CtrlK
BlogDocsLog inGet started
Tessl Logo

platform-norm-profiler

Use when the user asks to "build the norm card for this platform", "what are the char limits and visible-fold cutoffs here", "is the LinkedIn link-in-first-comment thing documented or folklore", or "which of our platform cards are stale"; maintains the dated, versioned per-platform norm cards in the references/platforms/ pack — char limits, visible-fold cutoffs, hashtag norms, format/aspect specs, link and first-comment placement, disclosure-label mechanics, algorithm emphases (e.g. 小红书 search+saves weighting) — every row labeled platform-documented (official doc, Measured) or Estimated-folklore (named source) with last-verified and review-by dates, and any card past its review date flagged stale rather than trusted. Extends the single pack in place; never forks a second one. Not for picking which channels to run — use channel-portfolio-planner. 平台规范卡/字符限制/折叠线/话题标签/算法侧重/过期标记

67

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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, actionable instruction-only skill body: concrete paths, scripts, and an 8-step workflow with a staleness validation pass. Its main weakness is repetition of the same guardrails across several sections, which inflates length without adding guidance.

Suggestions

State the 'single pack, edited in place — never a second pack or memory/ shadow pack' rule once in the Scope Guard and reference it from Writes/Save Results instead of repeating it verbatim four times.

Define the registry-events.py 'operation: propose' record shape (fields for card + last-verified date) inline so the pointer submission is copy-paste ready rather than implied.

Add an explicit validate→fix→retry loop for the staleness pass (e.g. 'if a card is stale, re-pull the official doc, re-date the row, then re-run the staleness check') to lift workflow_clarity to the top anchor.

DimensionReasoningScore

Conciseness

The body is mostly efficient domain-specific guidance with no concept-explaining padding, but key refrains — 'single pack, edited in place, never forks a second one' and 'flagged, not trusted' — each recur across four to five sections and could be tightened.

3 / 5

Actionability

Gives concrete, executable guidance — specific paths (references/platforms/x.md, memory/events/channels.ndjson), scripts (firecrawl.py, tavily.py), an authorized operation: propose to registry-events.py, and a 90-day horizon — with only minor gaps such as the exact pointer record payload.

4 / 5

Workflow Clarity

Eight clearly sequenced steps with a staleness validation pass and a 'Done when' checklist; validation is present so the batch/destructive cap does not bind, but there is no explicit validate-fix-retry feedback loop for error recovery.

4 / 5

Progressive Disclosure

Well-signaled one-level references (echo-benchmark, the platforms pack, skill-contract, CONNECTORS, SECURITY) organized into a Reference Materials section; the body is somewhat dense in places rather than a lean overview pointing to detail, keeping it just below the top anchor.

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: it pairs a concrete, comprehensive action list with natural quoted trigger phrases, states both what and when, and explicitly fences off adjacent skills to avoid mis-triggering. The only cost is some verbosity from the trailing CJK keyword echo, which no rubric dimension penalizes.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with comprehensive coverage — 'char limits, visible-fold cutoffs, hashtag norms, format/aspect specs, link and first-comment placement, disclosure-label mechanics, algorithm emphases' — matching the anchor for several specific concrete actions.

5 / 5

Completeness

Explicitly answers both what ('maintains the dated, versioned per-platform norm cards…') and when (a leading 'Use when the user asks to…' clause with concrete triggers), satisfying the top anchor.

5 / 5

Trigger Term Quality

Includes natural quoted trigger phrases a user would actually say — 'build the norm card for this platform', 'what are the char limits and visible-fold cutoffs here', 'is the LinkedIn link-in-first-comment thing documented or folklore', 'which of our platform cards are stale'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (per-platform norm cards) and draws an explicit boundary — 'Not for picking which channels to run — use channel-portfolio-planner' — minimizing conflict risk.

5 / 5

Total

20

/

20

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: 22 suspicious

Warning

referenced_paths_exist

Referenced path issues: 10 missing, 4 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.