Name: slo-architect
Rating: 72 (1 reviews)
Author: alirezarezvani

slo-architect

Use when defining, reviewing, or operating SLOs/SLIs/error budgets. Triggers on "define an SLO", "what should our SLO be", "error budget", "burn rate", "SLI", "service level objective", "Google SRE workbook", "multi-window burn-rate alert", or any reliability-target question. Ships SLO designer, error-budget calculator with multi-window burn-rate thresholds, and SLO reviewer that catches the common bugs (target too aggressive, window too short, conflicting SLOs, no SLI definition). 4 references on SLO principles + SLI design + error budget math + composition with feature-flags-architect/chaos-engineering/kubernetes-operator. NOT a generic observability skill — specifically the SLO discipline.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is slo-architect in alirezarezvani/claude-skills

Quality

Content

78%Weight 40%Scale 1-5

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

The body is highly actionable with executable commands and well-sequenced workflows, but it is undermined by a completely missing bundle: every referenced file path (references, scripts, assets) is absent, breaking progressive disclosure. Some motivational prose could also be tightened.

Suggestions

Ship the missing bundle files (references/*.md, scripts/*.py, assets/*) or remove the references and inline the essential detail — currently every referenced path resolves to nothing.

Trim the motivational opener and 'four cardinal mistakes' prose; let the tool checks and anti-patterns list carry those points more concisely.

In Workflow 1, spell out the validate→fix→revalidate loop (what to do when slo_review.py returns FAIL) instead of only a terminal 'must pass before live' gate.

Dimension	Reasoning	Score
Conciseness	Mostly lean and actionable, but the motivational opener ('Most SLOs in the wild are arbitrary numbers no one believes') and the 'four cardinal mistakes' prose re-frame concepts that the tool checks already convey, so a few passages could be trimmed.	4 / 5
Actionability	Copy-paste-ready commands with full flags, SLI formulas, concrete output shapes (PromQL-shaped alert rules, JSON/markdown), and exact review thresholds — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	Three clearly sequenced workflows with checkpoints (Workflow 1 step 9 'must pass before live'; Workflow 2 'fix any FAIL findings'), but the primary define workflow uses a terminal validation gate rather than an explicit validate→fix→revalidate loop.	4 / 5
Progressive Disclosure	SKILL.md is well-structured with clearly signaled one-level-deep references, but the entire bundle is absent — all 4 references, 3 scripts, and 2 assets resolve to nothing, so the disclosure structure is non-functional rather than merely a minor gap.	3 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

An exemplary description: concrete capabilities, natural trigger keywords with synonyms, explicit what-and-when guidance, and an explicit boundary statement against observability skills. Voice is appropriately third person with no first/second-person leakage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions via named tools — 'Ships SLO designer, error-budget calculator with multi-window burn-rate thresholds, and SLO reviewer that catches the common bugs (target too aggressive, window too short, conflicting SLOs, no SLI definition)' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what ('Ships SLO designer... SLO reviewer...') and when ('Use when defining, reviewing, or operating SLOs/SLIs/error budgets. Triggers on...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases with synonyms — 'define an SLO', 'what should our SLO be', 'error budget', 'burn rate', 'SLI', 'service level objective', 'multi-window burn-rate alert' — exactly the terms a user would say.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche with 'NOT a generic observability skill — specifically the SLO discipline' and distinct SLO/SLI/error-budget triggers, minimizing overlap with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 11 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/skills-slo-architect/SKILL.md
Commit: 19392f7

Reviewed: ~17 hours 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.