he-reliability-review
Review services, APIs, and multi-component systems for reliability risks including failure modes, cascading failures, resilience gaps, and SLO readiness. Use when the work involves new services, significant service changes, multiple external dependencies, or high blast-radius failure scenarios.
62
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/code_quality_review/he-reliability-review/SKILL.mdQuality
Discovery
100%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 is an excellent skill description that clearly defines its scope (reliability review of services and systems), lists specific capabilities (failure modes, cascading failures, resilience gaps, SLO readiness), and provides explicit trigger conditions for when to use it. It uses proper third-person voice and includes natural terminology that engineers would use when discussing reliability concerns.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: reviewing for 'failure modes, cascading failures, resilience gaps, and SLO readiness' across 'services, APIs, and multi-component systems'. These are concrete, well-defined review activities. | 3 / 3 |
Completeness | Clearly answers both what ('Review services, APIs, and multi-component systems for reliability risks including failure modes, cascading failures, resilience gaps, and SLO readiness') and when ('Use when the work involves new services, significant service changes, multiple external dependencies, or high blast-radius failure scenarios') with explicit trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'services', 'APIs', 'reliability', 'failure modes', 'cascading failures', 'resilience', 'SLO', 'blast-radius', 'dependencies'. These cover the domain well and match how engineers naturally discuss reliability concerns. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around reliability review and failure analysis for distributed systems. The specific focus on SLO readiness, cascading failures, and blast-radius scenarios makes it highly distinct from general code review or architecture skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable framework for reliability reviews with clear review lenses, a defined procedure, and appropriate references to external files. Its main weaknesses are redundancy between sections (Use/When to use, Full Context/Subagent Routing), lack of concrete output examples showing what a reliability finding actually looks like, and missing validation checkpoints within the review workflow itself. The content would benefit from tightening and adding a sample structured output.
Suggestions
Add a concrete example of a structured reliability finding (with severity, blast radius, detection gap, mitigation fields) so Claude knows exactly what output format to produce.
Consolidate the 'Use' and 'When to use' sections, and deduplicate the subagent routing content that appears in both 'Full Context' and its own section.
Add explicit validation checkpoints within the procedure steps—e.g., 'Confirm dependency map is complete before assigning severity' or 'Verify all critical flows are covered before producing findings.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some redundancy—'When to use' repeats the 'Use' section, 'Full Context' and 'Subagent Routing' sections contain operational boilerplate that could be trimmed, and the 'Progressive Disclosure Entry' header adds little value. However, the review lenses and procedure sections are reasonably tight. | 2 / 3 |
Actionability | The procedure provides a clear sequence of steps and the review lenses give concrete areas to inspect, but there are no executable code examples, no sample output format, and the guidance remains at the level of 'inspect' and 'map' without showing what a concrete finding looks like in practice. | 2 / 3 |
Workflow Clarity | The procedure has a numbered sequence with conditional branching (step 2 for QA reports, step 6 for routing), and the validation section provides concrete bash commands with a fail-fast gate. However, there are no explicit validation checkpoints between review steps (e.g., confirming dependency mapping before severity assignment), and the feedback loop for error recovery is absent. | 2 / 3 |
Progressive Disclosure | The skill references multiple external files (resilience-patterns.md, contract.yaml, evals.yaml, routing files) with 'Read when' annotations, which is good progressive disclosure design. However, no bundle files were provided to verify these references exist, the 'Full Context' section is somewhat cluttered mixing different reference types, and the subagent routing content is duplicated between the Full Context section and its own dedicated section. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- jscraik/Agent-Skills
- Commit
4c78f98
- Reviewed
Table of Contents
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.