blog-drafting
Skill0 starsChanged 7 months agoMITView on GitHub
Generates blog post outlines from exercises and learnings for portfolio building. Triggers on /blog, blog idea, or after significant exercises. Produces structure and key points only -- the student writes the prose. Maintains a running ideas backlog in blog-drafts/ideas.md. Prioritizes topics that demonstrate hireable AI engineering skills.
In this repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adr-captureSkill
- adversarial-reviewSkill
- architect-firstSkill
- brainstorming-knowledge-builderSkill
- code-reviewingSkill
- session-startSkill
- debug-systemsSkill
- evolution-logSkill
- faang-loop-simulationSkill
- learn-in-publicSkill
- mock-assessingSkill
- os-lensSkill
- partner-systemSkill
- progress-updatingSkill
- review-systemsSkill
- spaced-reviewingSkill
- system-checkingSkill
- systems-traceSkill
- trend-scoutingSkill
- weekly-reflectingSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Every exercise is potential portfolio content.
- Distinctive: line 14
After completing significant exercises or topics
- Distinctive: line 15
When an insight is worth sharing publicly
- Distinctive: line 63
NEVER write the blog post.
- Distinctive: line 65
Every outline needs a clear "so what" -- why should anyone read this?
≈ “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.
Files
Blog Draft -- Portfolio Content Generator
Every exercise is potential portfolio content. Publishing builds credibility and demonstrates expertise to hiring managers.
Trigger
/blogor/blog <topic>- After completing significant exercises or topics
- When an insight is worth sharing publicly
Execution
- Identify the story angle (not "I learned X" but "Here's what surprised me about X"):
- What was non-obvious or counterintuitive?
- What would help another developer avoid a mistake?
- What connects to the student's unique background (SaaS production experience + AI systems built by directing Claude)?
- Generate outline (NOT the post):
BLOG DRAFT -- {topic} Title options: 1. [option -- specific, not generic] 2. [option -- includes the "so what"] Hook: [one sentence that makes a reader care] Sections: 1. [section] -- [2-3 sentences on what to cover] 2. [section] 3. [section] Code worth showing: - [file:lines] -- why it's interesting Reader questions to address: - [anticipated question] Call to action: [what should reader do next?] SEO keywords: [3-5 terms people search for] - Save to
blog-drafts/{slug}.md - Update
blog-drafts/ideas.mdbacklog
Unique Story Angles
These are angles unique to this learning journey:
- "I built production AI systems without writing code. Here's what happened when I learned to write it."
- SaaS production context applied to AI patterns
- The gap between directing AI and understanding AI
- Building a Claude-powered learning system from scratch
Rules
- NEVER write the blog post. Outlines only.
- Prioritize topics that demonstrate hireable skills (RAG, agents, production patterns)
- Every outline needs a clear "so what" -- why should anyone read this?
- Track all ideas, even ones not ready yet. The backlog compounds.
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
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.

