CtrlK
BlogDocsLog inGet started
Tessl Logo

offsite-signal-analyzer

Use when the user asks to "analyze backlinks", "analyze my off-site signals", or "track AI traffic / ChatGPT / Perplexity referrals"; profiles referring domains, anchor-text mix, toxic links, and disavow candidates (backlinks mode) or isolates AI-assistant referral sessions in GA4/GSC/logs and reports their trend, landing pages, and AI-vs-organic conversion (ai-referrals mode). Not for internal links — use site-structure-optimizer; not for keyword positions — use rank-tracker; not for multi-metric stakeholder reports — use performance-monitor. 外链分析/反向链接/AI流量/AI引荐/ChatGPT流量/AI转化

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

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 two-mode skill with strong workflow sequencing and clean progressive disclosure into verified reference files. Its main weakness is conciseness — repeated handoff phrasing and dense mapping tables add tokens that could be trimmed without losing clarity.

Suggestions

De-duplicate the domain-authority-auditor handoff and the 'engagement signal that informs (does not evidence)' caveat — state each once and reference back rather than repeating full sentences.

Condense the two CITE-item mapping tables into a single compact table or move them into a reference file, keeping only the dimension summary inline.

Trim the repeated connector-command prose (gdlet/tavily/ledger blocks share the same 'trend it like everything else' pattern) into one parameterized example.

DimensionReasoningScore

Conciseness

Mostly efficient operational prose, but it repeats the same handoff caveats multiple times (domain-authority-auditor handoff, the 'engagement signal that informs (does not evidence)' disclaimer appears twice) and the dense CITE-mapping tables could be tightened; verbosity is present even though accurate.

3 / 5

Actionability

Provides concrete executable commands (gdlet.py, ledger.py record/diff/trend, tavily.py) and a copy-paste starter regex, plus specific GA4 Exploration instructions; minor gaps remain since the regex is explicitly 'starter, adapt' and some steps describe rather than command.

4 / 5

Workflow Clarity

Both modes have clear numbered sequences (7 backlinks steps, 8 ai-referrals steps) with explicit validation checkpoints — Decision Gates ('Stop and ask'), 'Done when' checklists, source-tagging rules, and the measurement-protocol Promote/Keep-testing/Rollback/Unproven control comparison as a feedback loop.

5 / 5

Progressive Disclosure

Body is an overview that points to real one-level-deep bundle files (references/backlinks-analysis-templates.md, link-quality-rubric.md, outreach-templates.md, all confirmed present) via clearly signaled links and a dedicated Reference Materials section; navigation is easy and content is appropriately split.

5 / 5

Total

17

/

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.

The description is exemplary: third-person voice, concrete actions across two modes, natural trigger phrases with synonyms, and explicit boundary guidance against neighboring skills. It hits the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across both modes — 'profiles referring domains, anchor-text mix, toxic links, and disavow candidates' and 'isolates AI-assistant referral sessions in GA4/GSC/logs and reports their trend, landing pages, and AI-vs-organic conversion' — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (profiles/isolates and reports specific metrics) and when ('Use when the user asks to...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('analyze backlinks', 'analyze my off-site signals', 'track AI traffic / ChatGPT / Perplexity referrals') plus Chinese synonyms (外链分析/反向链接/AI流量), covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Carves a clear off-site-signal niche and explicitly excludes adjacent skills ('Not for internal links — use site-structure-optimizer; not for keyword positions — use rank-tracker; not for multi-metric stakeholder reports — use performance-monitor'), 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: 18 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing, 1 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.