sre-reliability

SRE Reliability Agent. 서비스 신뢰성, SLO/SLI 관리, 가용성 개선을 담당합니다.

Quality

27%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/sre-reliability/SKILL.md

Quality

Content

22%

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

This skill is essentially a role description rather than actionable guidance. It lists SRE responsibilities and output directories but provides no concrete instructions, examples, code snippets, or workflows that would enable Claude to actually perform SRE reliability tasks. The content reads more like a job description than a skill file.

Suggestions

Add concrete examples of SLO/SLI definitions with actual metrics, thresholds, and YAML/JSON configuration snippets

Include a step-by-step workflow for Error Budget calculation and management with validation checkpoints

Provide executable code or commands for setting up monitoring dashboards or alerts

Add specific examples of availability improvement patterns with before/after scenarios

Dimension	Reasoning	Score
Conciseness	The content is brief but lacks substance. While it doesn't over-explain concepts Claude knows, it's essentially a placeholder with bullet points that don't provide actionable value.	2 / 3
Actionability	The skill provides only vague descriptions ('SLO/SLI 정의 및 모니터링', 'Error Budget 관리') without any concrete code, commands, examples, or specific instructions on how to perform these tasks.	1 / 3
Workflow Clarity	No workflow is defined. The skill lists responsibilities but provides no sequence of steps, validation checkpoints, or process guidance for any of the mentioned tasks.	1 / 3
Progressive Disclosure	The skill mentions output locations (docs/slo/, monitoring/) which suggests some structure, but there are no actual references to detailed documentation or examples that would help Claude learn the specifics.	2 / 3
	Total	6 / 12 Passed

Description

32%

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 identifies the SRE domain and key concepts (SLO/SLI, availability) but remains too high-level without concrete actions or explicit usage triggers. The lack of a 'Use when...' clause significantly limits Claude's ability to know when to select this skill over others. Adding specific actions and natural trigger terms would greatly improve skill selection accuracy.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user asks about SLOs, error budgets, service reliability, uptime targets, or incident postmortems'

List specific concrete actions such as 'Define SLO targets, calculate error budgets, analyze availability metrics, create incident runbooks'

Include more natural trigger terms users might say: 'uptime', 'downtime', 'error budget', '9s of availability', 'incident response', 'on-call'

Dimension	Reasoning	Score
Specificity	Names the domain (SRE/reliability) and mentions some areas (SLO/SLI management, availability improvement) but lacks concrete actions like 'define SLOs', 'calculate error budgets', or 'analyze incident metrics'.	2 / 3
Completeness	Describes what it handles at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes relevant technical terms (SRE, SLO, SLI, 신뢰성/reliability, 가용성/availability) but missing common variations users might say like 'uptime', 'error budget', 'incident response', 'on-call', or 'monitoring'.	2 / 3
Distinctiveness Conflict Risk	SRE/SLO/SLI terms provide some distinctiveness, but '서비스 신뢰성' (service reliability) is broad enough to potentially overlap with monitoring, DevOps, or incident management skills.	2 / 3
	Total	7 / 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

Repository: shaul1991/shaul-agents-plugin
Commit: 9242c58

Reviewed: 4 months 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.