agentleFS
Sign inStart free
DrFIRASSDrFIRASS/hermes-skills-autopilot/skills/content-forge/SKILL.md

content-forge

Skill14 starsChanged 7 months agoMITView on GitHub

Your content pipeline on rails. From raw idea → shot list → draft → shipped piece, across YouTube, LinkedIn, blog, and course platforms. Keeps the queue honest and the shipping schedule visible. content-forge is built for the voice-with-an-audience: creators, educators, consultants, and conference speakers. It owns workspace/content/pipeline.md and tracks every piece of content from the moment it's captured as an idea to the moment it ships. It does three things: Status legend: - ⚪ idea — captured, not yet committed…

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Culeot/content-forge-kit★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every piece flows through a set of stages specific to its channel.

    line 72
  2. Very specific:

    When the owner says advance <piece> the forge moves it to the next stage, time-stamps the transition, and — if the new stage is scheduled …

    line 82
  3. Very specific:

    Every idea lands in workspace/content/ideas.md with:

    line 93
  4. Very specific:

    Every Sunday evening, the forge produces a proposed shipping schedule for the next week.

    line 105

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

🎬 Content Forge

Your content pipeline on rails. From raw idea → shot list → draft → shipped piece, across YouTube, LinkedIn, blog, and course platforms. Keeps the queue honest and the shipping schedule visible.

🎯 Mandate

content-forge is built for the voice-with-an-audience: creators, educators, consultants, and conference speakers. It owns workspace/content/pipeline.md and tracks every piece of content from the moment it's captured as an idea to the moment it ships.

It does three things:

  1. Daily pipeline check (19:00) — surfaces what's due tomorrow, what's overdue, what's blocked
  2. Weekly planning (Sunday 18:00) — drafts next week's shipping schedule based on capacity and backlog
  3. Capture on demand — accepts new ideas via owner prompt, classifies, and files them

🗂️ The Pipeline File

# Content Pipeline — <YYYY-MM-DD>

## 📺 YouTube
| Title | Status | Stage | Ship date | Notes |
| --- | --- | --- | --- | --- |
| "Agentic AI in 2026 — the full stack" | 🟢 | script | 2026-04-22 | Long-form, 18 min |
| "5 n8n automations that saved me 10h/week" | 🟡 | recorded | 2026-04-20 | Editing pending |
| "Why Claude Skills change everything" | ⚪ | idea | — | Pin after ship |

## 💼 LinkedIn
| Topic | Status | Ship date | Angle |
| --- | --- | --- | --- |
| Launch of hermes-skills-autopilot | 🟢 | 2026-04-19 | Building in public |
| Recap of Paris AI Summit | 🔴 | 2026-04-23 | Thought leadership |

## 📚 Udemy / Course
| Module | Status | Release | Notes |
| --- | --- | --- | --- |
| Module 7 — Building production agents | 🟡 | 2026-04-25 | Recording done |
| Module 8 — MCP deep dive | ⚪ | 2026-05-10 | Outline stage |

## ✍️ Blog / Newsletter
| Title | Status | Ship date |
| --- | --- | --- |
| "The Heartbeat Model" essay | 🟢 | 2026-04-21 |

Status legend:

  • ⚪ idea — captured, not yet committed
  • 🟡 in progress — script / recording / editing in flight
  • 🟢 scheduled — slotted to ship on a date
  • 🔴 overdue — past ship date, needs attention
  • ✅ shipped — moved to workspace/content/shipped.md

🧪 Pipeline Stages

Every piece flows through a set of stages specific to its channel. The forge tracks which stage each piece is in.

ChannelStages
YouTube long-formidea → outline → script → recorded → edited → thumbnail → scheduled → shipped
YouTube shortidea → script → recorded → edited → scheduled → shipped
LinkedIn postidea → draft → scheduled → shipped
Blog / newsletteridea → outline → draft → edited → scheduled → shipped
Course moduleidea → outline → script → recorded → edited → uploaded → released

When the owner says advance <piece> the forge moves it to the next stage, time-stamps the transition, and — if the new stage is scheduled or recorded — auto-creates a follow-up task in mission-ledger for the next stage.

🧠 Idea Capture

Ideas arrive from three places:

  1. Owner prompt: capture: idea for a short on how n8n webhooks actually work
  2. knowledge-vault emits an idea_candidate note after a call or recording
  3. audience-echo surfaces a highly-engaged question from YouTube or LinkedIn

Every idea lands in workspace/content/ideas.md with:

  • Channel guess (forge auto-classifies, owner can override)
  • Source
  • Timestamp
  • Initial angle (one sentence)

Ideas older than 30 days with no activity are auto-archived with a note: "Stale — promote or release."

📅 Weekly Planning (Sunday 18:00)

Every Sunday evening, the forge produces a proposed shipping schedule for the next week. The proposal lands as a 🟡 Draft for review in the escalation channel:

🗓️ Next week's shipping proposal (2026-04-20 → 2026-04-26):

 Mon  LinkedIn: "Launch of hermes-skills-autopilot"
 Tue  YouTube short: "5 n8n automations that saved me 10h/week"
 Wed  Blog: "The Heartbeat Model" essay
 Thu  — (rest day declared)
 Fri  Udemy: Module 7 release
 Sat  YouTube long: "Agentic AI in 2026 — the full stack"
 Sun  —

Capacity: 5 pieces shipped / 6 scheduled
Backlog pressure: moderate (3 overdue → 0 overdue after this week)

Approve, edit, or reroll?

The owner can approve, edit, or reroll (which regenerates with different picks from the backlog). Nothing ships until approved.

⏰ Daily Check (19:00)

Quick scan of the pipeline. Outputs one of three things:

  1. Something due tomorrow is not ready → draft ping to escalation channel: "⚠️ LinkedIn post 'Launch of hermes-skills-autopilot' is scheduled for tomorrow but still in draft stage."
  2. Something is overdue → draft ping: "🔴 YouTube short '5 n8n automations' was due 2 days ago, still in editing. Bump or kill?"
  3. Pipeline is healthy → HEARTBEAT_OK.

🤝 Cross-Skill Contracts

Contract partnerWhat flows
mission-ledgerForge creates tasks when a piece advances to recorded (needs editing) or scheduled (needs thumbnail/preview).
audience-echoEcho hands the forge highly-engaged audience questions as idea candidates.
knowledge-vaultVault emits idea_candidate tags that land in ideas.md.
command-maestroMaestro reads pipeline status for morning briefings ("shipping today: X") and EOD reviews ("shipped this week: Y").

⚠️ Hard Never-Dos

  • Never auto-publish a piece, even if fully prepared. Shipping requires owner confirmation.
  • Never silently move a piece backwards in stages — require an explicit revert command.
  • Never overwrite ideas.md entries without archiving — ideas are compost, not trash.
  • Never propose shipping on a declared rest day.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free