flaqai/Awesome_SEO_Writing_Skill / writer/linkedin-writer
linkedin-writer
VerifiedLinkedIn-native long-form article and newsletter writing workflow for LinkedIn and Google-to-LinkedIn topic discovery, business-depth research, professional thought leadership, evidence-led drafting, final humanization, discussion design, SEO settings, auditing, and publish-ready packaging. Use when creating, outlining, researching, enriching, rewriting, humanizing, auditing, or packaging LinkedIn Articles, LinkedIn newsletters, LinkedIn long-form posts, LinkedIn thought leadership, LinkedIn B2B articles, LinkedIn 长文, LinkedIn 专栏, LinkedIn 话题调研, LinkedIn 商务内容, 去 AI 化编辑, or LinkedIn 发布包.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 23.4 KB |
| references/linkedin-article-template.md | markdown | 15.3 KB |
| references/linkedin-business-depth-and-humanization.md | markdown | 12.1 KB |
| references/linkedin-review-rubric.md | markdown | 12.3 KB |
| references/linkedin-topic-research.md | markdown | 15.0 KB |
| scripts/audit-linkedin-markdown.mjsexecutable | script | 18.5 KB |
references/linkedin-topic-research.md
View on GitHub# LinkedIn Topic Research and Conversation Map
Use this reference before outlining a LinkedIn Article, newsletter edition, or thought-leadership series. Its purpose is to find a professionally relevant conversation with enough evidence and specificity to support a useful article.
## Research Principle
LinkedIn topic research is not a hunt for the largest hashtag. The useful signal is the intersection of:
1. a recurring professional problem or decision;
2. a current change, tension, or misconception;
3. an audience the author can credibly help;
4. evidence or experience strong enough to support a point of view;
5. a question that qualified readers may want to discuss.
Search frequency, feed reach, and business relevance are different things. Do not treat one as proof of another.
## Source Hierarchy
Use the strongest available sources in this order:
1. User-provided customer questions, approved professional experience, support themes, sales objections, or internal research.
2. Primary platform, product, policy, standards, research, regulatory, or company sources.
3. LinkedIn's own search suggestions and filtered Posts results.
4. Original reports and credible industry datasets.
5. Attributable practitioner posts that add experience or disagreement.
6. Google results restricted to public LinkedIn Posts, Articles/Pulse pages, newsletters, and Company pages as conversation-discovery aids.
7. General web search, community summaries, and third-party trend lists as discovery aids only.
Do not use a search snippet as evidence when the original page can be opened. Do not copy the structure or conclusion of a high-performing post.
## LinkedIn Search Procedure
When LinkedIn search is available:
1. Enter the core phrase in the LinkedIn search bar.
2. Record type-ahead suggestions as discovery signals, not search-volume data.
3. Open the **Posts** category.
4. Compare recent and top results when the interface exposes sorting.
5. Apply useful filters such as date posted, content type, author industry, author company, mentioning member, or mentioning company.
6. Repeat with a natural-language problem or question, not only a keyword.
7. Inspect a small, relevant sample deeply enough to identify repeated questions, disagreements, examples, and vocabulary.
8. Search the same topic under **People**, **Companies**, **Groups**, **Events**, **Courses**, or **Products** only when that surface matters to the article.
LinkedIn search supports keywords and natural-language queries. Hashtags can be searched, but suggested searches do not necessarily surface hashtags. Treat hashtags as optional topic labels, not the main research method.
## Google Search for LinkedIn Content
Use Google when LinkedIn search is inaccessible, personalized, too narrow, or when the article needs a broader sample of publicly indexed LinkedIn conversations.
Start with:
```text
site:linkedin.com/posts "<topic>" "<professional role>"
site:linkedin.com/posts "<topic>" "<business outcome or objection>" after:YYYY-MM-DD
site:linkedin.com/pulse "<topic>" "<implementation, ROI, risk, or governance>"
site:linkedin.com/company "<topic>" "<official case, launch, or report>"
site:linkedin.com "<exact phrase>" -jobs -learning
```
Google officially supports quoted exact phrases, `site:`, exclusions with `-`, and `after:`/`before:` date operators. Do not put a space after `site:`.
For each useful result, record the query, date, URL, result type, author role, visible date, directly observed professional question or tension, and whether the original page was opened. Treat snippets as discovery text only. A LinkedIn post or Article may supply practitioner experience or a competing interpretation, but material factual claims still require primary or authoritative verification.
Read `linkedin-business-depth-and-humanization.md` for the complete Google-to-LinkedIn query matrix, business-depth extraction, synthesis rules, and `linkedin-insight-map.md` template.
