launch-smoke-test

End-to-end smoke test for the `tessl launch skill --cloud` pipeline. Reads one Linear issue (read-only) via the Linear API to prove `LINEAR_TOKEN` is wired into the sandbox, appends a single run-marker line to a log file, then opens a GitHub pull request with that one-line change to prove `GITHUB_TOKEN` and the publish path work. Use whenever you need to verify a cloud launch can reach Linear and GitHub and open a PR end to end -- dogfooding the launch pipeline, checking that credentials forward into the sandbox, or as a minimal known-good skill to launch when debugging the launch flow itself. Self-contained: driven by launcher-supplied inputs plus `LINEAR_TOKEN` and `gh` credentials in the environment. Makes no Linear writes; its only change is the one appended log line in the PR it opens.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

An executable, well-sequenced smoke-test skill with concrete commands and explicit validation/boundary guidance; its only real weaknesses are mild repetition of the same 'one log line, no Linear writes' framing and a referenced schema file that is not present in the bundle.

Suggestions

Consolidate the repeated 'no Linear writes / single appended log line' rationale into one place (e.g. the Notes or 'deliberately omits' section) and reference it elsewhere rather than restating it four times.

Either include the referenced `./schemas/output.schema.json` in the bundle or drop the `schemas.output` declaration / inline reference so there is no dangling path.

Tighten the Procedure preamble ('You are running in a clone...') to the minimum needed, as some of that context is implied by the skill's cloud-launch scope.

Dimension	Reasoning	Score
Conciseness	Largely efficient with executable code blocks and no explanatory padding about what Linear/GitHub/PRs are, but the 'no Linear writes / single log-line change' point recurs four times (intro, step prose, Notes, and 'deliberately omits'), which is noticeable repetition for such a small skill.	4 / 5
Actionability	Provides copy-paste-ready, complete commands: the Linear `curl` GraphQL query, the exact `date -u` timestamp format, and the full `git`/`gh pr create` sequence with placeholders filled in.	5 / 5
Workflow Clarity	A clearly sequenced three-step procedure with explicit validation checkpoints — stop and report on GraphQL errors or a missing issue, stop and report missing credentials, and an explicit 'Then stop. Do not write launch-result.json' boundary — plus idempotency/concurrency guidance for the PR write.	5 / 5
Progressive Disclosure	Well-organized single-file structure with clear sections and one-level-deep reference to `./schemas/output.schema.json`, but that referenced schema file is absent from the bundle, leaving a minor dangling reference that keeps it just below a clean 5.	4 / 5
	Total	18 / 20 Passed

Description

92%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 precise, third-person description that states concrete capabilities and explicit, natural-language use triggers tied to a well-scoped niche. Minor headroom only in trigger-term synonym coverage.

Dimension	Reasoning	Score
Specificity	Names three concrete actions — 'Reads one Linear issue (read-only) via the Linear API', 'appends a single run-marker line to a log file', 'opens a GitHub pull request' — with comprehensive coverage of the skill's scope.	5 / 5
Completeness	Explicitly answers both 'what' (the three actions) and 'when' ('Use whenever you need to verify a cloud launch can reach Linear and GitHub and open a PR end to end' with concrete trigger enumerations).	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('smoke test', 'verify a cloud launch', 'debugging the launch flow', 'dogfooding the launch pipeline'); a few common synonyms are absent, so just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (`tessl launch skill --cloud` end-to-end smoke test spanning Linear and GitHub) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: drew-tessl/repo-schedules-test
Path: plugins/launch-smoke-test/SKILL.md
Commit: e75c51f

Reviewed: 8 hours 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.