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

72

Quality

92%

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

85%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 and well-sequenced with concrete commands, explicit validation checkpoints, and clean one-level-deep reference structure. The only weakness is moderate redundancy where mode selection and scope boundaries are restated across several sections.

Suggestions

Consolidate the mode-selection and scope-boundary text: the backlinks-vs-ai-referrals split and the 'not for internal links / keyword positions / stakeholder reports' exclusions currently recur in the Skill Contract, Scope Guard, and Next Best Skill sections — state each once.

Merge the Decision Gates 'Continue silently' list with the Instructions preamble, since both cover the same N/A / default-handling rules, to reduce overlap.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence (no padding about what backlinks or GA4 are), but mode-selection logic and scope boundaries are restated across the Skill Contract, Decision Gates, Scope Guard, and Next Best Skill sections, so it could be tightened; not level 3 due to that redundancy, not level 1 because there is no concept exposition.

2 / 3

Actionability

Provides copy-paste-ready commands — 'python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/gdelt.py" ... --days 30', ledger record/diff/trend invocations with JSON data, and a literal AI-source regex block — plus specific GA4 channel-group placement ('above Referral'), matching the fully-executable anchor.

3 / 3

Workflow Clarity

Both modes have explicit numbered sequences (backlinks 1–7, ai-referrals 1–8) with validation checkpoints — Decision Gates stop/continue rules, per-metric source tagging, the promote/keep-testing/rollback/unproven control read, and the toxic-ratio >15% threshold — matching the clear-sequence-with-explicit-checkpoints anchor.

3 / 3

Progressive Disclosure

The body is an overview that signals one-level-deep references to real bundle files — backlinks-analysis-templates.md, link-quality-rubric.md, outreach-templates.md (all present under references/) — with detailed templates/rubrics appropriately split out; matches the well-signaled one-level-deep anchor.

3 / 3

Total

11

/

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 third-person, concise yet comprehensive, with explicit 'Use when...' triggers, concrete per-mode actions, and clear boundaries against sibling skills. It satisfies all four dimensions at the top of the scale.

DimensionReasoningScore

Specificity

Lists multiple concrete actions per mode — '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' — matching the multiple-specific-actions anchor; not level 2 because the action coverage is comprehensive rather than partial.

3 / 3

Completeness

An explicit 'Use when the user asks to...' clause answers when, and the two-mode capability list answers what, with explicit 'Not for...' exclusions — clearly both what and when with explicit triggers, not level 2 where when is only implied.

3 / 3

Trigger Term Quality

Natural user phrasing is explicitly quoted — 'analyze backlinks', 'analyze my off-site signals', 'track AI traffic / ChatGPT / Perplexity referrals' — plus Chinese variants (外链分析, 反向链接, AI流量), giving good coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Draws explicit boundaries against three named sibling skills — 'use site-structure-optimizer', 'use rank-tracker', 'use performance-monitor' — giving a clear niche unlikely to conflict, matching the distinct-triggers anchor.

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: 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.