test-release

Verify a released archon binary works end-to-end via a specific install path. Use when: cutting a new release, reproducing a user bug report on the released version, or validating that a hotfix binary actually works after a re-tag. Triggers: "test the release", "test 0.3.1 via brew", "verify the curl install", "smoke test the binary", "did the release binary work", "run /test-release", "verify the release". NOT for: testing dev work (use bun link directly), testing unreleased changes (build locally via scripts/build-binaries.sh first), or running the full validate suite (bun run validate is separate).

Quality

88%

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

81%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.

The body is highly actionable with a clearly sequenced, validated multi-phase workflow and strong internal organization. Its main weakness is conciseness: several historical and rationale blockquotes run long and could be condensed.

Suggestions

Condense the three long blockquotes (env-var-prefix, Test 4 history note, restored-version note) to the essential one-line caution; move issue-number regression context to a compact 'Known regressions' list rather than prose.

Trim the per-test 'Common failures' catalogs to the top 2-3 most likely causes, or collapse them into a single appendix, to reduce token load while keeping the diagnostic value.

Consider extracting the full PASS/FAIL report templates into a reference file so the Phase 6 section stays a lean outline of required fields.

Dimension	Reasoning	Score
Conciseness	The body is mostly high-signal operational detail, but several lengthy blockquotes (the env-var-prefix explanation, the "History — do not re-assert the old criteria" note, and the restored-version note) are over-explanation that could be tightened without losing the regression-prevention value.	3 / 5
Actionability	Every phase gives copy-paste-ready bash, exact pass criteria, and pinned assertions such as the `grep -qxF "$expected"` leak check, covering the common install and test cases concretely.	5 / 5
Workflow Clarity	A six-phase sequence with pre-flight prerequisite checks, explicit user confirmation before touching install state, per-test pass criteria, and mandatory cleanup-on-failure provides clear validation checkpoints and feedback loops throughout.	5 / 5
Progressive Disclosure	No bundle files exist, so the single SKILL.md carries everything; it is well-organized into clearly headed phases and tests with a clearly signaled Related section, though some catalog-style content (report templates, common-failures lists) could in principle be externalized if a bundle existed.	4 / 5
	Total	17 / 20 Passed

Description

95%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.

The description is specific, trigger-rich, and complete with explicit use-when and not-for boundaries, making it highly distinct from neighboring skills. Its only minor gap is that the concrete install-path variants are described in the body rather than the description itself.

Dimension	Reasoning	Score
Specificity	"Verify a released archon binary works end-to-end via a specific install path" names the artifact, action, and mechanism concretely, but stops short of enumerating the multiple distinct install paths in the description itself (those live in the body).	4 / 5
Completeness	It answers both what (verify a released binary end-to-end) and when (a "Use when:" clause plus explicit "NOT for" boundaries), with concrete trigger phrases attached.	5 / 5
Trigger Term Quality	An explicit Triggers list spans natural synonyms ("test the release", "smoke test the binary", "verify the release") plus the slash-command form "run /test-release", giving comprehensive coverage of phrases a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The niche is narrow (released-binary smoke testing via specific install paths) and the "NOT for" clause cleanly separates it from dev testing and the full validate suite, minimizing overlap with sibling skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (543 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	13 / 16 Passed

Repository: coleam00/Archon
Path: .claude/skills/test-release/SKILL.md
Commit: e237584

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.