JasonColapietro/suede-creator-skills / skills/suede-social
suede-social
VerifiedPlan, audit, and draft organic social for founder/brand accounts: platform mix, 30-post audits, calendars, Instagram, LinkedIn/X, short-video scripts, social search, and listening. Use when asked to "audit our Instagram growth" or build an approval-ready content loop. NOT FOR: paid ads (use suede-ads or suede-ad-creative), editorial agents (use suede-newsroom), clip-to-guide work (use suede-clip-to-guide), video rendering (use suede-video), or broad content strategy (use suede-content-strategy).
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 4.6 KB |
| SKILL.md | skill md | 14.2 KB |
| agents/openai.yaml | config | 643 B |
| evals/evals.json | config | 12.2 KB |
| references/account-audit.md | markdown | 5.2 KB |
| references/carousel-frameworks.md | markdown | 10.4 KB |
| references/content-production.md | markdown | 3.3 KB |
| references/daily-loop.md | markdown | 2.9 KB |
| references/listening-sources-template.md | markdown | 3.9 KB |
| references/listening.md | markdown | 12.8 KB |
| references/measurement.md | markdown | 2.8 KB |
| references/platform-limits.md | markdown | 3.0 KB |
| references/platforms.md | markdown | 7.0 KB |
| references/post-templates.md | markdown | 3.8 KB |
| references/reverse-engineering.md | markdown | 6.4 KB |
| references/short-form-video.md | markdown | 8.6 KB |
| references/social-search.md | markdown | 3.4 KB |
| references/worked-handoff.md | markdown | 1.7 KB |
references/platforms.md
View on GitHub# Platform-Specific Strategy Guide
Use these as starting hypotheses, never platform truths. Before recommending a
cadence, time, format, or algorithm tactic, check current official guidance and
the account's last 30–90 days of reach, retention, saves, replies, follows, and
production capacity. Preserve the ranges below only as first-test bounds when
account evidence is unavailable.
## Contents
- LinkedIn
- Twitter/X
- Instagram
- TikTok
- Facebook
## LinkedIn
**Fit hypothesis:** B2B, professional expertise, networking, recruiting
**Audience hypothesis:** professionals and work-context communities
**Starting cadence hypothesis:** 2–4 posts per week for a four-week test
**Timing test:** compare two audience-local windows drawn from current follower
activity; if unavailable, rotate morning, midday, and evening slots
**Formats to test:**
- Personal stories with business lessons
- Contrarian takes on industry topics
- Behind-the-scenes of building a company
- Data and original insights
- Carousel posts (document format)
- Polls that spark discussion
**Risks to inspect:**
- Overly promotional content
- Generic motivational quotes
- Uncontextualized links that move readers away before delivering value
- Corporate speak without personality
**Format tips:**
- Test whether the opening line establishes useful context before any current
truncation point; compare against the account baseline
- Use line breaks for readability
- Test a short and a long treatment of the same idea; use account-level dwell,
completion, and response data to choose
- Test native context with body links, comment links, or no link where current
platform guidance permits; compare qualified outcomes
- Tag people sparingly and genuinely
**Evidence to check:**
- Compare early and later response curves before setting reply windows.
- Compare comments, reactions, clicks, dwell, and follows at equal reach.
- Test text, document, link, and poll formats against the account baseline.
- Do not infer authority or algorithm preference from one high-reach post.
---
## Twitter/X
**Fit hypothesis:** real-time expertise, media, tech, and niche communities
**Audience hypothesis:** topic-led communities and professional peers
**Starting cadence hypothesis:** 3–5 original posts per week plus 3–5
substantive replies on each of 3–5 active days
**Timing test:** use current follower activity when available; otherwise rotate
three audience-local windows across comparable posts
**Formats to test:**
- Hot takes and opinions
- Threads that teach something
- Behind-the-scenes moments
- Engaging with others' content
- Memes and humor (if on-brand)
- Real-time commentary on events
**Risks to inspect:**
- Pure self-promotion
- Threads without a strong hook
- Ignoring replies and mentions
- Scheduling everything (no real-time presence)
**Format tips:**
- Test concise and expanded versions against equal-reach engagement and follow
outcomes
- Threads: Hook in tweet 1, promise value, deliver
- Compare original commentary, quote posts, and replies using current results
- Use visuals to stop the scroll
**Evidence to check:**
- Compare replies, quote posts, threads, text, images, and video at equal reach.
