with one click
linkedin-brand
// LinkedIn + personal brand system for founders. Apply when drafting LinkedIn posts, reactions, DMs, LinkedIn About sections, or planning LLM visibility.
// LinkedIn + personal brand system for founders. Apply when drafting LinkedIn posts, reactions, DMs, LinkedIn About sections, or planning LLM visibility.
Founder voice enforcement for all written output. Apply to any text another person will read.
Propose a principle edit to a skill or persona file based on a (agent_output, human_output) correction pair. Outputs a proposal markdown for human review - never auto-edits the target file.
Generate modern presentation decks (PDF) from markdown content. Local open-source alternative to Gamma — uses Slidev for layouts and Unsplash for imagery. Invoke when the user asks to "make a deck", "build slides from this", or "turn this into a presentation".
PRD creation and PRD execution operating system. Use when the founder asks to turn a rough idea into a PRD, run a Codex review on a PRD or issue, decompose an approved PRD into issue specs, or execute an issue with scope enforcement and receipt-based closeout. Not for general product ideation or casual drafting; this is the formal gated workflow.
Anti-hallucination research mode. Toggle on to enforce citation requirements, source grounding, and "I don't know" behavior. Toggle off for creative work.
AUDHD executive function accommodations. Apply to all output the founder will act on.
| name | linkedin-brand |
| description | LinkedIn + personal brand system for founders. Apply when drafting LinkedIn posts, reactions, DMs, LinkedIn About sections, or planning LLM visibility. |
This skill is the operating system for a founder's LinkedIn presence and broader LLM visibility. It enforces the 2026 algorithm reality (360Brew decoder-only LLM), provides summary frameworks, and governs the cross-platform entity graph that makes a founder legible to ChatGPT, Claude, Gemini, and Perplexity.
Auto-fire on any of these:
Skip for: internal ops chat, code, system files.
Always read in this order:
references/playbook.md — format rules, cadence, first-hour rulereferences/voice-check.md — AI-detection patterns to avoidreferences/summary-frameworks.md — if drafting/editing an About sectionreferences/llm-visibility.md — if question is about broader visibilityThen read instance-specific files (not bundled in the skill):
my-project/linkedin-playbook.md — this founder's committed pillarsmy-project/linkedin-summary-template.md — this founder's current About draftmy-project/llm-visibility-plan.md — this founder's entity graph and mention pipelineIf those instance files do not exist, ask the founder to create them before drafting. Do not invent pillars or positioning.
All patterns below are enforced deterministically by kipi_voice_lint and kipi_copy_edit_lint during the Pre-Publish Checklist. No memory-based self-check.
Enforced by kipi_voice_lint / kipi_copy_edit_lint:
\u2014 character)plugins/kipi-core/kipi-mcp/src/kipi_mcp/draft_scanner.py → TIER1_WORDS / TIER1_VERBS / TIER1_ADVERBS."in today's X" variant (regex), "let's dive in," "let's explore," "it's important to note," "it's worth noting," "in conclusion," "game-changer," "unlock the potential," "revolutionize the way," "circling back," "just checking in," "i'm excited to," "thrilled to share," "humbled by," and more. Full list: draft_scanner.py → BANNED_PHRASES.word, word, word): flagged as warning (non-blocking). Review context; if it reads generic, rewrite.If a pattern keeps slipping past, extend draft_scanner.py or linter.py. Never add rules to this file that ask Claude to remember.
See references/voice-check.md for the teaching reference.
Before drafting a reaction (comment, reply, quote-post, DM about someone's content):
Run in this order. Drafting is never blocked by cadence — only the final ship decision is.
When drafting a new original post, call kipi_linkedin_cadence_check() and surface the result to the founder. Do NOT block the draft — the founder may be preparing a post for a later week, or deliberately overriding the cap.
posts_this_week >= 3: surface verbatim "This would be your Nth post this week (cap is 3). Intentional override, or draft for next week?" and wait for the founder's answer before continuing.warnings[] contains engage_ratio: surface the ratio and suggest 2nd-degree comments before shipping. Not blocking.Skip Step 0 entirely when drafting a comment, reply, DM, or About section.
Call kipi_linkedin_gate(draft, kind, day_of_week, override_day). Pass kind every time based on what you are drafting:
kind="post" — original post. Hashtag, body-link, and day-of-week rules all apply.kind="comment" — comment or reply on another post. Hashtag and voice/copy rules apply; body-link and day-of-week rules do not.kind="dm" — direct message. Same as comment.kind="about" — LinkedIn About section. Same as comment.For kind="post" only:
day_of_week is the ship day weekday (tue/wed/thu). If you do not know the ship day, OMIT this field — passing today's weekday by default will block drafts prepared a day early.override_day=true bypasses the day-of-week gate.If pass: false, read violations[], lint_voice.violations[], and lint_copy.replacements/filler_words/passive_voice. Fix each one and re-run until pass: true. After 3 iterations, surface the violation verbatim and ask whether to override.
Violation types: hashtag_count, body_link (posts only), day_of_week (posts only), plus any from lint_voice (emdash, banned_word, banned_phrase, filler_opener, structural_opener, sentence_length, paragraph_uniformity, rule_of_three warning-only) and lint_copy (replacements, filler_words, passive_voice).
These require human judgment. Verify before returning:
my-project/linkedin-playbook.md)?[Pillar 1: scar], [Pillar 2: founder-op], [Pillar 3: AI/visibility])?If any subjective check fails, fix before returning the draft.
When the founder confirms a post shipped, call kipi_log_linkedin_activity(kind="post", url=..., pillar=...). Same for every 2nd-degree comment: kind="comment". This feeds Step 0's cadence check.
When the question is about visibility beyond LinkedIn (personal site, schema, podcasts, being findable by AI):
references/llm-visibility.md for the entity graph framework.my-project/llm-visibility-plan.md for the founder's committed plan.[Pillar 1: scar], [Pillar 2: founder-op], [Pillar 3: AI/visibility].my-project/linkedin-playbook.md, ask before drafting.{{UNVALIDATED}} or {{NEEDS_PROOF}}.founder-voice — apply alongside for voice DNA enforcementaudhd-executive-function — apply if founder profile flags AUDHD (all output must be copy-paste actionable)