Marketing content linkedin post
Skill b2bforce/b2bforce/.agents/skills/marketing-content-linkedin-post
Write a LinkedIn post (150-250 words, plain text) from a content idea. Use when content_type is linkedin_post. No Exa research. Stage-specific frameworks apply. Output to workspace/marketing/content/drafts/linkedin/. Not for blog or X formats.From its SKILL.md
npx -y skills add b2bforce/b2bforce --skill marketing-content-linkedin-postAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 1 command, including `scripts/validate-content-draft.sh {output}`.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.1 KB, 448 tokens by cl100k_base, as published. Nobody here has run it
LinkedIn Post Generation
Draft pipeline for a content idea of type linkedin_post.
When to Use
- Idea with
content_type: linkedin_post - User wants LinkedIn-native copy (not cross-posted blog summary)
Prerequisites
- Content idea file + firm/service/ICP/persona context
- Current agent/LLM session
- Do NOT run Exa reference search (skipped for this type)
Prompt layering
- Base writer (style only)
- Quality layer
- LinkedIn format layer →
references/format-requirements.md
Optional: workspace/firm/content-guidelines/linkedin-post.md
Follow the shared draft gate and writing quality rules in docs/content-generation.md.
Use buyer_question, unique_angle, proof_source, next_action, and
research_mode from the idea; do not write from title + description only.
Output format (critical)
- Plain text — NOT Markdown headers
- One sentence per line
- 150–250 words optimal; max ~300 words / 3000 chars
- 0–2 emojis if brand-appropriate
- 2–3 hashtags at end
- Engagement question at end
- No bullet lists (hurts engagement)
- First-person voice (I, we, you)
Stage → framework (from format prompt)
| Stage | Framework |
|---|---|
| Problem | Story Hook, Poll |
| Concept | Category, This-vs-That |
| Education | Framework, How-To |
| Decision | Comparison, Data |
| Vendor | CSR, Behind-the-Scenes |
Output path
workspace/marketing/content/drafts/linkedin/{slug}.md
Frontmatter: idea, content_type, buying_stage, service, icp, persona,
generated_at. Body = plain text only. Title in frontmatter for filing.
Run scripts/validate-content-draft.sh {output}. Update idea frontmatter to
status: generated after the draft validates.
Related Skills
marketing-content-x-post — different length/platform rules
What ships with it: 1 file
536 B alongside SKILL.md
references/
Gives 0 of the 12 instructions most marketing audience skills give in 448 tokens
Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07
- Apply Poppins font to headingsin 41 of 690, across 6 files
- Apply Lora font to body textin 41 of 690, across 6 files
- Use Arial fallback for headingsin 39 of 690, across 4 files
- Use Georgia fallback for body textin 39 of 690, across 4 files
- Maintain text hierarchy and formattingin 39 of 690, across 4 files
- Use accent colors for non-text shapesin 38 of 690, across 3 files
- Use RGB values for precise color matchingin 38 of 690, across 3 files
- Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
- Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
- Use active voice instead of passive voicein 26 of 690, across 10 files
- Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
- Prioritize clarity over clevernessin 22 of 690, across 8 files
Said here and by no other author read
- update idea status to generated
- Write plain text without Markdown headers
- Keep one sentence per line
- Keep post length under 300 words
- Put an engagement question at the end
- Write in first-person voice
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.