agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr
34
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
100%
51%Automate PR Handling with Swarm Agents
GitHub Actions swarm workflow
PR trigger events
100%
100%
Comment trigger event
100%
100%
Comment pattern check
13%
100%
ruv-swarm handle-comment command
0%
100%
PR number passed
30%
100%
Comment body passed
30%
100%
ubuntu-latest runner
100%
100%
Checkout step
100%
100%
No direct gh API in workflow
100%
100%
README documents $swarm commands
10%
100%
Without context: $0.2724 · 1m 22s · 16 turns · 21 in / 4,307 out tokens
With context: $0.4987 · 1m 37s · 22 turns · 26 in / 5,354 out tokens
92%
55%PR Swarm Bootstrap Script
PR swarm initialization with topology and memory
gh pr diff for diff
100%
100%
gh pr view JSON fields
50%
100%
Topology: ring for small
0%
100%
Topology: mesh for medium
0%
100%
Topology: hierarchical for large
0%
100%
ruv-swarm pr-init flags
0%
100%
swarm_init MCP tool
100%
0%
memory_usage store action
100%
100%
Memory key pattern
0%
100%
coordination_sync call
0%
100%
USAGE.md topology rules
0%
100%
No hardcoded PR number
100%
100%
Without context: $0.7236 · 3m 32s · 35 turns · 111 in / 10,630 out tokens
With context: $0.4389 · 1m 34s · 22 turns · 183 in / 4,922 out tokens
100%
74%Automated Code Review and Merge Pipeline
Swarm code review and auto-merge automation
gh pr view for files
100%
100%
ruv-swarm pr-review command
0%
100%
Review agents: security
0%
100%
Review agents: performance
0%
100%
Review agents: style
0%
100%
gh pr review for posting
0%
100%
Progress threshold at 90%
0%
100%
ready-for-review label
0%
100%
Swarm complete check
50%
100%
Minimum 2 reviews check
0%
100%
gh pr merge squash
100%
100%
Pipeline doc: merge conditions
37%
100%
Without context: $1.5765 · 5m 11s · 55 turns · 59 in / 17,720 out tokens
With context: $0.4258 · 1m 33s · 20 turns · 134 in / 5,501 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.