What does this skill do, and when should you use it?
Platform Norm Profiler is the Explore-phase social skill in Aaron Marketing Skills. It maintains per-platform organic-engagement norm cards covering character limits, visible-fold cutoffs, hashtags, format and aspect specifications, link placement, disclosure mechanics, and algorithm emphases. Each row distinguishes platform-documented evidence from named folklore and carries verification and review dates. It is a fit for teams that need current platform constraints before drafting or scheduling, but it does not choose channels, write posts, or automate publishing.
Reads existing cards in references/platforms/, relevant channel dossiers, official platform documentation, and user-provided exports or screenshots; adds or refreshes each card’s organic-engagement section; records character limits, fold cutoffs, hashtag norms, format and aspect specifications, link or first-comment placement, disclosure-label mechanics, and algorithm emphases; prioritizes official documentation; labels unsupported claims as Estimated-folklore with a named source; adds last-verified and review-by dates; runs stale-card checks; and produces changed-row summaries, staleness reports, and rule-snapshot pointer candidates. The source also identifies Firecrawl and Tavily connector scripts as retrieval paths and registry-events.py as the proposal path for channel pointers.
- A social team is preparing Xiaohongshu content and needs to verify character limits, fold cutoffs, hashtag conventions, and claims about search or saves.
- A brand is scheduling LinkedIn posts and wants to determine whether link-in-first-comment guidance is documented or folklore.
- A marketing team needs a staleness sweep across platform cards before building its next content calendar.
- A multi-channel team wants current platform cards to serve as references for downstream platform-native content creation.
How do you install this skill?
- Only the specified SKILL.md was scored; README, license, security policy, CI, and tests were treated as shared repository context and did not substitute for skill-specific evidence.
- The workflow depends on external platform documentation, Firecrawl/Tavily, or user exports; inaccessible evidence should produce NEEDS_INPUT or an unverified state, not a platform fact based on folklore.
- The skill edits shared cards and submits registry proposals; users should confirm the target platforms, write scope, authorization boundary, and recovery plan before use.
- Shell / CLI
- Network access
- Local filesystem
Python standard-library connector scripts
Install the repository for a compatible host with npx skills add aaron-he-zhu/aaron-marketing-skills, or clone it with git clone https://github.com/aaron-he-zhu/aaron-marketing-skills. For Claude Code, the repository documents /plugin marketplace add aaron-he-zhu/aaron-marketing-skills, followed by /plugin install aaron-marketing@aaron. The source does not document a separate copy procedure for placing only this skill in another host.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/social/explore/platform-norm-profiler" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
After loading the skill in Claude Code or another Agent Skills-compatible host, use a request such as: Build the organic-engagement section of the 小红书 norm card: char limits, fold cutoffs, hashtag norms, format specs, algorithm emphases — label and date every row. Other documented prompts include Staleness sweep: flag every platform card past its review-by date before the next calendar build. and Verify the LinkedIn link-in-first-comment norm — platform-documented or folklore?
What are this skill's strengths and limitations?
- Covers practical planning constraints including character limits, fold cutoffs, format specs, link placement, and disclosure mechanics.
- Separates official or measured evidence from named folklore and dates every row.
- Flags cards past their review date instead of treating them as current.
- Maintains one shared platform-card pack rather than creating project-specific copies.
- It depends on official documentation, user exports, screenshots, or pasted policy text; without named platforms or channels it can return NEEDS_INPUT.
- Closed and Chinese platforms rely heavily on manual or user-provided evidence rather than compliant keyless automation.
- It does not select channels, draft posts, or automate posting, engagement, or DMs.
- The supplied source does not show a skill-specific test suite or independent execution report.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Platform Norm Profiler this page | 60 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
| Channel Portfolio Planner | 57 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Evergreen Social Calendar | 59 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
| Social Measurement Loop | 56 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Short Video Script Studio | 61 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill defines several protective controls: fetched material is untrusted data, Chinese-platform automation is prohibited, connectors are keyless by default, and registry pointers use an authorized operation: propose flow. However, confirmation boundaries, rollback, and end-to-end data-flow disclosure for card, memory, and proposal writes remain incomplete, so 7 points are deducted.
Triggers, NEEDS_INPUT handling, stale-card behavior, termination rules, and abnormal-input guidance are detailed and largely self-consistent. Because this is a static review with no skill-specific execution evidence or reproducible key-path tests, the score is capped below 10 and set to 9, with deductions for unverified dependencies and edge behavior.
The target scenarios, non-fit skills, argument hint, and Chinese-platform handling are explicit. Platform access differences, user-export formats, and environment-specific boundaries are not fully specified, so 3 points are deducted.
The document has strong information architecture and includes versioning, Apache-2.0 licensing, quick starts, contracts, references, completion criteria, and handoffs. Maintenance ownership, changelog/update procedure, installation dependency notes, and troubleshooting are incomplete, so 4 points are deducted.
The expected card updates, row labels, dates, stale report, pointer candidates, and handoff are clearly specified and could be directly useful. No representative completed output or static result verifies practical completeness, and usefulness depends partly on external platform evidence, so 9 points are deducted and the static ceiling applies.
The skill requires official documentation, named folklore sources, retrieval dates, and separation of measured versus estimated claims. The supplied files contain no completed source examples, independent reproduction record, or key-path test coverage for this skill, so the score is limited to 4.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →