linkedin-studio/skills/linkedin-studio/SKILL.md
Kjell Tore Guttormsen be8c9b01fb fix(linkedin-studio): S11 — model-name declaration drift + model-consistency lint guard
Cold full-brief re-review (S10) reached a class the S7->S9 algorithm-stat lens
never did:

BLOCKER — post-feedback-monitor published as Haiku in four surfaces
(README:259, skills/linkedin-studio:159 with wrong color Green too,
skills/linkedin-analytics:41, agents-capability-matrix:20) while
agents/post-feedback-monitor.md runs Opus. v4.0.0's Opus promotion never
reached the user-facing tables. Synced all to Opus/Lime. Refreshed
agents-capability-matrix.md (frozen at the v2.0 14-agent era): header 14->19,
+5 missing longform agents, tier counts Opus 2->8 / Haiku 1->0, longform-gate
diagram updated to the real 8-Opus-agent chain.

MAJOR — de-branded docs/plan-fullspektrum-innholdsmotor.md:70 (model brand +
jan-2026 asserted as fact -> no-name/no-month relevance-model phrasing). It was
the only tracked survivor; the rest live in gitignored ROADMAP.md /
.claude/research/ (not shipped, out of honesty scope).

META — added Section 10 model-consistency guard
(scripts/check-model-consistency.mjs): each agents/*.md model: must match every
surface declaration AND the canonical rosters must list all 19 agents.
Permanent non-vacuity self-test + e2e mutation-proven.

Pre-patch sweep confirmed post-feedback-monitor was the sole drifted agent
(89 model rows, 0 other mismatches). test-runner.sh 68/0/0, node --test 94/94.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 15:05:37 +02:00

