accent.
Loop Engineering
huytieu/COG-second-brain
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns.
Release Video
huytieu/COG-second-brain
Turn a product release (the list of shipped items plus real screen recordings) into a motion recap video and one explained demo per feature, with sound effects tied to on-screen motion and a…
Onboarding
huytieu/COG-second-brain
Personalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!)
Related
Questions about Content Factory
What does Content Factory do?
Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and…. Content Factory is an agent skill from huytieu/COG-second-brain.
When should I use Content Factory?
Content Factory fits situations like: productivity & Automation work in your project.
How do I install Content Factory in Claude Code?
Run `npx skills add huytieu/COG-second-brain --skill content-factory -a claude-code`. Or copy the skill folder (skills/content-factory in huytieu/COG-second-brain) into .claude/skills/content-factory in your project. Claude Code loads it when a task matches its description.
How do I install Content Factory in Codex?
Run `npx skills add huytieu/COG-second-brain --skill content-factory -a codex`. Or copy the skill folder (skills/content-factory in huytieu/COG-second-brain) into .agents/skills/content-factory in your project. Codex loads it when a task matches its description.
Can I use Content Factory in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huytieu/COG-second-brain --skill content-factory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/content-factory, .gemini/skills/content-factory, .github/skills/content-factory and .opencode/skills/content-factory in your project.
What does Content Factory need to run?
SKILL.md names no scripts, command-line tools or credentials: Content Factory is instructions for the agent only.
Does Content Factory access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Content Factory safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Content Factory use?
Content Factory is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Content Factory use?
About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Content Factory?
Skills that share tags, products or a category with Content Factory: WeChat Article Search (zjp1997720/wechat-article-search, 269 stars), Openpost CLI (getopenpost/openpost, 661 stars), WeChat Article Publisher (iamzifei/wechat-article-publisher-skill, 157 stars) and Sc Summary (remix-run/react-router, 57k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Content Factory?
huytieu (a GitHub user) maintains it in huytieu/COG-second-brain, which has 1,268 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 2, 2026.
Source: huytieu/COG-second-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.