ericrisco/rsc-harness / skills/linkedin-content
linkedin-content
VerifiedUse when writing the actual words of one LinkedIn feed post — turning a raw idea, story or asset into ready-to-paste copy: a text post, a document/carousel cover with slide copy and caption, or a short native-video script. Covers fixing a weak hook, reformatting a wall of text for the mobile feed, and a CTA that provokes a real comment. NOT planning what or when to post (that is `linkedin-strategy`), NOT designing the carousel slides and PDF export (that is `linkedin-carousels`), NOT DM sequences (that is `linkedin-outreach`), NOT programmatic publishing (that is `linkedin-api`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.7 KB |
| evals/README.md | markdown | 950 B |
| evals/cases.yaml | config | 4.0 KB |
| references/hooks-and-formats.md | markdown | 5.3 KB |
| scripts/verify.shexecutable | script | 5.8 KB |
evals/cases.yaml
View on GitHubskill: linkedin-content
# Prompts that MUST load `linkedin-content`. The skill owns THE WORDS of one
# LinkedIn feed post — text, document/carousel copy (cover + slides + caption),
# or a native-video script + caption — written to earn dwell and comments. It
# does NOT plan what/when to post (linkedin-strategy), design the carousel
# pixels (linkedin-carousels), write DMs/connection notes (linkedin-outreach),
# or publish via API (linkedin-api).
should_trigger:
- prompt: "Write a LinkedIn post about how we cut onboarding from 3 weeks to 3 days."
why: "Core job — turn a raw before→after story into a finished text post with hook, arc, and comment-CTA."
- prompt: "My hook is weak — rewrite the first three lines so people actually click 'see more'."
why: "Non-obvious: the user names the symptom (first three lines / see more), not the skill. The ~150-char hook rule and the Bad→Good hook table answer it directly."
- prompt: "Turn this into a LinkedIn document/carousel — give me the cover line and the slide copy."
why: "Document-post TEXT (cover + per-slide copy + caption) is owned here; only the slide layout/export belongs to linkedin-carousels."
- prompt: "Write a 45-second native-video script and the caption that goes with it."
why: "Native-video format (30–90s beats + caption) is one of the three formats this skill writes."
- prompt: "Give me a CTA that gets comments, not 'thoughts?'."
why: "Non-obvious phrasing — the comment-earning CTA + the dead-CTA banlist exist for exactly this; comments weigh ~15x likes."
- prompt: "fes-me un post de LinkedIn amb ganxo sobre el llançament"
why: "Catalan trigger — same skill regardless of language; the hook rules and arc apply."
- prompt: "Should the link go in the post or in the first comment?"
why: "Non-obvious: the body-link ~60% reach hit AND the now-dead first-comment workaround are a load-bearing fact this skill owns."
should_not_trigger:
- prompt: "Plan my LinkedIn content calendar and pillars for next month."
route_to: linkedin-strategy
why: "What/when/cadence is strategy; this skill only writes the words of one post inside that plan."
- prompt: "Design the actual carousel slides — layout and visuals — and export the PDF."
route_to: linkedin-carousels
why: "Pixels, not copy. linkedin-content writes the slide TEXT; the visual deck and export are linkedin-carousels."
- prompt: "Write connection requests and a DM follow-up sequence for these prospects."
route_to: linkedin-outreach
why: "Outbound 1:1 messages, not a public feed post — different playbook entirely."
- prompt: "Programmatically schedule and publish this post via the LinkedIn API."
route_to: linkedin-api
why: "Shipping/automation, not writing; the API integration is linkedin-api."
- prompt: "Define our durable LinkedIn brand tone and the words we never use."
route_to: brand-voice
why: "The reusable voice the copy must obey is brand-voice; this skill consumes that voice to write one post, it doesn't define it."
capability:
- scenario: "Given a rough story — 'we lost our biggest client and here's what I learned about retention' — produce a finished, ready-to-paste LinkedIn text post."
must_include:
- "A hook in the first ~150 characters with specificity or tension and NO greeting / no 'excited to share'."
- "The hook's first line reads complete on its own (won't truncate mid-clause on mobile)."
- "A clear hook → turn → payoff → CTA arc."
- "Total length lands ~1,300–1,900 characters (or a justified shorter length, not padded)."
- "Mobile line breaks: 1–2 sentence paragraphs with blank lines between blocks — no wall of text."
- "A comment-earning CTA that asks what only the reader can answer — never 'thoughts?' / 'agree?'."
- "No link in the body, and no 'link in first comment' suggestion."
- "A note about working the golden hour (reply fast, seed a question in the first 60–90 min)."
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |