performance-reporter

Generate SEO/GEO dashboards: rankings, traffic, backlinks, AI visibility for stakeholders. SEO报告/绩效仪表盘

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/performance-reporter/SKILL.md

Quality

Content

71%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 content is well-organized with a clear 11-step workflow, validation checkpoints, a concrete example, and excellent progressive disclosure via three clearly-signaled reference files. It could tighten a few redundant intro/banner sections for token efficiency.

Suggestions

Consolidate the duplicated 'When This Must Trigger' phrasing (two opening sentences say nearly the same thing) to save tokens.

Tie validation checkpoints inline to the relevant steps (e.g. validate parameters after step 1) rather than only as a separate checklist section.

Trim the banner metadata block at the top of the body, which duplicates frontmatter-style info already in the YAML.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured, but sections like the extended frontmatter-style banner, repeated 'When This Must Trigger' phrasing, and the manual-data bullet list include some redundancy and explanation that could be tightened.	3 / 5
Actionability	Provides an 11-step numbered workflow with specific report sections, concrete output template references, and a full example with a real metrics table; minor gaps are that example prompts use placeholders ([domain], [time period]) and there is no executable command, which is acceptable for an instruction-only skill.	4 / 5
Workflow Clarity	The Instructions section is a clear numbered sequence of 11 report sections, and explicit Input/Output Validation Checkpoints are present with a feedback loop (note automated vs. user-provided data); minor gaps are that checkpoints are checklists rather than inline validate-then-proceed gates tied to each step.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview pointing to three real one-level-deep reference files (report-output-templates.md, kpi-definitions.md, report-templates.md), each clearly signaled with a labeled link and one-line purpose, and the bundle structure confirms the referenced paths exist.	5 / 5
	Total	16 / 20 Passed

Description

66%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 names a clear niche with concrete metric areas and natural trigger terms, but lacks an explicit 'Use when...' clause, capping completeness at 3. It is concise and third-person but could list the concrete actions (aggregate, summarize, visualize) more explicitly.

Suggestions

Add an explicit 'Use when...' clause naming trigger scenarios, e.g. 'Use when generating SEO performance reports, traffic summaries, ranking reports, or stakeholder-facing dashboards.'

Lead with concrete verbs for each capability (e.g. 'Aggregate, analyze, and visualize SEO/GEO metrics') rather than only listing the metric nouns.

Include a few common natural synonyms in the description itself ('monthly report', 'stakeholder report') instead of burying them in the frontmatter triggers.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas ('rankings, traffic, backlinks, AI visibility') plus the output form ('dashboards'), but each action is a domain noun rather than an explicit verb and coverage of the full reporting workflow is incomplete.	4 / 5
Completeness	Has a clear 'what' (SEO/GEO dashboards with listed metrics) but no explicit 'Use when...' trigger clause in the description; the 'when' is only weakly implied by the domain terms, so per the rubric a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes strong natural terms users say ('SEO', 'rankings', 'traffic', 'backlinks', 'dashboards', '绩效仪表盘') but omits common synonyms like 'monthly report', 'stakeholder report', and 'performance report' that appear only in the body, so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	The SEO/GEO reporting niche with specific metric areas (backlinks, AI visibility, GEO) is fairly distinct and unlikely to trigger for unrelated skills, with only minor overlap risk against generic analytics skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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

	Total	14 / 16 Passed

Repository: MODSetter/SurfSense
Path: .cursor/skills/performance-reporter/SKILL.md
Commit: d96e29d

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.