181 lines
9.7 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
name: linkedin-studio
description: |
Main entry point and router for LinkedIn Studio. Provides overview, status, and routes to 5 specialized skills. Contains shared algorithm knowledge and content quality standards.
This skill should be used when the user wants a general overview, needs help choosing the right LinkedIn command, or asks about LinkedIn capabilities.
Triggers on: "LinkedIn help", "LinkedIn overview", "what LinkedIn commands are available", "show LinkedIn status", "LinkedIn plugin", "LinkedIn capabilities", "how does the LinkedIn plugin work", "LinkedIn commands list".
---
## Personalization
**To customize this skill for your voice and goals:**
1. Copy `config/user-profile.template.md` to `config/user-profile.local.md`
2. Fill in your profile, voice preferences, and goals
3. The skill will use your settings when generating content
If no personalization file exists, the skill works with generic best practices.
---
## Skill Architecture
This plugin uses **6 focused skills**. This main skill contains shared knowledge (algorithm, quality, personalization). Domain-specific guidance lives in the specialized skills:
| Skill | Domain | Key Commands |
|-------|--------|--------------|
| **linkedin-content-creation** | Post creation, templates, batch, pipeline, video, long-form | `/linkedin:post`, `/linkedin:quick`, `/linkedin:batch`, `/linkedin:pipeline`, `/linkedin:multiplatform`, `/linkedin:video`, `/linkedin:newsletter` |
| **linkedin-analytics** | Analysis, reporting, import, troubleshooting | `/linkedin:analyze`, `/linkedin:audit`, `/linkedin:import`, `/linkedin:report` |
| **linkedin-strategy** | Growth, authority, competitive, monetization | `/linkedin:strategy`, `/linkedin:competitive`, `/linkedin:monetize` |
| **linkedin-networking** | Engagement, collaborations, speaking | `/linkedin:outreach` |
| **linkedin-voice** | Voice training, profile, differentiation | `/linkedin:profile` |
### Routing Guide
| User Intent | Route To |
|-------------|----------|
| "Just installed" / "Walk me through" | `/linkedin:onboarding` |
| "Set up plugin" | `/linkedin:setup` |
| "Personalize" | `/linkedin:setup` |
| "Improve personalization" | `/linkedin:setup` |
| "Write a LinkedIn post" | linkedin-content-creation |
| "Quick post about..." | linkedin-content-creation |
| "Create a week of content" | linkedin-content-creation |
| "Turn this into a carousel" | linkedin-content-creation |
| "Create a video script" | linkedin-content-creation |
| "LinkedIn video" | linkedin-content-creation |
| "Video for LinkedIn" | linkedin-content-creation |
| "Why isn't my content performing?" | linkedin-analytics |
| "Generate weekly report" | linkedin-analytics |
| "Import my LinkedIn data" | linkedin-analytics |
| "Audit my content strategy" | linkedin-analytics |
| "How do I grow on LinkedIn?" | linkedin-strategy |
| "Build my authority" | linkedin-strategy |
| "What are competitors doing?" | linkedin-strategy |
| "How to monetize LinkedIn" | linkedin-strategy |
| "Find speaking opportunities" | linkedin-networking |
| "Collaborate with someone" | linkedin-networking |
| "Engagement strategy" | linkedin-networking |
| "Optimize my profile" | linkedin-voice |
| "Does this sound like me?" | linkedin-voice |
| "Is this original enough?" | linkedin-voice |
---
### Algorithm Context (Profile/Topic Relevance, 2026)
LinkedIn's topic-relevance ranking now validates your profile across 5 criteria (About, Experience, Content History, Network, Engagement Patterns) BEFORE distributing content. Strong profile alignment = wider distribution. See the `linkedin-voice` skill for detailed profile optimization guidance and the full relevance-model framework.
---
## Shared Knowledge: Content Quality Rules
These rules apply to ALL content created by any skill or command:
1. **Hook:** 110-140 characters (mobile cutoff threshold)
2. **Post length:** 1,200-1,800 chars (standard), 150-500 chars (quick)
3. **No external links** in post body (correlate with lower reach — see `references/algorithm-signals-reference.md`)
4. **No corporate buzzwords:** leverage, synergy, paradigm shift, thought leader, disruptive, value proposition, ecosystem, holistic approach
5. **Topic alignment:** Must align with user's 5 core expertise areas (topic-relevance signal)
6. **Voice:** Always read `assets/voice-samples/` before generating content
7. **Quality scorecard:** See `assets/checklists/quality-scorecard.md`
---
## Shared Knowledge: Quick Start Guide
### First 24 Hours
**Hour 1 -- Foundation (15 min):**
- Rewrite headline: WHO you help + RESULT you deliver
- Review first 3 lines of About section (use linkedin-voice skill)
**Hour 2-3 -- Content Planning (30 min):**
- Pick 3-5 core topics
- Stick to these for 90 days minimum
**Hour 4-6 -- Create First Post (45 min):**
- Use linkedin-content-creation skill
- Structure: Hook -> Context -> Insight -> Implication -> CTA
- Check: 1,200-1,800 characters
