CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

release-smoke-test

Test an oh-my-opencode-slim release candidate or bugfix before publishing. Use when validating a packed plugin artifact, release branch, crash fix, OpenCode runtime compatibility, or model-specific smoke test such as OpenCode 1.17.11 message transform regressions.

Quality

90%

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

88%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 tight, highly executable smoke-test runbook with real validation checkpoints and an honest reporting template that discloses isolation limitations. The main improvements are moving the version-pinned crash-signature example out of the main flow (or into a labeled section/reference) to protect long-term conciseness and structure.

Suggestions

Move the OpenCode 1.17.11-specific signature regex into a clearly labeled 'Known crash signatures' section or a one-level-deep reference file so the mainline steps stay version-agnostic.

Add an explicit failure branch for the signature search (e.g., 'If matches appear, the fix is not verified — do not publish; attach the log excerpt to the release issue') to make the go/no-go outcome unambiguous.

State what to do when the expected 'OK' output is not returned, mirroring the existing host-alias fallback guidance.

DimensionReasoningScore

Conciseness

The body is lean — copy-paste bash blocks with almost no concept explanation and no padding ('Use env -i for the cleanest smoke. This strips host OPENCODE_*...') earns its tokens by explaining a non-obvious isolation rationale. It misses anchor 5 because it embeds a time-sensitive version-specific example ('For the OpenCode 1.17.11 malformed-message crash, use:') inline rather than in a dedicated section, which the guidelines penalize.

4 / 5

Actionability

Every step is fully executable: complete bash for packing, tarball install with a version verification one-liner, a heredoc config, env -i invocations, the run command with timeout, and a concrete rg pattern for the crash-signature search, plus an expected output ('OK') and a fill-in reporting template. Nothing is pseudocode or hand-waved.

5 / 5

Workflow Clarity

The 'Core Workflow' numbers steps 1-8 in execution order, and explicit validation checkpoints are woven throughout: verify 'plugin_origins has exactly one entry', confirm the model, check the expected 'OK' result, and 'No matches should appear' for the signature search. Conditional recovery paths are also handled ('If OpenCode needs provider aliases from the host environment, run a second non-isolated... smoke and clearly label it').

5 / 5

Progressive Disclosure

Sections are well organized (Core Workflow, Pack Candidate, Isolated Config, Runtime Smoke, Host-Provider Smoke, Reporting Template) with no nested references and no orphaned pointers — the bundle has no external files and the body references none. It is not anchor 5 because at ~150 lines the version-specific signature detail and the host-provider variant are candidates for a one-level-deep reference file rather than staying fully inline.

4 / 5

Total

18

/

20

Passed

Description

87%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 with an explicit 'Use when...' clause, natural trigger terms, and a clearly delimited niche. Voice is imperative third-person, consistent with the rubric's good examples. The only soft spot is that the capability surface is a single test/validate verb rather than a list of distinct actions.

Suggestions

Consider enumerating the concrete sub-actions the skill performs (e.g., 'pack the tarball, install it into a throwaway app, run an isolated OpenCode smoke, and search logs for the crash signature') to strengthen the capability list.

Add a couple of common user phrasings such as 'tarball' or 'pre-publish check' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The description names a concrete action ('Test an oh-my-opencode-slim release candidate or bugfix before publishing') and enumerates several specific validation targets ('packed plugin artifact, release branch, crash fix, OpenCode runtime compatibility, or model-specific smoke test'). It stops short of anchor 5 because the 'what' is essentially a single test/validate action applied to multiple objects rather than multiple distinct concrete actions.

4 / 5

Completeness

Both halves are explicit: the 'what' ('Test an oh-my-opencode-slim release candidate or bugfix before publishing') and the 'when' ('Use when validating a packed plugin artifact, release branch, crash fix, OpenCode runtime compatibility, or model-specific smoke test'). Anchor 4 would require the 'when' to be less explicit, but here it is a full clause with concrete trigger scenarios.

5 / 5

Trigger Term Quality

Natural trigger phrases are present: 'release candidate', 'crash fix', 'release branch', 'smoke test', 'before publishing' — the words a maintainer would actually say. Not anchor 5 because terms like 'tarball', 'pre-publish check', or plugin-publishing synonyms are missing and 'packed plugin artifact' leans jargon-adjacent.

4 / 5

Distinctiveness Conflict Risk

The description is anchored to a named, narrow niche (oh-my-opencode-slim release validation) with distinct triggers (packed artifact, release branch, crash fix, OpenCode version-specific regression). It would not plausibly fire for any other skill, matching the clear-niche anchor.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

alvinunreal/oh-my-opencode-slim

Path

.agents/skills/release-smoke-test/SKILL.md

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.