## Query Grid
Generate 8-20 targeted queries from this grid:
| Dimension | Examples |
|---|---|
| Core entity or skill | AI agents, skills-first hiring, product-led growth, responsible AI |
| Audience or role | founder, CHRO, recruiter, developer, product manager, B2B marketer |
| Work outcome | revenue growth, quality of hire, faster delivery, risk reduction, retention |
| Tension | build vs buy, speed vs governance, automation vs judgment, reach vs trust |
| Implementation | workflow, operating model, metrics, adoption, mistakes, checklist |
| Career impact | skills, role redesign, hiring signal, portfolio evidence, leadership |
| Time/change | 2026, new policy, after launch, moving from pilot to production |
| Content intent | how, why, comparison, lessons, case study, what changed, what fails |
Example expansions for `AI agents`:
- `AI agents for product teams`
- `AI agent governance`
- `moving AI agents from pilot to production`
- `AI agents build vs buy`
- `how leaders measure AI agent value`
- `AI agents workflow redesign`
- `skills teams need for agentic AI`
- `AI agents failure modes`
Avoid repeating the same broad phrase with trivial wording changes.
## Topic Expansion Lenses
Use these lenses to enrich one article without losing focus:
### Professional outcome
What changes in cost, speed, quality, growth, hiring, learning, risk, customer value, or decision quality?
### Role impact
What does the topic mean for an individual contributor, manager, executive, buyer, candidate, operator, or specialist?
### Workflow
What happens before, during, and after adoption? What prerequisites, handoffs, review points, or metrics matter?
### Trade-off
Which desirable outcomes conflict? What does the popular advice ignore?
### Evidence
Which official data, original report, documented product behavior, or attributable example can support the article?
### Failure mode
Where does the method break? What is expensive, slow, risky, hard to measure, or inappropriate?
### Decision
What should the reader choose, stop, start, measure, or discuss with their team?
### Career and skill signal
Which capabilities, portfolio evidence, communication patterns, or leadership behaviors become more valuable?
## 2026 LinkedIn Topic Seeds
The following seed map was refreshed on **2026-08-12** from official LinkedIn Help, LinkedIn News, and LinkedIn business/editorial material. It is a starting point, not a permanent trend ranking. Recheck it for any time-sensitive assignment.
### 1. AI moves from experimentation into everyday work
Core topics:
- human-AI workflow design;
- agentic workflows and AI implementation;
- moving from pilots to production;
- measuring innovation, customer value, and workflow quality rather than only task speed;
- responsible deployment, governance, security, and compliance;
- AI literacy, prompt engineering, large language models, and strategic AI skills.
Related angles:
- Why AI adoption is becoming an operating-model question.
- What managers should redesign before adding another AI tool.
- Where human judgment remains the bottleneck.
- How to measure value when productivity metrics are incomplete.
- Which new roles connect models, workflows, governance, and customers.
### 2. Leadership and organizational change in the AI era
Core topics:
- continuous skill building for executives;
- CTO-CHRO collaboration;
- workforce visibility and role redesign;
- executive and stakeholder communication;
- team management, mentorship, and cross-functional coordination;
- innovation vs short-term efficiency.
Related angles:
- The new questions leaders need to ask about AI-enabled work.
- Why the skills plan and the technology roadmap must connect.
- How leaders communicate uncertainty without losing momentum.
- What an AI-ready team structure looks like in practice.
### 3. Skills-first hiring and changing career signals
Core topics:
- skills-first recruiting;
- verified AI proficiency and portfolio evidence;
- quality of hire;
- AI-assisted candidate discovery and screening;
- career transitions and skill gaps;
- job-search strategy in more competitive markets.
Related angles:
- How candidates can show capability when job titles lag behind the work.
- What recruiters gain and risk when AI expands candidate discovery.
- Why skills assessment is harder than removing degree requirements.
- How teams can evaluate AI fluency without rewarding tool-name lists.
### 4. Career development, learning, and internal mobility
Core topics:
- career development systems;
- upskilling and reskilling;
- internal mobility;
- manager-supported learning;
- mentorship and team capability building;
- learning tied to business outcomes.
Related angles:
- Why course completion is a weak proxy for capability.
- How managers turn learning into work evidence.
- When internal mobility is faster than external hiring.
- What makes a durable learning culture during rapid role change.
### 5. Business and revenue growth under tighter constraints
Core topics:
- go-to-market strategy;
- business development;
- expansion into new markets and channels;
- product-led, sales-led, and partner-led trade-offs;
- customer value and adoption;
- operating leverage without empty efficiency claims.
Related angles:
- Which growth motion fits the buying process.
- What teams should measure before scaling a new channel.
- How AI changes research, qualification, and customer education.
- Why more automation can still create a worse buyer experience.
### 6. B2B thought leadership, trusted experts, and hidden buyers
Core topics:
- expert-led and executive content;
- thought leadership as buyer education;
- B2B creators and subject-matter experts;
- hidden stakeholders in buying groups;
- trust, evidence, independent judgment, and disclosure;
- measuring audience quality rather than vanity reach.
Related angles:
- How one article can answer concerns from technical, financial, legal, and operational buyers.
- Why polished brand copy is not the same as expertise.
