rp1-run/pr-visual
plugins/dev/skills/pr-visual/SKILL.md
Transform pull request diffs into Mermaid diagrams for visual code review and change understanding.
$ install --global
skillsauthnpx skillsauth add rp1-run/rp1 pr-visualInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 8:51 PM1.8s1 file scanned
SKILL.md
- name:
- pr-visual
- description:
- Optional focus filter
- allowed-tools:
- Bash(echo *), Bash(rp1 *)
- category:
- review
- is_workflow:
- true
- run_policy:
- fresh
- identity_args:
- []
- version:
- 3.2.0
- created:
- 2025-10-25
- updated:
- 2026-04-12
- author:
- cloud-on-prem/rp1
- - name:
- FOCUS_AREAS
- type:
- string
- required:
- false
- default:
- all
- - "rp1-dev:
- pr-visualizer
Visual PR Analyzer
§ROLE: Standalone PR visualization orchestrator. Dispatches pr-visualizer, registers artifact.
STATE-MACHINE
stateDiagram-v2
[*] --> visualize
visualize --> [*] : done
On each phase transition, report via:
rp1 agent-tools emit \
--workflow pr-visual \
--type status_change \
--run-id {RUN_ID} \
--name "PR Visual: {PR_BRANCH}" \
--step {STATE} \
--data '{"status": "{running|completed}", "branch": "{PR_BRANCH}"}'
RUN_IDcomes from the generated Workflow Bootstrap section- Use the pre-resolved
projectRoot,kbRoot, andworkRootvalues from the generated Workflow Bootstrap section
§1 Visualize
Emit visualize running. Spawn the pr-visualizer agent:
{% dispatch_agent "rp1-dev:pr-visualizer" %} PR_BRANCH={PR_BRANCH}, BASE_BRANCH={BASE_BRANCH}, REVIEW_DEPTH={REVIEW_DEPTH}, FOCUS_AREAS={FOCUS_AREAS}, STANDALONE=true, KB_ROOT={kbRoot}, WORK_ROOT={workRoot} {% enddispatch_agent %}
Wait for completion. Extract the artifact path from agent output.
Register the artifact:
rp1 agent-tools emit \
--workflow pr-visual \
--type artifact_registered \
--run-id {RUN_ID} \
--step visualize \
--data '{"path": "{ARTIFACT_PATH}", "type": "pr-visual", "feature": "pr-visual", "storageRoot": "project"}'
Emit visualize completed. Output the artifact path.
Anti-Loop
Single pass. Dispatch agent once, register once, stop.
Related Skills
rp1-run/note
data-ai
VerifiedTrustedCommunity
Capture session context as a structured, frontmatter-rich markdown note under .rp1/work/notes/ with auto-maintained index and log.
31SKILL.mdUpdated Jun 11, 2026
rp1-run/pr-stack
tools
VerifiedTrustedCommunity
Plan and execute splitting a large PR or branch into a reviewable stacked PR sequence.
31SKILL.mdUpdated Jun 4, 2026
rp1-run/prompt-writer
development
VerifiedTrustedCommunity
Write maximally terse agent prompts from scratch. Use when creating new agent specs, command prompts, or instruction sets. Teaches structure-first composition with compression-by-default patterns. Extended with constitutional governance, epistemic stance selection, and a six-stage prompt pipeline.
31SKILL.mdUpdated Apr 21, 2026
rp1-run/speedrun
development
VerifiedTrustedCommunity
Interactive speedrun loop for small, low-risk changes. Delegates each request to a general sub-agent. Redirects larger work to /build-fast or /build.
31SKILL.mdUpdated Apr 16, 2026