AGENT SKILL

ln-910-community-engagement

Community engagement coordinator: analyzes repo health, consults strategy, delegates to announcer/debater/triager

License 许可
MIT
最近更新
2026-05-02
Stars
★ 3
Forks
1

01 前言 Front Matter

name
ln-910-community-engagement
license
MIT
description
Community engagement coordinator: analyzes repo health, consults strategy, delegates to announcer/debater/triager
allowed-tools
Read, Grep, Glob, Bash, Skill

02 资源文件 3

03 SKILL.md 正文

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.

ln-910-community-engagement

Type: L2 Coordinator (active) Category: 9XX Community Engagement

Analyzes current community health and repository state, consults the engagement strategy, and delegates to the appropriate worker. Each worker is also invocable standalone.


Overview

Aspect Details
Input $ARGUMENTS (optional): topic, action keyword, or empty for auto-analysis
Output Situation report + delegated action via worker skill
Workers ln-911 (triager), ln-912 (announcer), ln-913 (debater)

Phase 0: GitHub Discovery

MANDATORY READ: Load references/github_discovery.md

Execute the discovery protocol. Extract:

  • {owner}/{repo} for all GitHub operations
  • repo.id for GraphQL mutations (passed to workers)
  • maintainer login (authenticated user)
  • Discussion category IDs

Gate checks: gh authenticated? Discussions enabled?

Load strategy: check docs/community_engagement_strategy.md in target project, fallback to references/community_strategy_template.md.


Phase 1: Situation Analysis

If $ARGUMENTS contains a direct action keyword (announce, debate, triage), skip analysis and jump to Phase 3 (Direct Delegation).

Otherwise, gather context from multiple sources in parallel:

1a. Community Health

Delegate to triager in summary mode (no interactive preview):

Skill(skill: "ln-911-github-triager", args: "summary")

Extract from triager output: red flags, priority counts (P0/P1/P2), health metrics.

1b. Unreleased Changes

# Last announcement date: most recent Announcements discussion
gh api graphql -f query='query($owner: String!, $name: String!) {
  repository(owner: $owner, name: $name) {
    discussions(first: 1, categoryId: "{categories.Announcements}", orderBy: {field: CREATED_AT, direction: DESC}) {
      nodes { createdAt title }
    }
  }
}' -f owner="{owner}" -f name="{repo}"

Then check what changed since:

git log --oneline --since="{last_announcement_date}"

Read CHANGELOG.md — any entries newer than the last announcement?

1c. Cadence Check

From strategy Section 4:

  • Days since last announcement → monthly digest overdue if >30 days?
  • Any pending architectural decisions that need RFC?

Phase 2: Decision Matrix

Apply strategy Section 1 (Announcement vs Debate) to the gathered context:

Condition Priority Action Worker
Red flags: unanswered discussions >7d P0 List items needing response (no worker — direct action) Recommendations only
Red flags: PRs needing review P0 List PRs needing review Recommendations only
Unreleased changes in CHANGELOG P1 Announce: new features/fixes → ln-912
$ARGUMENTS contains RFC/debate topic P1 Debate: launch RFC → ln-913
Monthly digest overdue (>30d) P2 Monthly digest announcement → ln-912
Design questions identified in Phase 1 P2 Debate: RFC for open decisions → ln-913
Community health OK, nothing unreleased — Report "all clear" No delegation

Output: Situation Report

Present to user:

## Community Status — {YYYY-MM-DD}

**Repo:** {owner}/{repo}
**Last announcement:** {date} ({days} days ago)
**Open items:** {issues} issues, {prs} PRs, {discussions} discussions

### Red Flags
{list or "None"}

### Recommended Action
{One of: Announce / Debate / Respond to items / No action needed}

**Reason:** {brief explanation based on strategy criteria}

Wait for user approval before proceeding.


Phase 3: Delegate

After user approves the recommended action:

Direct Delegation (when $ARGUMENTS specifies action)

Argument Delegation
announce or announce {topic} Skill(skill: "ln-912-community-announcer", args: "{topic}")
debate or debate {topic} Skill(skill: "ln-913-community-debater", args: "{topic}")
triage or triage {scope} Skill(skill: "ln-911-github-triager", args: "{scope}")

Analysis-Based Delegation

Recommended action Delegation
Announce Skill(skill: "ln-912-community-announcer") — worker gathers its own context
Debate Skill(skill: "ln-913-community-debater", args: "{identified topic}")
Respond to items No delegation — present the list of items needing response with GitHub URLs
No action needed Report status, done

Shared References

File Purpose
references/github_discovery.md Phase 0: dynamic repo/category/user discovery
references/community_strategy_template.md Default engagement strategy (fallback)
references/discussion_formatting.md GitHub Discussion formatting rules

Strategy Override

Each target project can override the default strategy by creating docs/community_engagement_strategy.md. All skills check project-local first, then fall back to the template in references/.


Definition of Done

  • [ ] GitHub discovery complete (owner/repo, categories, maintainer extracted)
  • [ ] Situation analyzed (health + unreleased changes + cadence) OR direct delegation triggered
  • [ ] Decision matrix applied with priority-based action selection
  • [ ] Worker delegated or recommendations shown to user
  • [ ] User informed of outcome

Phase 4: Meta-Analysis

MANDATORY READ: Load shared/references/meta_analysis_protocol.md

Skill type: planning-coordinator. Run after Phase 3 completes. Output to chat using the planning-coordinator format.


Version: 1.0.0 Last Updated: 2026-03-13

04 同仓库更多 Skills

levalencia
levalencia/agent-god-mode

zarr-python

Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

★ 3
levalencia
levalencia/agent-god-mode

zabbix

Zabbix monitoring system automation via API and Python. Use when: (1) Managing hosts, templates, items, triggers, or host groups, (2) Automating monitoring configuration, (3) Sending data via Zabbix trapper/sender, (4) Querying historical data or events, (5) Bulk operations on Zabbix objects, (6) Maintenance window management, (7) User/permission management

开发工程师后端与接口Skill与智能体开发
★ 3
levalencia
levalencia/agent-god-mode

x-twitter-growth

X/Twitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X/Twitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.

★ 3
levalencia
levalencia/agent-god-mode

what-if-oracle

Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like "what if...", "what would happen if...", "what are the possibilities", "explore scenarios", "scenario analysis", "possibility space", "what could go wrong", "best case / worst case", "risk analysis", "contingency planning", "strategic options", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.

★ 3
levalencia
levalencia/agent-god-mode

vercel-react-best-practices

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

前端开发
★ 3
levalencia
levalencia/agent-god-mode

venue-templates

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.

内容创作者写作与文案资料检索与研究
★ 3