trigger-ai-reviews
Use when asked to "trigger AI reviews", "request AI re-reviews", "get Claude/Gemini/Copilot to review my PR", "re-review this PR", or trigger review-request comments on a PR. Triggers all three AI reviewers by default, or specific ones when named.
What this skill does
# Trigger AI Reviews
Trigger Claude, Gemini, and/or Copilot reviews on a PR with a single invocation.
## Usage
```text
/trigger-ai-reviews # Trigger all 3 AIs on current branch's PR
/trigger-ai-reviews 42 # Trigger all 3 AIs on PR #42
/trigger-ai-reviews 42 claude # Trigger only Claude
/trigger-ai-reviews 42 gemini # Trigger only Gemini
/trigger-ai-reviews 42 copilot # Trigger only Copilot
/trigger-ai-reviews 42 all # Explicitly trigger all 3 AIs
```
## Step 1: Resolve PR Context
```bash
OWNER=$(gh repo view --json owner --jq '.owner.login')
REPO=$(gh repo view --json name --jq '.name')
# If PR_NUMBER not provided, get from current branch
PR_NUMBER=${PR_NUMBER:-$(gh pr view --json number --jq '.number' 2>/dev/null)}
```
Verify the PR exists and is open:
```bash
STATE=$(gh pr view "$PR_NUMBER" --json state --jq '.state')
[ "$STATE" = "OPEN" ] || { echo "PR #$PR_NUMBER is $STATE — only open PRs can be reviewed"; exit 1; }
```
## Step 2: Trigger Claude
Post a comment mentioning `@claude`:
```bash
gh pr comment "$PR_NUMBER" --body "@claude review this PR"
```
Expected: Claude Code bot picks up the mention and posts a review.
## Step 3: Trigger Gemini
Post the Gemini slash command:
```bash
gh pr comment "$PR_NUMBER" --body "/gemini review"
```
Expected: Gemini Code Assist bot responds with a review.
## Step 4: Trigger Copilot
Request Copilot as a reviewer via the GitHub API:
```bash
gh api \
--method POST \
"/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}/requested_reviewers" \
-f "reviewers[]=copilot-pull-request-reviewer[bot]"
```
**Important limitation**: Copilot can only be requested once per PR. If Copilot has already submitted
a review, this API call will return an error — that is expected behavior.
See [references/ai-triggers.md](references/ai-triggers.md) for details.
## Step 5: Report Results
After all steps, report clearly:
```text
AI Review Triggers — PR #{NUMBER}
✅ Claude — comment posted (@claude review this PR)
✅ Gemini — comment posted (/gemini review)
✅ Copilot — reviewer requested via API
OR
⚠️ Copilot — request failed (already reviewed or not installed)
```
## Error Handling
| Error | Cause | Resolution |
|-------|-------|------------|
| `gh: not found` | `gh` CLI missing | Install: `brew install gh` |
| `no PR found for current branch` | Branch has no open PR | Create PR first or provide PR number |
| PR is CLOSED/MERGED | Targeting wrong PR | Verify PR number |
| Copilot API 422 | Already reviewed or not installed | Expected — report as warning, not failure |
| Claude/Gemini comment fails | Auth or rate limit | Retry manually or check `gh auth status` |
## Selective Triggering
When a specific AI is named in the argument (e.g., `/trigger-ai-reviews 42 claude`), skip the other steps. Only run the steps for the requested AI(s).
## Related Skills
- finalize-pr (github-workflows) — full PR finalization pipeline; trigger AI reviews as part of the process
- resolve-pr-threads (github-workflows) — resolve review threads after AI reviewers post feedback
- review-standards (code-standards) — standards applied when reviewing code
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.