CtrlK
BlogDocsLog inGet started
Tessl Logo

tdg-personal/enterprise-agent-ops

Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.

35

Quality

35%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Discovery

17%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is overly abstract and jargon-heavy, reading more like a product tagline than actionable skill guidance. It lacks concrete actions, natural trigger terms, and any explicit 'when to use' clause, making it difficult for Claude to reliably select this skill from a pool of alternatives.

Suggestions

Add a 'Use when...' clause with specific trigger scenarios, e.g., 'Use when the user asks to run a long-running background process, manage agent lifecycles, or monitor running workloads.'

Replace abstract nouns with concrete actions, e.g., 'Start, stop, and monitor long-running agent processes; set security sandboxes; view logs and metrics; manage process restarts and health checks.'

Include natural user-facing keywords like 'background task', 'daemon', 'process monitoring', 'agent logs', 'restart', 'sandbox' that users would actually use in requests.

DimensionReasoningScore

Specificity

Names a domain (agent workloads) and some capabilities (observability, security boundaries, lifecycle management), but these are abstract concepts rather than concrete actions. No specific verbs like 'monitor logs', 'restart processes', or 'set resource limits' are provided.

2 / 3

Completeness

The description provides a vague 'what' but completely lacks a 'when' clause. There is no 'Use when...' or equivalent guidance for when Claude should select this skill, which per the rubric caps completeness at 2, and the weak 'what' brings it to 1.

1 / 3

Trigger Term Quality

The terms used ('observability', 'security boundaries', 'lifecycle management') are technical jargon that users are unlikely to naturally say. Missing common trigger terms like 'background process', 'daemon', 'long-running task', 'monitoring', or 'sandbox'.

1 / 3

Distinctiveness Conflict Risk

The phrase 'long-lived agent workloads' is somewhat distinctive and narrows the domain, but 'observability' and 'lifecycle management' are broad enough to overlap with monitoring, DevOps, or container management skills.

2 / 3

Total

6

/

12

Passed

Implementation

22%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads as a high-level overview of enterprise agent operations concepts rather than actionable guidance. It lacks concrete commands, code examples, configuration snippets, or specific tool usage instructions. Most of the content describes general DevOps principles that Claude already knows, without adding novel, executable knowledge.

Suggestions

Replace abstract bullet points with concrete, executable examples—e.g., actual PM2 commands for lifecycle management, sample systemd unit files, or specific logging/metrics collection configurations.

Add validation checkpoints to the incident pattern workflow with specific commands (e.g., 'Run `curl -s http://localhost:3000/health | jq .status` to verify recovery before resuming rollout').

Include at least one complete, copy-paste-ready example for a common scenario like deploying an agent with health checks and a kill switch.

Either link to detailed reference files for each deployment integration (PM2, systemd, containers, CI/CD) or provide inline configuration examples for at least one.

DimensionReasoningScore

Conciseness

The content is relatively lean and avoids excessive explanation, but much of it is high-level conceptual knowledge Claude already possesses (e.g., what metrics to track, what baseline controls are). These are generic ops principles, not novel instructions.

2 / 3

Actionability

The skill provides no concrete commands, code, configuration examples, or executable guidance. Everything is abstract and descriptive—bullet lists of concepts and vague numbered steps like 'isolate failing route' without specifying how.

1 / 3

Workflow Clarity

The incident pattern section lists steps but they are vague and lack validation checkpoints, specific commands, or feedback loops. 'Capture representative traces' and 'patch with smallest safe change' are not actionable sequences. No verification steps are included for the deployment/rollback workflow.

1 / 3

Progressive Disclosure

The content is organized into clear sections with reasonable headers, but the 'Deployment Integrations' section merely lists names without links or references to actual detailed files. There's no progressive disclosure structure pointing to deeper resources.

2 / 3

Total

6

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Reviewed

Table of Contents