CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

61

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body is well-structured with a clear procedure, concrete review lenses, and good reference signaling, but it is held back by redundancy, abstract procedure steps without a worked output example, and bundle references that point to non-existent files.

Suggestions

Consolidate the redundant '## Use' and '## When to use' trigger sections and remove the duplicate Assets references to tighten the body and raise conciseness.

Add a worked example of a structured reliability finding showing the 'schema_version: 1' output shape so the expected output is concrete rather than only described.

Provide the referenced bundle files (references/resilience-patterns.md, contract.yaml, evals.yaml, task-profile.json, and assets/) or remove the broken links so progressive-disclosure navigation resolves.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence, but includes redundant trigger guidance (both '## Use' and '## When to use') and duplicate Asset references ('Assets: [./assets]' plus 'Assets directory marker'), so it could be tightened rather than being fully lean.

2 / 3

Actionability

Concrete elements exist (executable validation commands, a specific Review Lenses checklist, $context7 guidance), but the procedure steps are abstract directives ('Map service boundaries', 'Inspect resilience controls') with no worked example of a finding or the 'schema_version: 1' output shape, leaving key details missing.

2 / 3

Workflow Clarity

A clear 6-step numbered sequence with a checklist (Review Lenses) and a fail-fast gate is present, but it lacks the validate->fix->retry feedback loops anchor 3 centers on, and the prominent Validation block addresses skill self-audit rather than the review workflow itself.

2 / 3

Progressive Disclosure

References are well-signaled and one-level-deep with 'Read when' triggers (good organization, above a monolithic wall), but the referenced bundle files (references/resilience-patterns.md, contract.yaml, evals.yaml, task-profile.json, ./assets) do not exist in the bundle, so the navigation is broken and disclosure is not actually realized.

2 / 3

Total

8

/

12

Passed

Description

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.

The description is concise, third-person, and clearly states both capabilities and explicit use-when triggers with natural reliability vocabulary. It is distinctive and unlikely to conflict with adjacent skills.

DimensionReasoningScore

Specificity

Names multiple concrete review targets and risks — 'Review services, APIs, and multi-component systems for reliability risks including failure modes, cascading failures, resilience gaps, and SLO readiness' — matching the anchor that lists several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (review services/APIs/systems for reliability risks) and when via a clear 'Use when the work involves...' trigger clause, so it is not the level below where 'when' is only implied.

3 / 3

Trigger Term Quality

Covers natural reliability terms a user would say — 'new services', 'significant service changes', 'multiple external dependencies', 'high blast-radius failure scenarios' — with good variation rather than jargon-only phrasing.

3 / 3

Distinctiveness Conflict Risk

Targets a clear reliability-review niche with distinct triggers (cascading failures, SLO readiness, blast radius) unlikely to fire for general code-quality or document skills.

3 / 3

Total

12

/

12

Passed

Validation

75%

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

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 6 missing, 4 suspicious

Warning

referenced_paths_exist

Referenced path issues: 10 missing

Warning

Total

12

/

16

Passed

Repository
jscraik/Agent-Skills
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.