- What makes a point of view useful enough to change a buying discussion.
- How to turn comment objections into the next article.
### 7. Risk, governance, and trust
Core topics:
- governance, risk, and compliance;
- responsible AI and model oversight;
- privacy, security, and data handling;
- regulated workflows;
- documentation and accountability;
- speed vs control.
Related angles:
- The minimum governance layer before production adoption.
- How to separate policy from operating practice.
- What responsible deployment looks like for small teams.
- Which risks require a technical control and which require a decision process.
### 8. Human capabilities that gain value as tools improve
Core topics:
- cross-functional collaboration;
- executive and stakeholder communication;
- public speaking and clear writing;
- mentorship and team management;
- judgment, consulting, and relationship development;
- communicating through uncertainty.
Related angles:
- Why tool fluency without judgment creates shallow work.
- How specialists make technical choices legible to executives.
- What strong cross-functional coordination looks like in an AI project.
- How managers evaluate work when output becomes easier to generate.
## Topic Candidate Scorecard
Score each candidate from 1 to 5:
| Criterion | Question |
|---|---|
| Audience relevance | Does a defined professional reader face this problem now? |
| Timeliness | Is there a verified change, active tension, or current trigger? |
| Authority fit | Can this author credibly contribute evidence, analysis, or approved experience? |
| Evidence strength | Are reliable sources or attributable examples available? |
| Practical value | Can the reader make a decision or improve a workflow? |
| Distinctiveness | Is there a non-obvious thesis, trade-off, or synthesis? |
| Conversation potential | Can qualified readers answer a specific question? |
| Series value | Does this open a coherent follow-up topic without padding? |
Reject a topic if authority fit or evidence strength is below 3, even when it appears timely.
## `linkedin-topic-map.md` Template
```markdown
# LinkedIn Topic Map
## Research context
- Research date:
- Target audience:
- Author or Page:
- Core business/content goal:
- Available LinkedIn access:
- Verification limits:
## Query log
| Query | Surface/filter | Observed signal | Interpretation | Evidence strength |
|---|---|---|---|---|
| ... | Posts / past week / author industry | ... | ... | directional / supported |
## Google-to-LinkedIn query log
| Google query | Date | LinkedIn result type | Author role | Observed signal | Original opened | Evidence status |
|---|---|---|---|---|---|---|
| ... | ... | post / Article / newsletter / company | ... | ... | yes / no | conversation signal / practitioner experience / vendor claim / verified fact |
## Repeated questions and tensions
1. ...
2. ...
3. ...
## Candidate topics
| Topic | Audience | Thesis/tension | Evidence | Score | Main risk |
|---|---|---|---|---:|---|
| ... | ... | ... | ... | 0-40 | ... |
## Selected topic
- Working topic:
- Professional reader:
- Reader decision:
- Core thesis:
- Why now:
- Expertise basis:
- Related topics to include:
- Topics explicitly out of scope:
- Discussion gap:
## Refresh note
- What must be rechecked before publication:
```
## Research Stop Rule
Stop topic research when all of the following are true:
- the professional audience and reader decision are specific;
- one thesis is stronger than the alternatives;
- 3-6 material claims have viable evidence paths;
- related topics add depth without changing the subject;
- one real counterargument or limitation is visible;
- the article can end with a concrete professional question.
More browsing after this point often adds noise rather than value.
## Official LinkedIn Reference Points
Recheck these pages when platform behavior or current themes matter:
- LinkedIn search overview: https://www.linkedin.com/help/linkedin/answer/a523136/
- Search for member posts and available filters: https://www.linkedin.com/help/linkedin/answer/a526104
- Write and publish LinkedIn Articles: https://www.linkedin.com/help/linkedin/answer/a522427
- SEO settings for Articles and newsletters: https://www.linkedin.com/help/linkedin/answer/a6244140
- LinkedIn newsletter best practices: https://www.linkedin.com/help/linkedin/answer/a517940/
- Post and Article analytics: https://www.linkedin.com/help/linkedin/answer/a516971/
- LinkedIn's 2026 guidance on Article visibility and engagement: https://www.linkedin.com/business/marketing/blog/content-marketing/linkedin-articles
- LinkedIn/Edelman 2025 thought-leadership and hidden-buyer analysis: https://www.linkedin.com/business/marketing/blog/research-and-insights/b2b-thought-leadership-influence-hidden-buyers
- Skills on the Rise 2026: https://news.linkedin.com/2026/Skills-on-the-rise-2026
- LinkedIn 2026 C-suite and AI-era leadership data: https://news.linkedin.com/2026/new-linkedin-data--90--of-c-suite-leaders-are-continuously-build
- LinkedIn 2026 talent research: https://news.linkedin.com/en-us/2026/LinkedIn-Research-Talent-2026
- Google Search operators and refinements: https://support.google.com/websearch/answer/2466433
These sources inform the workflow; they do not guarantee that a topic will perform well.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |