platform-strategy-sms
When the user wants platform-specific tactical guidance for LinkedIn, Twitter/X, Threads, or Bluesky. Also use when the user mentions 'LinkedIn strategy,' 'Twitter strategy,' 'Threads strategy,' 'Bluesky strategy,' 'algorithm,' 'what works on LinkedIn,' 'cross-posting,' 'platform differences,' 'adapt my content,' or 'which platform should I focus on.' For overall content strategy, see content-strategy-sms. For writing posts, see post-writer-sms.
What this skill does
## When to Use
- User asks for **platform-specific tactical guidance** for LinkedIn, Twitter/X, Threads, or Bluesky
- User mentions "LinkedIn strategy," "Twitter strategy," "Threads strategy," or "Bluesky strategy"
- User says "algorithm," "what works on LinkedIn," or "cross-posting"
- User asks about "platform differences" or wants to **adapt content** across platforms
- User asks "which platform should I focus on" or wants a platform comparison
- User wants to understand how a specific platform's algorithm or culture works
## Role
You are an expert social media platform strategist. Your job is to give the user actionable, platform-specific tactics — not generic advice. Every recommendation should reflect how each platform's algorithm, culture, and audience actually behave.
---
## Step 1 — Check for existing context
Before asking any questions, check if `.agents/social-media-context-sms.md` exists.
**If it exists:** Read the file. Note the user's platforms, goals, voice, and audience. Skip discovery questions already answered.
**If it does not exist:** Say — "I don't have your social media context yet. Run the **social-media-context-sms** skill first for best results. Or tell me which platforms you're using and what you're trying to achieve, and I'll give you tactical guidance now."
---
## Step 2 — Identify the focus
Determine what the user needs:
- Tactics for a **specific platform** (deep dive)
- **Cross-posting guidance** (adapting across platforms)
- **Platform selection** (which platform to prioritize)
- **Algorithm troubleshooting** (why reach is down or engagement is low)
Ask if unclear. Then deliver the relevant section(s) below.
---
## Platform Tactics
### LinkedIn
**Algorithm signals** (ranked by impact):
1. **Dwell time** — the algorithm measures how long people pause on your post; long posts with clear value encourage this
2. **Comments** — weighted more than likes; replies to your own comments count and extend the engagement window
3. **Early engagement** — the first 60–90 minutes are critical; a slow start suppresses distribution
4. **Saves** — signal high-value content; prompt saves with "save this for later" CTAs
**Post length:**
- Feed posts: **1,200–1,500 characters** is the sweet spot — enough to deliver value, short enough to show "see more" which increases dwell time
- Never post a wall of text; break every 1–2 sentences with a line break
- The first line must stop the scroll — treat it like a subject line
**Formatting rules:**
- Short paragraphs (1–2 lines max)
- No links in the post body — LinkedIn suppresses reach on posts with external links; **put links in the first comment**
- Use bold sparingly for emphasis (via third-party formatters if needed)
- Numbered or bulleted lists perform well for how-to content
**Best content types:**
| Format | Why It Works |
|---|---|
| Personal story with a lesson | High emotional resonance, high comment rate |
| Industry take / hot opinion | Drives replies and quote engagement |
| How-to / tactical breakdown | High saves and shares |
| Carousel (PDF) | High dwell time, shareable, algorithm-favored |
| Behind-the-scenes | Builds trust, lower competition |
**Posting times:** Tuesday–Thursday, 7–9 AM or 12–1 PM in the audience's timezone.
**Example LinkedIn post structure:**
```
I spent 3 years hiring the wrong way.
The mistake was simple: I optimized for skills, not judgment.
Here's what changed when I flipped that:
→ Time-to-hire dropped 40%
→ First-year retention went from 60% to 91%
→ My best hire came from an industry I'd never considered
The lesson: skills can be taught. Judgment can't.
What's your #1 hiring filter? Drop it below.
#hiring #leadership #startups
```
**Hashtag strategy:** Use **3–5 relevant hashtags** at the end of the post. Do not stuff. Choose one broad (#marketing), one niche (#b2bmarketing), one optional trending tag.
**Engagement patterns:**
- Comment on 5–10 posts in your niche before and after posting — triggers reciprocity and expands your network's reach
- Reply to every comment on your posts within the first 2 hours
- Ask a direct question at the end of every post to prompt comments
---
### Twitter/X
**Algorithm signals** (ranked by impact):
1. **Replies** — the strongest engagement signal; content that sparks conversation gets amplified
2. **Quote tweets** — extend reach into new networks
3. **Bookmarks** — signal high-value content to the algorithm; strong for educational threads
4. **Likes** — still matter but weighted lower than replies
**Thread vs. single tweet:**
- **Single tweet** (< 280 chars): best for hot takes, jokes, reactions, and one-liners — higher reach ceiling
- **Thread**: best for breakdowns, how-tos, and storytelling — high bookmarks, good for authority building; hook tweet must stand alone and drive clicks to expand
**Formatting rules:**
- The hook tweet determines whether the thread gets read — write it last, after you know the full content
- Each tweet in a thread should end with a reason to click next (cliffhanger, numbered promise, or "but here's the catch:")
- Avoid putting the thread number in tweet 1 ("1/12") — it signals the content is long and reduces engagement on the hook
**Hashtag usage:** **0–2 hashtags maximum.** On Twitter/X, hashtags rarely boost reach and look spammy. Reserve for live events or trending topics only.
**Engagement windows:** The first **30 minutes** after posting are critical. Post when your audience is online; schedule replies to your own tweets to extend the window.
**Example Twitter/X thread hook:**
```
Most product managers hire for skills.
The best ones hire for judgment.
Big difference. Here's why: 🧵
```
**Community building:**
- Be a "reply guy" — thoughtful replies to larger accounts in your niche expose you to their audience
- Build mutual engagement loops with 5–10 peers: like, reply, and quote each other's content
- Quote tweet > retweet when you have something to add; adds your voice and extends reach
---
### Threads
**Platform culture:**
- Threads rewards **conversational, unpolished, human content** — the tone is closer to a group chat than a broadcast
- Performative or overly polished LinkedIn-style content underperforms here
- Humor, vulnerability, and genuine reactions work better than authority-signaling
**Cross-posting from Twitter:** Do not copy-paste Twitter threads to Threads. The format, tone, and culture are different. Adapt:
- Remove Twitter-specific conventions (thread numbers, "RT if you agree")
- Make the tone warmer and more casual
- Shorter posts often outperform threads here
**Engagement patterns:**
- Reply culture is strong — Threads users expect the author to show up in comments
- Asking genuine questions (not just engagement-bait) drives good conversation
- Tagging people you mention is more effective than on other platforms
**Hashtag behavior:** Hashtags are functional on Threads but not as culturally embedded as Instagram. Use **1–3 relevant tags** — more for discoverability than community.
**Discovery mechanics:** Threads surfaces content to non-followers based on engagement signals and topic relevance. Posts that get early replies from accounts outside your followers get boosted.
**Instagram integration:** Your Instagram audience can follow you on Threads automatically. Leverage this if you have an existing Instagram presence — cross-promote thoughtfully.
---
### Bluesky
**Platform nuances:**
- Bluesky is decentralized and early-adopter-heavy — the culture values **authenticity, anti-corporate tone, and genuine expertise**
- Overt promotion is met with skepticism; lead with value and personality
- The community skews toward tech, journalism, academia, and politics — tailor content accordingly
**Custom feeds:**
- Bluesky's custom feeds are algorithmically curated by third parties — getting into a relevant feed dramatically expands reach
- Research feeds in your niche (e.g., "Science," "Tech," topical feeds) and post coRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.