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.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/code_quality_review/he-reliability-review/SKILL.md

Quality

Content

56%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.

A well-structured, lean review skill with a clear procedure and validation gate, but its actionability is partly high-level and its progressive-disclosure references point to bundle files that are not present.

Suggestions

Merge the redundant '## Use' and '## When to use' sections into a single trigger list and drop the meta 'This entrypoint stays concise...' line to tighten the body.

Add a concrete inspection checklist or example finding under the Procedure (e.g., a sample severity-ranked finding with blast-radius/detection-gap/mitigation) so the review steps are executable rather than directive.

Provide the missing referenced bundle files (references/resilience-patterns.md, contract.yaml, evals.yaml, task-profile.json, and the assets/ directory) so the progressive-disclosure navigation resolves to real content.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight bullet lists and assumes Claude knows SLO/cascading-failure concepts, but it carries redundant trigger sections ("## Use" and "## When to use" both enumerate when to use it) plus a meta "This entrypoint stays concise..." line that could be trimmed, fitting the 'mostly efficient but could be tightened' anchor.	3 / 5
Actionability	Concrete guidance is present in the executable Validation commands and the specific Review Lenses, but the core Procedure steps remain high-level directives ("Map service boundaries and dependency failure paths", "Inspect resilience controls") rather than executable detail, matching the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	The Procedure is a clear 6-step sequence with a conditional load gate (step 1) and an explicit fail-fast validation checkpoint ("stop at the first failed gate and do not proceed"), placing it at 'clear sequence with most checkpoints present' just below the full feedback-loop anchor.	4 / 5
Progressive Disclosure	The disclosure design is sound — overview body with one-level-deep references and clear "Read when" signals — but the referenced bundle (references/resilience-patterns.md, contract.yaml, evals.yaml, task-profile.json, assets/, and ../../../references/*) does not actually exist, so the navigation is non-functional in practice.	3 / 5
	Total	13 / 20 Passed

Description

78%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.

A strong, third-person description with an explicit Use-when clause and good natural trigger coverage. It is slightly held back by relying on a single review action rather than enumerating several distinct capabilities.

Dimension	Reasoning	Score
Specificity	Names the reliability domain and one concrete action ("Review services, APIs, and multi-component systems for reliability risks") plus several risk categories (failure modes, cascading failures, resilience gaps, SLO readiness), but it is essentially a single review action rather than a list of distinct actions, so it stops at the '1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.	3 / 5
Completeness	It clearly answers both what ("Review services, APIs, and multi-component systems for reliability risks including...") and when via an explicit "Use when the work involves new services, significant service changes, multiple external dependencies, or high-blast-radius failure scenarios" clause with concrete triggers.	5 / 5
Trigger Term Quality	Natural trigger terms a user would say are well covered — "reliability risks", "failure modes", "cascading failures", "SLO readiness", "external dependencies", "high-blast-radius" — but it lacks synonyms/file-extension style breadth, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	It carves a clear reliability-review niche with distinct triggers, but as a code_quality_review skill in a family of review skills there is minor overlap risk with closely related review skills, keeping it just below the minimal-conflict anchor.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 6 missing, 4 suspicious	Warning
referenced_paths_exist	Referenced path issues: 10 missing	Warning

	Total	13 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/code_quality_review/he-reliability-review/SKILL.md
Commit: 2f91362

Reviewed: 1 day 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.