Agent skill

int-github-review

Review GitHub repos — open PRs, community issues, stars/forks, releases, contributors. Use when user says 'check github', 'github review', 'repo status', 'open PRs', 'github issues', 'repository status', or any reference to checking GitHub repos status.

Stars 211
Forks 54

Install this agent skill to your Project

npx add-skill https://github.com/EvolutionAPI/evo-nexus/tree/main/.claude/skills/int-github-review

SKILL.md

GitHub Review — Repository Status

Skill to review the organization's GitHub repositories: open PRs, community issues, activity, stars, and releases.

Always respond in English.

Monitored repositories

Repo Descrição
YOUR_ORG/main-api Main API (open source)
YOUR_ORG/crm-product CRM + AI agents
YOUR_ORG/go-service Go microservice
YOUR_ORG/crm-community CRM Community edition
YOUR_ORG/methodology Development methodology

Workflow

Step 1 — Collect data from each repo

For each repository, use gh CLI to fetch:

bash
# Open PRs
gh pr list --repo YOUR_ORG/{repo} --state open --json number,title,author,createdAt,updatedAt,labels,reviewDecision --limit 20

# Open issues (last 20)
gh issue list --repo YOUR_ORG/{repo} --state open --json number,title,author,createdAt,updatedAt,labels,comments --limit 20

# Repo statistics
gh api repos/YOUR_ORG/{repo} --jq '{stargazers_count, forks_count, open_issues_count, updated_at}'

# Latest release
gh release list --repo YOUR_ORG/{repo} --limit 1 --json tagName,publishedAt,name

# Recent activity (commits in last 7 days)
gh api "repos/YOUR_ORG/{repo}/commits?since=$(date -v-7d +%Y-%m-%dT00:00:00Z)&per_page=5" --jq 'length'

Step 2 — Analyze

For each repo, classify:

  1. Open PRs: how many, how long open, who needs to review, pending reviews
  2. Community issues: reported bugs, feature requests, questions
  3. Stale issues: open for more than 14 days without response
  4. Activity: weekly commits, whether active or stagnant
  5. Growth: stars/forks (compare with previous data if available)

Step 3 — Report

Present in the format:

## GitHub Review — {data}

### Summary
| Repo | PRs | Issues | Stars | Commits (7d) | Status |
|------|-----|--------|-------|---------------|--------|

### PRs that need attention
| Repo | PR | Title | Author | Days open | Review |
|------|----|----|-------|-------------|--------|

### Community issues (unanswered)
| Repo | Issue | Title | Days without response |
|------|-------|--------|-------------------|

### Most voted / commented issues
| Repo | Issue | Title | Comments | Labels |
|------|-------|--------|------------|--------|

### Recent releases
| Repo | Version | Date |
|------|--------|------|

### Activity (last 7 days)
{activity summary per repo — active/moderate/stagnant}

Step 4 — Generate HTML report

Read the template at .claude/templates/html/custom/github-review.html.

Replace the {{...}} placeholders with the actual collected data.

Time classifications:

  • PRs/Issues < 2 days: fresh (green)
  • 2-5 days: aging (yellow)
  • 5 days: stale (red)

Activity classifications:

  • 10 commits/week: active (green)

  • 1-10 commits: moderate (yellow)
  • 0 commits: inactive (red)

Save the filled HTML to:

workspace/projects/github-reviews/[C] YYYY-MM-DD-github-review.html

Create directory if it does not exist.

Rules

  • Use gh CLI — already authenticated on the system
  • Do not create issues or PRs — only read and report
  • PRs without review > 2 days = alert — highlight
  • Issues without response > 7 days = alert — highlight
  • Compare with previous review if it exists in the directory
  • Focus on action — what needs the responsible person's attention, not just numbers

Notify via Telegram

Upon completion, send a short summary via Telegram to the user:

  • Use the Telegram MCP: reply(chat_id="YOUR_CHAT_ID", text="...")
  • Format: emoji + routine name + main result (1-3 lines)
  • If the routine had no updates, send anyway with "no updates"

Expand your agent's capabilities with these related and highly-rated skills.

EvolutionAPI/evo-nexus

data-create-viz

Cria visualizações de dados de qualidade profissional com Python no tema Evolution (fundo escuro, acento

211 54
Explore
EvolutionAPI/evo-nexus

cs-customer-escalation

Empacota uma escalação para Devs, Produto ou Davidson com contexto completo. Use quando um bug precisa de atenção além do suporte normal, vários clientes reportam o mesmo problema, um cliente está ameaçando cancelar, ou um problema ficou sem resolução além do SLA. / Package an escalation for engineering, product, or leadership with full context. Use when a bug needs engineering attention beyond normal support, multiple customers report the same issue, a customer is threatening to churn, or an issue has sat unresolved past its SLA.

211 54
Explore
EvolutionAPI/evo-nexus

mkt-draft-content

Draft blog posts, social media, email newsletters, landing pages, press releases, and case studies with channel-specific formatting and SEO recommendations. Use when writing any marketing content, when you need headline or subject line options, or when adapting a message for a specific platform, audience, and brand voice.

211 54
Explore
EvolutionAPI/evo-nexus

gog-tasks

Create, manage, and prioritize tasks and todo items. Convert emails to tasks, set priorities (P0-P3) and categories (Work/Personal/Errands/Admin), review daily priorities, track blocked and overdue tasks. Use when user mentions tasks, todos, action items, or wants to convert emails to tasks. Requires confirmation before creating or deleting tasks.

211 54
Explore
EvolutionAPI/evo-nexus

discord-get-messages

Retrieve messages from Discord channels via the Discord API. Use this skill when the user wants to read, search, or analyze messages from a Discord channel.

211 54
Explore
EvolutionAPI/evo-nexus

cs-customer-research

Pesquisa multi-fonte sobre pergunta ou tópico de cliente com atribuição de fontes. Use quando um cliente pergunta algo que precisa ser verificado, investigando se um bug foi reportado antes, verificando o que foi dito anteriormente a uma conta específica, ou coletando contexto antes de redigir uma resposta. / Multi-source research on a customer question or topic with source attribution. Use when a customer asks something you need to look up, investigating whether a bug has been reported before, checking what was previously told to a specific account, or gathering background before drafting a response.

211 54
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results