test-release-canary

Manually dispatch and iterate on the Release Canary workflow that smoke-tests published OpenShell artifacts (install.sh on macOS/Ubuntu/Fedora, Helm chart on kind) after each Release Dev publish. Use when changing `.github/workflows/release-canary.yml`, validating a release before tagging, debugging a canary failure, or reproducing a canary job locally. Trigger keywords - release canary, release-canary, canary failed, canary dispatch, test release canary, post-release smoke, install.sh canary, helm chart canary, kind canary, dispatch canary.

Quality

98%

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

Quality

Content

96%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 dense, executable runbook that assumes Claude's competence and provides concrete commands plus a strong diagnostics feedback loop. The only minor gap is progressive disclosure: all content lives in one ~145-line file with no external references, though for a debugging runbook this is largely appropriate.

Suggestions

Consider moving the 'Diagnosing failures' symptom/cause/where table into a references/ file (e.g. DIAGNOSTICS.md) and keeping SKILL.md as a pointer, to shorten the core file.

The full 'Local kind reproduction' command block could be extracted to a scripts/ or references/ file with a one-line pointer, improving token efficiency for users who only need dispatch guidance.

Dimension	Reasoning	Score
Conciseness	Lean operational prose with no padding of concepts Claude already knows; it assumes competence with gh, helm, and kubectl, and every section (jobs table, dispatch commands, kind reproduction, diagnostics) earns its place with task-specific nuance.	5 / 5
Actionability	Fully executable, copy-paste-ready commands throughout (`gh workflow run`, `gh run watch`, `helm install ... --wait --timeout 5m`, `kubectl wait`, `kubectl port-forward`) plus a symptom→cause→where diagnostics table covering the common failure cases.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced (manual dispatch: run → watch → view-failed; local kind: create cluster → install → helm install → wait → port-forward → add gateway → status) with a feedback-loop diagnostics table and explicit teardown (`kind delete cluster`).	5 / 5
Progressive Disclosure	Well-organized into clear section headers with no nested references and a useful 'Related' pointer to sibling skills, but the single-file runbook inlines a sizable diagnostics table and full local-reproduction script that could optionally live in separate reference files.	4 / 5
	Total	19 / 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.

A strong description: it states concrete capabilities, gives an explicit 'Use when' clause, and supplies a rich set of natural trigger keywords. It is third-person, concise, and clearly scoped to a single workflow.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Manually dispatch and iterate', 'smoke-tests published OpenShell artifacts (install.sh on macOS/Ubuntu/Fedora, Helm chart on kind)' — with comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (dispatch and iterate on the Release Canary workflow that smoke-tests artifacts) and 'when' ('Use when changing `.github/workflows/release-canary.yml`, validating a release before tagging, debugging a canary failure, or reproducing a canary job locally') with concrete trigger phrases.	5 / 5
Trigger Term Quality	An explicit 'Trigger keywords' list provides comprehensive natural-term coverage including synonyms and hyphen variants ('release canary', 'release-canary', 'canary failed', 'canary dispatch', 'install.sh canary', 'helm chart canary', 'kind canary').	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche — the OpenShell Release Canary workflow — with distinct, specific triggers unlikely to fire for unrelated 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/OpenShell
Path: .agents/skills/test-release-canary/SKILL.md
Commit: 292559c

Reviewed: 5 days 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.