**Hour 7-24 -- Strategic Engagement (30 min):**
- 5x5x5 method (see linkedin-networking skill)
- Respond within 5 minutes to first comments
**Week 1 Commitments:**
- Post 3x this week
- 15 minutes daily strategic commenting
- Respond to all comments within 2 hours
- Track each post in LinkedIn Analytics
---
## All Commands
| Command | Purpose |
|---------|---------|
| `/linkedin` | Router -- shows status line + command menu |
| `/linkedin:onboarding` | Multi-step onboarding wizard (profile → setup → first-post) |
| `/linkedin:first-post` | First-post accelerator (zero to published in 10 min) |
| `/linkedin:setup` | Guided setup to populate asset templates with real data |
| `/linkedin:react` | URL-to-post pipeline -- react to articles, news, research |
| `/linkedin:post` | Full post creation (10-15 min workflow) |
| `/linkedin:quick` | 5-minute quick post (3-line formula) |
| `/linkedin:profile` | profile/topic-relevance optimization |
| `/linkedin:analyze` | Content/performance analysis |
| `/linkedin:ab-test` | Design and manage A/B content tests |
| `/linkedin:strategy` | Growth strategy planning |
| `/linkedin:import` | Import CSV export to structured JSON |
| `/linkedin:report` | Generate weekly performance report |
| `/linkedin:batch` | Create a full week of content |
| `/linkedin:calendar` | View + manage post scheduling queue, and run the publish action (mark a scheduled post as published) |
| `/linkedin:pipeline` | Full end-to-end content pipeline |
| `/linkedin:newsletter` | Long-form orchestrator (newsletter editions, essays, series articles) -- single long-form entry point |
| `/linkedin:headless-review` | Cold adversarial review of a FROZEN long-form draft (argument, language, facts, reader-fit) before lock |
| `/linkedin:pivot` | Re-open a long-form edition after a late substantive change so cleared gates re-run before lock |
| `/linkedin:carousel` | Structured multi-slide carousel generator with visual layout guidance |
| `/linkedin:multiplatform` | Adapt content for other platforms (short-form/cross-format) |
| `/linkedin:audit` | Periodic content strategy audit |
| `/linkedin:competitive` | Competitive analysis of niche |
| `/linkedin:monetize` | Monetization strategy and funnels |
| `/linkedin:outreach` | Outreach orchestrator — collaborations + speaking opportunities |
| `/linkedin:video` | Video script generator (30s/60s/90s/2min) |
## All Agents
| Agent | Model | Color | Responsibility |
|-------|-------|-------|----------------|
| `content-optimizer` | Sonnet | Blue | Optimize existing posts |
| `strategy-advisor` | Sonnet | Green | Growth recommendations |
| `analytics-interpreter` | Sonnet | Yellow | Audience pattern analysis + weekly/monthly performance reports (interpret/report modes) |
| `engagement-coach` | Sonnet | Magenta | 5x5x5 + first-hour tactics + CEA commenting + target selection |
| `content-planner` | Sonnet | Cyan | Content audit + weekly/monthly plans |
| `network-builder` | Sonnet | Cyan | Strategic networking + outreach |
| `content-repurposer` | Sonnet | Magenta | Format conversion + evergreen refresh |
| `trend-spotter` | Sonnet | Cyan | Trending topics + opportunity scores |
| `voice-trainer` | Sonnet | Magenta | Voice profile building + drift detection |
| `differentiation-checker` | Sonnet | Blue | Originality scoring + commodity detection |
| `post-feedback-monitor` | Opus | Lime | Post-publish 48h monitoring, real-time interventions |
| `video-scripter` | Sonnet | Violet | Video script creation with pacing + visual cues |
| `fact-checker` | Opus | Brown | Factual-claim verification against primary/credible sources (longform) |
| `persona-reviewer` | Opus | Olive | Reader-persona skeleton + resonance + hook-conversion gate (longform) |
| `editorial-reviewer` | Opus | Orange | Editor's craft gate — prose-craft + narrative-architecture, before the persona sweep (longform) |
| `voice-scrubber` | Opus | Red | De-AI scrub + chronicle voice-drift correction; gold standard = approved editions in the configured language (longform) |
| `content-reviewer` | Opus | Maroon | Cold/headless argument-integrity review (C1C5) on a frozen draft (longform) |
| `language-reviewer` | Opus | Navy | Cold/headless language-quality review (L1L5); grades against the configured language (longform) |
| `fact-reviewer` | Opus | Gold | Cold/headless re-verification (F1F4 + pivot-risk) on the frozen draft (longform) |
---
### Reference Files
Each specialized skill includes its own relevant references. Key shared references:
- `references/algorithm-signals-reference.md` — Algorithm mechanics and signals
- `references/glossary.md` — Plugin terminology (38 terms)
- `references/troubleshooting-guide.md` — When reach drops or content underperforms
- `references/first-comment-strategy.md` — First comment timing and tactics
- `references/linkedin-visual-style.md` — Visual content standards and guidelines
For domain-specific references, see each skill's reference section.