sre-platform

SRE Platform Agent. 내부 개발자 플랫폼, 개발자 경험, CI/CD 플랫폼을 담당합니다.

Install with Tessl CLI

npx tessl i github:shaul1991/shaul-agents-plugin --skill sre-platform

What are skills?

Review — 22%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Discovery

22%

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

This description is too vague and lacks actionable detail. It identifies a domain (SRE/platform engineering) but fails to specify concrete capabilities or provide explicit trigger conditions for skill selection. The Korean language description would benefit from listing specific actions and adding a clear 'Use when...' clause.

Suggestions

Add specific concrete actions like 'Manages CI/CD pipelines, configures deployments, monitors infrastructure, troubleshoots build failures'

Include a 'Use when...' clause with trigger terms such as 'deployment', 'pipeline', 'build failure', 'infrastructure', 'Kubernetes', 'Docker', 'Jenkins', 'ArgoCD'

Add natural language variations users might say: 'deploy', 'release', 'DevOps', 'container', 'orchestration', specific tool names used in your platform

Dimension	Reasoning	Score
Specificity	The description uses vague language like '담당합니다' (is responsible for) without listing any concrete actions. It mentions domains (internal developer platform, developer experience, CI/CD platform) but no specific capabilities like 'deploy', 'monitor', 'configure pipelines', etc.	1 / 3
Completeness	The description only vaguely addresses 'what' (responsible for platforms) and completely lacks a 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent instruction for when Claude should select this skill.	1 / 3
Trigger Term Quality	Contains some relevant technical keywords (SRE, CI/CD, developer platform) that users might mention, but lacks common variations and natural terms users would say like 'deployment', 'pipeline', 'build', 'release', 'DevOps', or specific tool names.	2 / 3
Distinctiveness Conflict Risk	While 'SRE Platform Agent' and 'CI/CD' provide some specificity, the broad terms 'developer platform' and 'developer experience' could overlap with many other development-related skills. The lack of specific triggers increases conflict risk.	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 content reads as a role description or job summary rather than an actionable skill. It identifies areas of responsibility (IDP, CI/CD, developer tools) and output locations but provides zero concrete guidance on how to perform any tasks. Claude cannot execute any meaningful work based solely on this content.

Suggestions

Add concrete, executable examples for at least one core task (e.g., how to create a CI/CD pipeline template, how to set up a golden path)

Define specific workflows with clear steps for common platform tasks (e.g., onboarding a new service, updating pipeline configurations)

Include actual code snippets, CLI commands, or configuration examples that Claude can use directly

Specify what tools/technologies are used (e.g., ArgoCD, Backstage, GitHub Actions) with concrete usage patterns

Dimension	Reasoning	Score
Conciseness	The content is brief and doesn't over-explain concepts Claude knows, but it's so minimal that it provides almost no actionable value - it's more of a role description than a skill.	2 / 3
Actionability	The content is entirely abstract with no concrete code, commands, or executable guidance. It only describes responsibilities without instructing how to perform any specific task.	1 / 3
Workflow Clarity	No workflows, processes, or steps are defined. The skill lists areas of responsibility but provides no guidance on how to actually accomplish tasks in those areas.	1 / 3
Progressive Disclosure	References to file locations (templates/, docs/platform/) are provided, but there's no actual content to disclose progressively - the skill is too sparse to evaluate proper information architecture.	2 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.