- Measure profile visits, qualified replies, follows, and downstream actions.
- Test response timing rather than assuming a first-30-minute advantage.
- Do not infer paid-account distribution benefits without a controlled
account-level comparison and current platform documentation.
---
## Instagram
**Fit hypothesis:** visual brands, creator narratives, commerce, lifestyle
**Audience hypothesis:** visual-first communities; verify account demographics
**Starting cadence hypothesis:** 2–4 feed posts per week plus Stories on 3–5
days per week
**Timing test:** compare two follower-active windows from current insights; if
unavailable, rotate midday and evening windows
**Formats to test:**
- High-quality visuals
- Behind-the-scenes Stories
- Reels (short-form video)
- Carousels with value
- User-generated content
- Interactive Stories (polls, questions)
**Risks to inspect:**
- Low-quality images
- Too much text in images
- Ignoring Stories and Reels
- Only promotional content
**Verified platform facts (October 2026):** at most 5 hashtags per post or
Reel; Reels up to 3 minutes; grid previews crop to 3:4; public posts from
professional accounts can be indexed by Google. See
[platform-limits.md](platform-limits.md).
**Format tips:**
- Compare Reels, static posts, and carousels at equal account conditions.
- Put the search phrase in the first caption line and on-screen text; captions
now double as search snippets.
- Test first-frame treatments against retention.
- Set carousel length from the idea and slide-level completion, not a fixed
count.
- Test only the Story features that serve the current goal and are available on
the authenticated account
**Evidence to check:**
- Compare format reach, retention, saves, shares, replies, and follows.
- Use Stories and interactive features only when they serve the audience goal.
- Treat consistency and format preference as account-level hypotheses.
---
## TikTok
**Fit hypothesis:** native short-form storytelling and discovery
**Audience hypothesis:** entertainment- and interest-led communities; verify
current account demographics
**Starting cadence hypothesis:** 3–5 posts per week for a four-week test
**Timing test:** compare follower-active windows when available; otherwise
rotate morning, midday, and evening slots
**Formats to test:**
- Native, unpolished content
- Trending sounds and formats
- Educational content in entertaining wrapper
- POV and day-in-the-life content
- Responding to comments with videos
- Duets and stitches
**Risks to inspect:**
- Overly produced content
- Ignoring trends
- Hard selling
- Repurposed horizontal video
**Format tips:**
- Test opening treatments in the first 1–3 seconds against retention.
- Start with two length bands that fit the idea, then use completion and
downstream action to choose.
- Verify current upload requirements and composer previews; test 9:16 when it
fits the placement, but do not reject another supported ratio without evidence
- Test native audio, original audio, and no-audio versions when rights and
account context permit.
- Keep the test cadence stable enough to compare cohorts; do not claim it
trains the algorithm.
---
## Facebook
**Fit hypothesis:** communities, local businesses, events, and groups
**Audience hypothesis:** community-oriented users; verify page or group insights
**Starting cadence hypothesis:** 2–4 posts per week plus community replies as
needed
**Timing test:** compare two audience-local windows from current insights; if
unavailable, rotate midday and early-evening slots
**Formats to test:**
- Facebook Groups (community)
- Native video
- Live video
- Local content and events
- Discussion-prompting questions
**Risks to inspect:**
- Link-only posts that provide no native context or discussion value
- Pure promotional content
- Ignoring comments
- Cross-posting from other platforms without adaptation
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 |