Skip to content

sergebulaev/linkedin-skills

linkedin-marketing

Verified

Plan, draft, audit, and publish LinkedIn posts and comments. Use when the user wants to write a viral LinkedIn post, draft a comment or reply on any LinkedIn post URL, audit a draft against 2026 algorithm heuristics, remove AI tells, extract hook formulas from viral posts, or plan a week of content. Powered by the Publora API for publishing. User provides post/comment URLs, skill drafts content, user approves, then publishes.

references/voice-rules.md

View on GitHub
# Voice Rules for Comments

## Hard rules

1. **Em dashes (`—`) capped at about 1 per 100 words** (so 0-1 in a comment, 1-2 in a post). The character is no longer a tell (2026 models use fewer than humans); the density is. Replace the excess with a comma, colon or parentheses, never a period. No en dashes (`–`) between clauses, no double dashes (`--`).
2. **Use `..` as soft pause** when you'd reach for a second em dash. Feels human, matches the author's own rhythm.
3. **Capitalize personal names, company names, product names** (HubSpot, Claude, etc.). Lowercase reads as disrespectful.
4. **Sentence starts can be lowercase** (natural voice), but names inside are always capitalized.
5. **Don't mention the user's own product by name** in comments on third-party posts. Describe what they do instead ("our AI content system", "the platform we're building").

## Vocabulary blacklist

Never use in comments:
- leverage, utilize, facilitate, streamline, robust, seamless, delve, navigate, unlock, harness, foster, cultivate
- fundamentally, essentially, ultimately, crucially, notably
- landscape, ecosystem, paradigm, realm, tapestry, journey
- "It's not just X, it's Y"
- "In today's fast-paced world"
- "Game-changer", "deep dive", "at the end of the day"

## Structure

- 200-350 chars. Two short paragraphs max. Line break between them.
- One concrete number or named entity per comment minimum.
- One line that could be screenshot and quoted standalone.
- Never end with "What do you think?" — dead prompt. End with a specific question or a clean landing.

## Anti-patterns

- Thesis restatement ("so true, AI is changing everything")
- Generic praise ("great insight!", "love this")
- Overused openers: "This.", "100%", "Couldn't agree more"
- Rule of three ("faster, cheaper, better")
- Passive voice over 10% of clauses

## Algorithmic Scoring Criteria (NLP-level)

LinkedIn's ranker runs NLP on comments and rewards:

- **Depth** — comments with ≥12 words and multiple sentence structures
- **New keywords** — introduce at least one noun/concept NOT already in the parent post
- **Questions** — end with one that invites a sub-thread
- **Sub-thread sparks** — comments that generate replies from the author AND other commenters count as a strong signal

**Before submitting, check:** does your comment add at least one noun/concept not already in the post? If no, rewrite.
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall