seo-backlink-audit
Audit a backlink profile using Ahrefs MCP data: profile health, anchor text distribution, toxic link identification, lost link reclamation, and gap analysis against competitors. Use this skill when reviewing backlink health, scoping a disavow project, recovering from a manual action, planning link building, or doing M&A due diligence on a property's link equity. Triggers on backlink audit, link profile, toxic links, disavow, anchor text analysis, lost links, link reclamation, referring domains, link gap. Also triggers when traffic decline correlates with link loss or when an unnatural link warning appears in Search Console.
63
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/seo-backlink-audit/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines concrete capabilities (profile health, anchor text distribution, toxic link identification, lost link reclamation, gap analysis), specifies the data source (Ahrefs MCP), and provides comprehensive trigger guidance covering both explicit keyword triggers and situational triggers. The description is well-structured, uses third person voice, and occupies a clear niche that would be easily distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: profile health assessment, anchor text distribution analysis, toxic link identification, lost link reclamation, and gap analysis against competitors. Also specifies the data source (Ahrefs MCP data). | 3 / 3 |
Completeness | Clearly answers both 'what' (audit backlink profile with specific sub-tasks) and 'when' (explicit 'Use this skill when...' clause with multiple scenarios, plus a dedicated 'Triggers on' list and additional situational triggers). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'backlink audit', 'link profile', 'toxic links', 'disavow', 'anchor text analysis', 'lost links', 'link reclamation', 'referring domains', 'link gap', plus situational triggers like 'traffic decline correlates with link loss' and 'unnatural link warning'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on backlink profile auditing via Ahrefs MCP data. The specific SEO link-analysis terminology and tool reference make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-organized conceptual framework for backlink auditing that covers the domain thoroughly with useful failure patterns and a clear output format. Its main weaknesses are the lack of concrete, executable MCP tool calls (making it more of a guide than an actionable skill), some verbosity in explaining concepts Claude would already understand, and missing validation checkpoints in the workflow. It reads more like a consultant's playbook than a technical skill file.
Suggestions
Add concrete Ahrefs MCP tool call examples (function names, parameters, expected response shapes) for each data pull step — e.g., show the actual MCP call to retrieve referring domains with specific parameters.
Add explicit validation checkpoints in the workflow — e.g., after step 2, verify data completeness by checking referring domain count against Search Console; after step 5, review toxic list against the criteria before proceeding to disavow.
Trim explanatory prose that Claude already knows (e.g., 'Volume of links matters less than quality', 'Not all links are equal') and replace with terse decision criteria or thresholds.
Move the detailed 5-dimension breakdown into a reference file and keep only a summary table in the main SKILL.md to improve progressive disclosure and reduce token cost.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity. Phrases like 'Volume of links matters less than the quality and relevance of the linking domains' and 'Not all links are equal' explain things Claude already knows. The 'Healthy signal' descriptions are useful but could be more terse. The 'When to use' and 'When NOT to use' sections overlap with frontmatter description. | 2 / 3 |
Actionability | The skill describes what to pull from Ahrefs and what to look for, but never provides concrete MCP tool calls, specific API endpoints, or executable commands. It's a conceptual framework rather than copy-paste-ready instructions. For example, 'Pull from Ahrefs: Total referring domains' doesn't tell Claude which MCP function to call or what parameters to use. | 2 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced and logically ordered, and the failure patterns section adds valuable guardrails. However, there are no explicit validation checkpoints or feedback loops — for instance, no step to verify data completeness before analysis, no checkpoint to confirm toxic link classification before building a disavow file, and no error recovery guidance if Ahrefs data is incomplete. | 2 / 3 |
Progressive Disclosure | The skill references one external file (references/toxic-link-criteria.md) which is well-signaled, and cross-references other skills (seo-offpage, seo-audit-orchestration). However, no bundle files were provided, so the reference is unverifiable. The main content is quite long (~200 lines) and some sections like the detailed dimension breakdowns could potentially be split into reference files to keep the SKILL.md leaner. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rampstackco/claude-skills
- Commit
8e70d03
- 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.