CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

smoke-test

Run product-flow manual tests in parallel Docker containers, one per flow. Use when asked to smoke test, run manual tests, or validate product flows.

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

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.

This is a high-quality orchestration skill: fully executable commands, exact failure messages, explicit validation checkpoints and fallbacks for every risky operation, and a well-defined report format. The only improvements available are tightening the Observations/Snags rationale prose and consolidating the repeated docker-exec wrapping instructions.

Suggestions

Trim the rationale sentences in the Observations and Workflow Snags paragraphs (e.g. 'The goal is to surface latent issues before they become failures in a later flow') — the examples already make the intent clear.

State the docker-exec wrapping rule once in Step 3 and reference it in the numbered subagent steps instead of repeating the full bolded instruction and the wrap-each-line guidance separately.

DimensionReasoningScore

Conciseness

The body is dominated by executable commands and precise instructions with almost no explanation of concepts Claude already knows, but contains minor trimmable padding — the rationale paragraphs for Observations and Workflow Snags ("The goal is to surface latent issues before they become failures in a later flow") and the repeated docker-exec wrapping instructions. This fits 'efficient; minor instances of over-explanation' rather than the fully lean anchor 5.

4 / 5

Actionability

Every step ships copy-paste-ready commands: `git rev-parse --show-toplevel`, `bash REPO_ROOT/product-flows/build.sh`, a complete `docker run -d` with all mount flags, `ns2 spec sync product-flows/`, `ns2 spec verify`, and `docker rm -f`, plus exact bail-out messages and a concrete report table format. The `REPO_ROOT` placeholder convention is explicitly explained, matching 'fully executable, copy-paste ready'.

5 / 5

Workflow Clarity

Steps 0-5 are clearly sequenced with explicit validation checkpoints and feedback loops: build non-zero bails immediately, missing binary bails, unset ANTHROPIC_API_KEY forces SKIPPED, docker run failure marks the flow CRITICAL while still scheduling cleanup, spec-sync crash falls back to flows 01-12, and nothing-stale stops without starting containers. This is a batch operation and validation is present throughout, so the batch cap does not apply — it matches the 'explicit validation steps, feedback loops for error recovery' anchor.

5 / 5

Progressive Disclosure

With no bundle files present, this is a single-file skill whose section headers (Steps 0-5, Report) are well organized and easy to navigate, and the flow content it depends on lives in external product-flows files rather than being inlined. It is not anchor 5 — that requires well-signaled one-level-deep references and the under-50-line simple-skill exception does not apply to a ~165-line skill — but structure is good with only minor gaps, fitting anchor 4.

4 / 5

Total

18

/

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 description that clearly and explicitly states both capability and trigger conditions in third person with natural trigger phrases. Its only weakness is that the 'what' is a single composite action rather than a fuller enumeration of what the skill actually does.

Suggestions

Expand the 'what' clause to enumerate 2-3 more concrete capabilities, e.g. 'Build the project, run one Docker container per flow with isolated subagents, and report PASS/FAIL/CRITICAL verdicts per flow'.

Consider adding a synonym trigger such as 'check product flows' or 'QA the flows' to broaden natural-term coverage for users who don't use the term 'smoke test'.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action pattern — "Run product-flow manual tests in parallel Docker containers, one per flow" — but does not enumerate other capabilities (build gating, per-flow verdicts, verification stamping), matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' of 4.

3 / 5

Completeness

It explicitly answers both 'what' ("Run product-flow manual tests in parallel Docker containers, one per flow") and 'when' with concrete trigger phrases ("smoke test, run manual tests, or validate product flows"), matching the anchor-5 pattern; the 'when' clause is fully explicit, so anchor 4's 'could be more explicit' does not apply.

5 / 5

Trigger Term Quality

"Use when asked to smoke test, run manual tests, or validate product flows" provides good natural-phrase coverage that users would actually say, though common synonyms (e.g. 'QA', 'check flows') are missing, keeping it below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

"product flows" and "smoke test" establish a clear niche with distinct triggers, but "run manual tests" is broad enough to overlap with generic test-execution skills — minor overlap risk with closely related skills rather than the minimal conflict of anchor 5.

4 / 5

Total

16

/

20

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.

Validation — 15 / 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

drufball/ns2

Path

.claude/skills/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.