← Back to Skills Marketplace
69
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install nm-imbue-workflow-monitor
Description
Detect workflow failures and inefficient patterns, then create GitHub issues for improvement via /fix-workflow
Usage Guidance
Before installing: 1) Confirm what the three required config paths (night-market.leyline:git-platform, night-market.imbue:proof-of-work, night-market.sanctum:fix-workflow) will provide — specifically which tokens/credentials and scopes; prefer least privilege (repo-only tokens). 2) Ensure the environment where the skill runs has the gh CLI and any other tools the SKILL.md uses, or update the skill metadata to declare them. 3) Inspect how evidence is collected and stored (proof-of-work) and whether outputs or environment variables are sanitized — the templates include raw command output and env notes which can leak secrets; require redaction or manual approval before posting. 4) Keep auto_create_issues: false (the default) and test in a non-production repo to validate behavior. 5) If you accept the skill, restrict its git token scope, monitor created issues for leaked data, and ask the author to add explicit binary/credential declarations and an evidence-sanitization step to the SKILL.md.
Capability Assessment
Purpose & Capability
The skill claims to detect failures/inefficiencies and create issues on the git platform; its instructions and templates align with that purpose. However, it uses the GitHub CLI (gh) in examples and expects access to a 'git platform' via configuration, yet declares no required binaries or credentials. The declared config paths (night-market.leyline:git-platform, night-market.imbue:proof-of-work, night-market.sanctum:fix-workflow) appear relevant, but the mapping from those config paths to actual tokens/permissions isn't shown — a minor mismatch between claimed behavior and explicit requirements.
Instruction Scope
Instructions tell the agent to capture commands, outputs, timings and to generate issue bodies that include command outputs and environment/context details. Creating issues with raw command output or environment notes could leak sensitive data (secrets, tokens, internal paths). There are no explicit redaction or sanitization steps in the SKILL.md. The skill also references reading session context (e.g., /context) and running shell commands (gh issue list, timeout, etc.), which is expected for this functionality but increases the risk of unintended data exposure if approval/redaction are not enforced.
Install Mechanism
This is instruction-only with no install spec and no code files; that reduces install-time risk. There is no downloading/extracting of remote archives or third‑party packages in the skill itself.
Credentials
The skill declares no required environment variables but does require three configuration paths that likely supply git-platform credentials and hooks. Requiring a git-platform credential is proportionate to creating issues, but the skill does not explicitly declare the need for the GitHub CLI binary or a GitHub token scope. Users should confirm what the named config paths resolve to and ensure only minimal (repo-scoped) permissions are granted. Templates reference 'ENV_NOTES' and 'WORKING_DIR' which could pull sensitive environment information if collected.
Persistence & Privilege
The skill does not request always:true and is user-invocable. It documents guardrails (approval required by default, rate limiting, no duplicates) which mitigate autonomous creation of issues. Autonomous invocation is allowed by platform default but not combined with always:true or broad undeclared credential access here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install nm-imbue-workflow-monitor - After installation, invoke the skill by name or use
/nm-imbue-workflow-monitor - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of workflow-monitor.
- Monitors workflow executions for errors and inefficiencies.
- Automatically generates structured GitHub/GitLab issues with evidence and suggested fixes.
- Detects patterns such as command failures, timeouts, retry loops, context exhaustion, and inefficient tool usage.
- Provides configurable thresholds and guardrails to prevent duplicate or unnecessary issues.
- Outputs detailed reports and integrates with related skills for capturing evidence and proposing improvements.
Metadata
Frequently Asked Questions
What is Nm Imbue Workflow Monitor?
Detect workflow failures and inefficient patterns, then create GitHub issues for improvement via /fix-workflow. It is an AI Agent Skill for Claude Code / OpenClaw, with 69 downloads so far.
How do I install Nm Imbue Workflow Monitor?
Run "/install nm-imbue-workflow-monitor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Nm Imbue Workflow Monitor free?
Yes, Nm Imbue Workflow Monitor is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Nm Imbue Workflow Monitor support?
Nm Imbue Workflow Monitor is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Nm Imbue Workflow Monitor?
It is built and maintained by athola (@athola); the current version is v1.0.0.
More Skills