CtrlK
BlogDocsLog inGet started
Tessl Logo

eng-runbook

An engineering runbook — service overview, alerts table, dashboards links, common procedures with copy-pasteable commands, on-call rotation, and an incident-response checklist. Use when the brief mentions "runbook", "ops doc", "on-call guide", "SRE doc", or "运维手册".

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A concise, well-structured single-file skill with a clear output contract, but it stops short of providing executable procedure commands and lacks explicit validation checkpoints. The reference to a non-existent DESIGN.md slightly weakens workflow clarity.

Suggestions

Provide concrete, copy-pasteable example commands for the common procedures (deploy, rollback, rotate keys) rather than only naming them, to move actionability toward fully executable guidance.

Add an explicit verification step in the workflow — e.g., validate that the generated HTML renders the required sections (header, alerts table, on-call table, 5-step checklist) before returning the artifact.

Either include DESIGN.md as a real bundle reference under references/ or remove the 'Read DESIGN.md' step, since the file is currently absent from the bundle.

DimensionReasoningScore

Conciseness

Lean and token-efficient: it does not explain concepts Claude already knows, the layout section enumerates concrete deliverable sections directly, and the output contract is a tight artifact block. Every line earns its place, matching the score-3 anchor for lean content.

3 / 3

Actionability

Concrete structural guidance is present (header fields, alerts-table columns, on-call columns, a 5-step checklist) and the output-contract artifact block is copy-paste ready, but the 'common procedures' step only names deploy/rollback/rotate keys as examples without providing executable commands, leaving key details as description rather than instruction.

2 / 3

Workflow Clarity

Steps are clearly numbered (1–8) and sequenced with a detailed layout sub-list, but there are no explicit validation or verification checkpoints, and step 1 references a 'DESIGN.md' file that is not present in the bundle — a sequence with missing checkpoints, matching the score-2 anchor.

2 / 3

Progressive Disclosure

The body is short (under 50 lines), self-contained, and organized into clear sections (Workflow, Output contract) with no nested references; the rubric permits a score of 3 for compact single-purpose skills that are merely well-organized, and the only external mention (DESIGN.md) does not create a deep reference chain.

3 / 3

Total

10

/

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.

A strong description: concrete capability list, natural bilingual triggers, explicit when-to-use guidance, and a distinct niche. Written in third person with no first/second-person voice, so no specificity penalty applies.

DimensionReasoningScore

Specificity

Lists multiple concrete deliverables — 'service overview, alerts table, dashboards links, common procedures with copy-pasteable commands, on-call rotation, and an incident-response checklist' — matching the score-3 anchor for multiple specific concrete actions; not merely naming a domain.

3 / 3

Completeness

Explicitly answers both what (the enumerated deliverables) and when via a clear 'Use when the brief mentions ...' clause, matching the score-3 anchor and avoiding the score-2 cap for a missing Use-when clause.

3 / 3

Trigger Term Quality

Includes natural trigger terms a user would actually say — 'runbook', 'ops doc', 'on-call guide', 'SRE doc', '运维手册' — giving good coverage including a bilingual term, matching the score-3 anchor.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (engineering runbook / ops doc) with distinct, specific triggers, making it unlikely to fire for an unrelated skill; matches the score-3 anchor.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.