CtrlK
BlogDocsLog inGet started
Tessl Logo

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

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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

The body is highly actionable with a clear gated workflow, but loses conciseness to repeated registry-proposal boilerplate and lacks a local progressive-disclosure structure since no bundle files accompany the skill.

Suggestions

Hoist the recurring 'via an authorized operation: propose request to registry-events.py' phrasing into a single stated convention and refer back to it, rather than repeating the full clause at each step.

Move the ECHO C2/H1 framing into a short reference file under references/ and link once, instead of restating the veto context in both the intro and the instructions.

Add a local references/ or assets/ bundle for the share-kit skeleton and disclosure-line templates so progressive disclosure can score on real one-level-deep files rather than inline prose.

DimensionReasoningScore

Conciseness

Guidance avoids explaining concepts Claude already knows, but is padded with repeated boilerplate — 'via an authorized operation: propose request to registry-events.py' recurs 5+ times and ECHO jargon is restated — that could be tightened.

2 / 3

Actionability

Eight numbered steps each carry concrete deliverables — '3+ distinct angles', a 'fill-in-your-own-words skeleton', an 'explicit no-verbatim rule', 'per-advocate UTM links, labeled Estimated' — giving copy-paste-ready instruction without abstract hand-waving.

3 / 3

Workflow Clarity

A clear 8-step sequence is backed by explicit done-when criteria ('Done when: every roster row has all four fields…') and gating checkpoints routing to social-quality-auditor before anything ships and to creator-registry before paid work.

3 / 3

Progressive Disclosure

Sections are clearly labeled with a dedicated Reference Materials list, but no local bundle files exist (references/scripts/assets all missing), references point outside the bundle, and repeated inline cross-links inflate the body rather than being factored out.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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

The description is specific, trigger-rich, complete, and well-disambiguated, nailing all four dimensions with explicit natural-language triggers and clear out-of-scope routing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'produces an advocacy program blueprint', 'voluntary opt-in roster spec', 'share kits with mandatory per-person variation', 'staggered human posting windows plus anti-pod guardrails', and 'per-person material-connection disclosure lines per FTC'.

3 / 3

Completeness

Explicitly answers both what ('produces an advocacy program blueprint in two modes') and when ('Use when the user asks to…'), with explicit out-of-scope routing ('Not for paid creator campaigns — use campaign-planner').

3 / 3

Trigger Term Quality

Quotes natural user utterances — 'design an employee advocacy program', 'set up founder-led sharing', 'build a share kit for the team' — that a user would plausibly say, with the surrounding jargon not severe enough to drop below 3.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche and explicitly disambiguates from siblings — 'Not for paid creator campaigns — use campaign-planner' and 'Not 1:1 recruitment mechanics (outreach-manager)' — making wrong-skill triggering unlikely.

3 / 3

Total

12

/

12

Passed

Validation

75%

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

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.