the-rabak/slrj
.github_gpt/skills/slrj/SKILL.md
Full autonomous engineering workflow using swarm mode for parallel execution
$ install --global
skillsauthnpx skillsauth add the-rabak/compound-engineering-plugin slrjInstall 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 17, 2026, 5:47 AM90.7s1 file scanned
SKILL.md
- name:
- slrj
- description:
- Full autonomous engineering workflow using swarm mode for parallel execution
Goal
Run the autonomous workflow with swarm execution where specified and mandatory parallel follow-up stages.
Use this skill when
- The user wants the full LRJ pipeline but with swarm execution and explicit parallel stages.
- The work phase should use a swarm of agents, and post-work review plus browser testing should overlap.
Do not use this skill when
- The user wants the linear non-swarm pipeline; use
lrjinstead. - Only one workflow stage is needed.
- You cannot support the required swarm or parallel execution model.
Non-negotiable rules
- Preserve the same end-to-end routing as LRJ.
- Use swarm mode for
/workflows-work. - After work completes, you must run
/workflows-reviewand/compound-engineering-test-browserin parallel as background tasks. - Wait for both parallel tasks to finish before continuing.
- Do not skip
resolve_todo_parallelorfeature-video. - Do not reorder the pipeline.
Procedure
Execute the full source-of-truth workflow below. Preserve every conditional branch, phase, checklist, and validation step from the original instructions. When the workflow says to ask, wait, route, or run in parallel, do that exactly.
Arguments
[feature description]
Swarm-enabled LRJ. Run these steps in order, parallelizing where indicated.
Sequential Phase
/compound-engineering-ralph-loop "finish all slash commands" --completion-promise "DONE"/workflows-plan $ARGUMENTS/compound-engineering-deepen-plan/workflows-work-- Use swarm mode: Make a Task list and launch an army of agent swarm subagents to build the plan
Parallel Phase
After work completes, launch steps 5 and 6 as parallel swarm agents (both only need code to be written):
/workflows-review-- spawn as background Task agent/compound-engineering-test-browser-- spawn as background Task agent
Wait for both to complete before continuing.
Finalize Phase
/compound-engineering-resolve_todo_parallel-- resolve any findings from the review/compound-engineering-feature-video-- record the final walkthrough and add to PR- Output
DONEwhen video is in PR
Start with step 1 now.
Required output
Output exactly: DONE when the final feature video has been added to the PR.
Related Skills
the-rabak/focused-ticket-priming
tools
VerifiedTrustedCommunity
Package one plan execution packet into a compact ticket-local execution packet with parent refs, scope fences, feature-home ownership, and evidence commands. Use when converting plans into local tickets or when execution needs one ticket-sized context pack without the full plan.
1SKILL.mdUpdated May 22, 2026
the-rabak/focused-ticket-priming
tools
VerifiedTrustedCommunity
Package one plan execution packet into a compact ticket-local execution packet with parent refs, scope fences, feature-home ownership, and evidence commands. Use when converting plans into local tickets or when execution needs one ticket-sized context pack without the full plan.
1SKILL.mdUpdated May 22, 2026
the-rabak/adversarial-plan-audit
testing
VerifiedTrustedCommunity
Run a deep adversarial review of plans and architecture before implementation. Use when validating strategy docs, contracts, roadmaps, and competitive positioning with scored findings and prioritized recommendations.
1SKILL.mdUpdated May 20, 2026
the-rabak/adversarial-plan-audit
testing
VerifiedTrustedCommunity
Run a deep adversarial review of plans and architecture before implementation. Use when validating strategy docs, contracts, roadmaps, and competitive positioning with scored findings and prioritized recommendations.
1SKILL.mdUpdated May 14, 2026