Install
$ agentstack add skill-knuckles-team-universal-skills-workspace-validator-workflow ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
workspace-validator-workflow Workflow
Autonomous workflow for systematically validating all projects in the workspace, reviewing and fixing the identified issues concurrently, and optionally publishing updates.
⚠️ Error Resolution Policy
> CRITICAL: When fixing validation errors, you MUST follow these rules: > > 1. NEVER prefix variables with an underscore (_) to silence linting errors. This is strictly prohibited. Renaming var to _var is not a fix — it's hiding the problem. > 2. Always determine root cause. For every error, understand how the variable, implementation, or code was intended to function. Close the knowledge gap before making changes. > 3. Fix the real problem. If a variable is unused because a feature is incomplete, complete the implementation. If it's genuinely dead code, remove it entirely — don't rename it. > 4. Troubleshoot ALL errors. Every single error in the report must be understood and resolved at its root cause. No exceptions.
Step 0: user-interaction
Clarify with the user if they only want to validate and fix issues, or if they also want to perform a phased bump (e.g. minor version) and phased push once 0 issues are found. Expected: run_parameters
Step 1: repository-manager-mcp
Submit validation using the rm_projects tool with action="validate". If the user requested a phased bump and phased push, pass auto_bump=true, auto_push=true, and the requested bump_part parameter. This ensures the ecosystem will automatically bump and publish on the very first run if 0 issues are found. Store the reports in /home/apps/workspace/reports. Expected: job_id Depends On: Step 0
Step 2: repository-manager-mcp
Poll for validation results by calling rm_projects with action="validate_status" and job_id="". While polling is active, do NOT wait idle. Dynamically inspect the output directory /home/apps/workspace/reports/validation-reports-/ for newly created project results subdirectories (e.g. wger-agent-results/). As soon as a repository folder is created and populated with its project summary summary__.md, immediately read it to get a quick, actionable peek into the validation issues and start triaging and fixing that project's failures concurrently without waiting for the overall validation run to complete. Expected: initialvalidationreport Depends On: Step 1
Step 3: repository-manager-mcp
Enter remediation loop. Run automated remediation via rm_workspace with action="remediate", coordinate manual fixes following the strict Error Resolution Policy, and validate targeted projects using the "Next Validation Command" from the report. As new validation sweeps run, continue utilizing dynamic per-project summaries to rapidly triage and fix bugs for completed repositories on-the-fly. Expected: remediationloopcompleted Depends On: Step 2
Step 4: repository-manager-mcp
Execute the final regression sweep on all repositories (no targeted filtering) and verify that the report shows 0 failures. Expected: finalregressionsweep_passed Depends On: Step 3
Step 5: repository-manager-mcp
If bumping and pushing was approved, verify that every project is on the main branch, run a minor version bump via rm_workspace with action="maintain", and push via rm_git with action="phased_push". Expected: pushandpublish_results Depends On: Step 4
Execution
Run this workflow as a dependency-ordered DAG. Steps with no unmet depends_on run in parallel; dependents run after their prerequisites complete.
- Run first (in parallel): Step 0 — user-interaction; Step 1 — repository-manager-mcp; Step 2 — repository-manager-mcp; Step 3 — repository-manager-mcp; Step 4 — repository-manager-mcp; Step 5 — repository-manager-mcp
Execution: If graph-os is reachable, offload the whole DAG via graph_orchestrate action=execute_workflow (or the kg-delegate skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet depends_on in parallel, then their dependents.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Knuckles-Team
- Source: Knuckles-Team/universal-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.