advocacy-program-designer

Use when the user asks to "design an employee advocacy program", "set up founder-led sharing", or "build a share kit for the team"; produces an advocacy program blueprint in two modes — participation-driven opt-in (default) or top-down assigned with its coercion and authenticity risks flagged — with a voluntary opt-in roster spec submitted as channel-registry proposal events, share kits with mandatory per-person variation, staggered human posting windows plus anti-pod guardrails (no coordinated identical reshares, no engagement rings), per-person material-connection disclosure lines per FTC and 《互联网广告管理办法》, and a Slack/Teams distribution spec. Not for paid creator campaigns — use campaign-planner. 员工倡导/创始人IP分享/内部分享计划/披露合规

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, compliance-aware instruction skill with a clear sequenced workflow, explicit done-criteria, and good cross-skill navigation. Its main weakness is conciseness: the registry-events routing boilerplate and paid-creator handoff are restated across multiple sections rather than stated once and referenced.

Suggestions

State the 'authorized operation: propose request to registry-events.py' routing once in the Skill Contract and reference it from steps 3, 4, 5, and Save Results instead of repeating the full clause each time.

Consolidate the paid-creator conversion path (creator-registry + contract-helper) into a single mention — e.g. the Reference Materials entry — and link to it from the Scope guard and step 8 rather than re-explaining.

Move the dense per-platform access-class table (X / IG / TikTok / LinkedIn / 小红书 / 微信公众号 / 视频号 / 抖音) into a referenced doc and keep only the open-vs-closed-platform rule inline, trimming the Data Sources and step 2 sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of generic padding (no explaining what Slack or the FTC is), but the phrase 'via an authorized operation: propose request to registry-events.py' is repeated verbatim ~5 times and the paid-creator conversion path is restated in the Scope guard, step 8, Reference Materials, and Next Best Skill — these could be tightened or factored out.	3 / 5
Actionability	As an instruction-only design skill it gives concrete guidance: exact file paths (memory/social/advocacy-program-designer/), the four required roster fields ('advocate_ref', disclosure line, opt-in date, voluntary-basis evidence), and per-kit version/hash freezing — minor gaps only (no fully copy-paste-ready artifact templates).	4 / 5
Workflow Clarity	Eight clearly sequenced numbered steps plus an explicit 'Done when' checklist and gating checks ('no kit ships without its disclosure line filled in', 'block expired/revoked/disputed/unknown rights'); the validate-against-social-quality-auditor handoff is present, though the destructive/batch propose-write path lacks a stated fix-and-retry loop.	4 / 5
Progressive Disclosure	Well-organized into Quick Start, Skill Contract, Data Sources, Instructions, Reference Materials, and Next Best Skill, with a dedicated Reference Materials list of one-level-deep cross-links each given a one-line description; the body is dense for an overview and some of the repeated registry-routing detail could live in a referenced doc.	4 / 5
	Total	15 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: concrete deliverables, natural third-person trigger phrases, explicit what-and-when, and a clear out-of-scope handoff. It is dense but every clause earns its place and no over-claims or fluff are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables — 'advocacy program blueprint in two modes', 'voluntary opt-in roster spec', 'share kits with mandatory per-person variation', 'staggered human posting windows plus anti-pod guardrails', 'per-person material-connection disclosure lines', and 'a Slack/Teams distribution spec' — comprehensive coverage with no abstract filler.	5 / 5
Completeness	Explicitly answers both: what it produces ('produces an advocacy program blueprint in two modes...') and when to use it ('Use when the user asks to...'), matching the score-5 anchor that requires concrete trigger phrases for both.	5 / 5
Trigger Term Quality	Opens with natural quoted user phrases — 'design an employee advocacy program', 'set up founder-led sharing', 'build a share kit for the team' — exactly what a user would say, plus the negative trigger 'Not for paid creator campaigns' to disambiguate.	5 / 5
Distinctiveness Conflict Risk	A clear niche (employee/founder advocacy) with an explicit boundary — 'Not for paid creator campaigns — use campaign-planner' — minimizing overlap with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 30 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: social/craft/advocacy-program-designer/SKILL.md
Commit: 64562bc

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.