decocms/mcps/generate-report

Claude Code and agent skill by decocms/mcps

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Generate a structured Markdown report with YAML frontmatter for repository health monitoring. Use when the user asks to create a report, health check, audit, scan result, or status update for a repository.

Install

npx vskill@latest install decocms/mcps/generate-report

SKILL.md

Generate Report

You are writing a report as a Markdown file with YAML frontmatter. Follow these instructions exactly.

File format

Every report is a .md file. Metadata goes in YAML frontmatter delimited by ---. Any markdown content below the frontmatter becomes the report body.

markdown
---
title: "Report Title"
category: performance
status: warning
summary: "One-line summary of findings"
source: your-agent-name
tags: [extra-tag-1, extra-tag-2]
updatedAt: "2025-06-15T10:00:00Z"
sections:
-type: metrics
title: "Section Title"
items:
-label: "Metric Name"
value: 42
unit: "ms"
status: passing
---
## Markdown body
Any content below the closing `---` is rendered as a markdown section
after the structured sections declared in frontmatter.

Frontmatter fields

FieldRequiredTypeDescription
titleYesstringHuman-readable report title.
categoryYesstringCategory for filtering (e.g., performance, security, quality). See category list below.
statusYes`"passing" \"warning" \"failing" \"info"`Overall health outcome.
summaryYesstringOne-line summary of findings. Keep it concise — this is shown in list views.
updatedAtYesstringISO 8601 timestamp of when the report was generated (YYYY-MM-DDTHH:mm:ssZ).
sourceOptionalstringName of the agent or service that generated this report (e.g., lighthouse, security-scanner).
tagsOptionalstring[]Free-form tags for filtering (e.g., [homepage, mobile, ci]).
sectionsOptionalReportSection[]Structured content sections (metrics, tables, markdown). See section types below.

Always provide title, category, status, summary, and updatedAt. Do not leave them empty or omit them.

File placement and tagging

Place report files inside a reports/ directory. Subdirectories automatically become tags on the report.

reports/
daily-check.md # no directory tags
security/
audit.md # tagged: ["security"]
dependency-scan.md # tagged: ["security"]
performance/
mobile/
lighthouse.md # tagged: ["performance", "mobile"]

Directory-derived tags are merged with any tags declared in frontmatter, deduplicated.

Choose a filename that is a short, descriptive, kebab-case slug (e.g., dependency-scan.md, homepage-vitals.md).

Section types

Sections appear in the order listed in frontmatter. The markdown body (if present) is appended as a final section after all frontmatter sections. Put the most important information first.

Markdown section

Free-form text rendered as GitHub Flavored Markdown.

yaml
sections:
- type: markdown
content: |
## Analysis
The homepage load time has improved by **15%** since last week.
Metrics section

Key performance indicators with optional deltas and per-metric status.

yaml
sections:
- type: metrics
title: "Core Web Vitals"
items:
- label: LCP
value: 2.5
unit: s
previousValue: 3.1
status: passing
- label: FID
value: 300
unit: ms
previousValue: 150
status: failing

Each metric item:

FieldRequiredTypeDescription
labelYesstringMetric name (e.g., "LCP", "Coverage").
valueYes`number \string`Current value.
unitOptionalstringUnit of measurement (e.g., "s", "ms", "%", "score").
previousValueOptional`number \string`Previous value for delta comparison.
statusOptional`"passing" \"warning" \"failing" \"info"`Status of this individual metric.
Table section

Tabular data with column headers.

yaml
sections:
- type: table
title: "Dependency Vulnerabilities"
columns: [Package, Severity, Version, Fixed In]
rows:
- [lodash, High, 4.17.20, 4.17.21]
- [express, Medium, 4.17.1, 4.18.0]

Status reference

StatusWhen to use
passingEverything is within acceptable thresholds.
warningSome metrics are degraded or approaching thresholds.
failingCritical issues that need immediate attention.
infoInformational report with no pass/fail judgment.

Category conventions

CategoryUse case
performanceWeb vitals, bundle size, load times.
securityVulnerability scans, dependency audits.
accessibilityWCAG compliance, axe-core results.
seoMeta tags, structured data, crawlability.
qualityCode quality, test coverage, lint results.
uptimeHealth checks, availability monitoring.
complianceLicense audits, policy checks.

Git workflow

Reports are stored on a dedicated git branch (typically reports).

Committing a report
bash
git checkout reports
mkdir -p reports/security
# ... write the file ...
git add reports/
git commit -m "report(security): add dependency vulnerability scan"
git push origin reports
Creating the branch for the first time
bash
git checkout --orphan reports
git rm -rf .
mkdir reports
# ... create your first report file ...
git add reports/
git commit -m "report: initialize reports branch"
git push -u origin reports

Additional resources

  • For complete examples of different report types, see examples.md

Your task

Based on the user's request ($ARGUMENTS), generate a complete report file following the format above. Analyze the relevant code, data, or context in the repository before writing the report. Make sure the report contains real, accurate data — not placeholder values.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/decocms/mcps/generate-report/badge)](https://verified-skill.com/skills/decocms/mcps/generate-report)

Something wrong with this skill or its page? Tell us.