CtrlK
BlogDocsLog inGet started
Tessl Logo

fixing-metadata

Audit and fix HTML metadata including page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD structured data, and robots directives. Use when adding or reviewing SEO and social metadata.

65

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/fixing-metadata/SKILL.md

The canonical home for this skill is fixing-metadata in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a well-structured, mostly lean instruction-only rule set with clear sections, a priority table, and a verification checkpoint in the workflow. The main improvement opportunities are reducing redundancy across the framing sections, adding specific thresholds to vague rules, and introducing an explicit validate→fix→retry feedback loop.

Suggestions

Consolidate the redundant guidance across Workflow and review guidance (e.g. 'fix critical issues first', 'keep diffs minimal', 'ensure title/description/canonical/og:url agree') into a single source to trim tokens.

Add concrete thresholds to the directional rules — e.g. recommended title length ranges, specific OG image dimensions, and an example title-format pattern — so guidance is executable rather than just directional.

Add an explicit validate→fix→retry loop to the workflow (e.g. 'After edits, re-verify social cards and agreement; if any check fails, fix and re-verify before finalizing') to strengthen error recovery for batch metadata edits.

DimensionReasoningScore

Conciseness

The core quick-reference rules are lean and assume Claude's competence (no concept explanations), but the framing sections duplicate each other — 'fix critical issues first', 'keep diffs minimal', and 'ensure title/description/canonical/og:url agree' are restated across Workflow and review guidance — which could be trimmed; this keeps it at 4 rather than 5.

4 / 5

Actionability

Most rules are concrete and actionable ('Open Graph and Twitter images must use absolute URLs', 'set twitter:card appropriately, summary_large_image by default', 'og:url must match the canonical URL'), but several are directional without specific thresholds ('use a consistent title format', 'keep titles short and readable', 'prefer correct image dimensions'), leaving minor gaps.

4 / 5

Workflow Clarity

A clear 5-step sequence with an explicit verification checkpoint ('Verify social cards render correctly on a real URL, not localhost') is present, so the destructive/batch cap does not apply; however there is no explicit validate→fix→retry feedback loop, holding it at 4 rather than 5.

4 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers and a priority table, and no external references are needed for this compact rule set; minor organization gaps (section redundancy, no overview/detail split) keep it at 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

83%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 strong: it names a clear niche, enumerates comprehensive concrete metadata targets, and includes an explicit 'Use when' trigger clause answering both what and when. Minor room for improvement lies in adding a few more natural synonyms and a slightly richer action vocabulary.

DimensionReasoningScore

Specificity

Lists concrete actions ('Audit and fix') applied to a comprehensive enumeration of specific metadata targets (page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD, robots directives), but the action verbs themselves are limited to audit/fix rather than a rich set of distinct operations as in the 5-anchor.

4 / 5

Completeness

Clearly and explicitly answers both what ('Audit and fix HTML metadata including...') and when ('Use when adding or reviewing SEO and social metadata.') with concrete trigger phrases, matching the 5-anchor; the explicit 'Use when' clause satisfies the completeness gate.

5 / 5

Trigger Term Quality

Strong natural keyword coverage ('SEO', 'social metadata', 'Open Graph', 'Twitter cards', 'canonical URLs', 'JSON-LD', 'robots directives') that users would actually say, with a few common synonyms missing (e.g. 'meta tags', 'schema markup', 'rich snippets').

4 / 5

Distinctiveness Conflict Risk

Targets a distinct metadata/SEO niche with specific triggers (OG tags, Twitter cards, JSON-LD, canonical) but carries minor overlap risk with broader SEO or web-development skills, so it sits at 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.