From community-engagement
Posts codebase-informed replies to unanswered GitHub issues and discussions. Handles single (#N), batch (unanswered P1), or interactive modes for backlog clearance.
npx claudepluginhub levnikolaevich/claude-code-skills --plugin community-engagementThis skill is limited to using the following tools:
> **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. If `shared/` is missing, fetch files via WebFetch from `https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}`.
Analyzes GitHub repo community health from issues/discussions, unreleased changes, and cadence; delegates to triager, announcer, debater, or responder workers.
Triages issues, reviews PRs, analyzes contributor activity, generates maintenance reports, and proposes actions for open-source GitHub repositories.
Fetches unresolved GitHub PR comments and threads, analyzes reviewer feedback, implements fixes, builds/tests, commits/pushes changes, replies to comments, and resolves threads.
Share bugs, ideas, or general feedback.
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. Ifshared/is missing, fetch files via WebFetch fromhttps://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}.
Type: L3 Worker (standalone) Category: 9XX Community Engagement Responds to unanswered GitHub Discussions and Issues by analyzing the question, searching the codebase for answers, and composing a helpful reply. Supports single-item and batch modes.
| Aspect | Details |
|---|---|
| Input | $ARGUMENTS: discussion/issue number (#42), batch (all unanswered P1), or empty (interactive) |
| Output | Response comment(s) published to GitHub |
| Pattern | Read question → Search codebase → Compose response → Fact-check → Publish |
MANDATORY READ: Load shared/references/community_github_discovery.md
Execute the discovery protocol. Extract:
{owner}/{repo} for URLs and API callsrepo.id for GraphQL mutationsmaintainer login (authenticated user)Load strategy: check docs/community_engagement_strategy.md in target project, fallback to shared/references/community_strategy_template.md. Extract Section 5 (Engagement Metrics) and Section 6 (Tone Guide).
MANDATORY READ: Load shared/references/community_discussion_formatting.md
MANDATORY READ: Load response_styles.md
MANDATORY READ: Load shared/references/humanizer_checklist.md
If $ARGUMENTS contains a number (e.g., 42, #42):
# For discussions
gh api graphql -f query='query($owner: String!, $name: String!) {
repository(owner: $owner, name: $name) {
discussion(number: {N}) {
id number title body
category { name }
author { login }
createdAt
answerChosenAt
comments(first: 20) {
totalCount
nodes { author { login } body createdAt }
}
}
}
}' -f owner="{owner}" -f name="{repo}"
# For issues (if discussion not found)
gh issue view {N} --repo {owner}/{repo} --json number,title,body,author,createdAt,comments,labels
If $ARGUMENTS is batch:
If $ARGUMENTS is empty, list recent unanswered items and ask the user which to respond to.
For each item:
Based on the question type, search for relevant information:
| Question Type | Search Strategy |
|---|---|
| "How do I..." | Grep for keywords in SKILL.md files, README.md, docs/ |
| Bug report | Grep for mentioned function/file, check git log for recent fixes |
| Configuration | Read .hex-skills/environment_state.json, CLAUDE.md, relevant SKILL.md |
| Feature request | Check if feature already exists, grep for related patterns |
| Installation | Read README.md installation section, plugin.json |
FOR each item:
1. Extract keywords from question (function names, skill names, error messages)
2. Grep codebase for keywords (max 5 searches)
3. Read relevant files (max 3 files, prioritize SKILL.md and docs/)
4. Check git log for recent changes related to the topic
5. If answer found → proceed to Phase 3
6. If not found → mark as "needs-manual" and suggest the user respond directly
gh api graphql -f query='query($owner: String!, $name: String!) {
repository(owner: $owner, name: $name) {
discussions(first: 100) {
nodes { author { login } }
}
}
}' -f owner="{owner}" -f name="{repo}"
Count how many discussions the author has created. If 0 previous (this is their first) → flag for Welcome style.
MANDATORY READ: Load response_styles.md — use the classification matrix.
| Item Type | Response Style |
|---|---|
| Q&A question with answer found | Technical Answer |
| Bug report | Bug Acknowledgment |
| Feature request / idea | Feature Acknowledgment |
| Question already answered elsewhere | Redirect |
| First-time poster (any type) | Welcome + appropriate content style |
| Stale item with progress update | Status Update |
| Cannot find answer in codebase | Mark needs-manual — skip composition |
Use the selected style template from response_styles.md.
In batch mode, compose all responses first, then present ALL for user review before publishing any.
Before presenting to user, verify every claim:
File paths & links — verify each linked file exists: ls {path}
Code references — verify mentioned functions/classes exist: grep -r "{name}"
Feature descriptions — re-read source file, confirm accuracy
Install/usage commands — verify against README.md
Humanizer audit -- run the audit protocol from humanizer_checklist.md. If 3+ AI patterns found, rewrite flagged sections.
Gate: If any check fails, fix the response before proceeding.
Present the composed response to the user. Wait for explicit approval before publishing.
Present ALL responses in a summary table:
### Batch Responses — {N} items
| # | Type | Title | Style | Status |
|---|------|-------|-------|--------|
| {number} | {Discussion/Issue} | {title} | {Technical/Bug/Welcome/...} | Ready |
| {number} | ... | ... | ... | needs-manual |
Then show each response body. User can approve all, approve selectively, or edit individual responses.
gh api graphql -f query='
mutation($discussionId: ID!, $body: String!) {
addDiscussionComment(input: {
discussionId: $discussionId,
body: $body
}) {
comment { url }
}
}
' -f discussionId="{discussion.id}" -f body="{response body}"
gh issue comment {number} --repo {owner}/{repo} --body "{response body}"
Report the comment URL(s) to the user.
Version: 1.0.0 Last Updated: 2026-03-14