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

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

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.

A highly actionable, well-sequenced operational runbook with excellent validation checkpoints and feedback loops for a destructive/batch install-test workflow. Its chief weakness is conciseness: long diagnostic asides and inline version/issue specifics inflate the token budget where a leaner core plus a reference would do.

Suggestions

Move the long diagnostic blockquotes (the INSTALL_DIR-prefix pitfall, the env-leak history note, the archon-stable restore caveat) into a references/ troubleshooting file and keep only a one-line pointer plus the must-not-forget rule inline, to recover conciseness.

Extract the per-path install/uninstall commands for brew, curl-mac, and curl-vps into a references/ file (or separate per-path snippets) so SKILL.md reads as the overview + phase sequence, improving progressive_disclosure toward a 5.

Hoist time-sensitive specifics (version 0.3.1, issue numbers like #960/#979/#1210, the 0.7.1 observation) into a 'Known regressions / version notes' section or reference so the main flow stays evergreen and token-lean.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but several long blockquote asides (the INSTALL_DIR pitfall, the env-leak history note, the archon-stable restore note) and embedded issue numbers (#960, #979, #1210) add tokens a competent Claude could be trusted to skip; time-sensitive version specifics appear inline rather than in a deprecated section.	3 / 5
Actionability	Every phase is copy-paste-ready shell with real flags, paths, and expected output ('Archon CLI v0.3.1, Build: binary, Git commit: abc12345'); pass criteria and exact-match assertions ('stripped 1 keys from ${resolved_repo}') cover the common cases precisely.	5 / 5
Workflow Clarity	Six numbered phases (scope, pre-flight, install, smoke tests, uninstall, report) are explicitly sequenced with validation checkpoints (prereq checks, release-existence check, confirm-before-install, per-test pass criteria) and explicit feedback loops ('if a test fails, continue... but mark FAIL'; uninstall 'even if Phase 4 failed').	5 / 5
Progressive Disclosure	Well-organized with clear phase sections and a 'Related' pointer list to build-binaries.sh, release.yml, install.sh and the /release skill; however all content lives inline in SKILL.md with no bundle files and the lengthy per-path install/uninstall detail could arguably split into a reference, keeping it just below a 5.	4 / 5
	Total	17 / 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 strong description: specific actions, abundant natural triggers, explicit what/when guidance, and clear scope boundaries that separate it from adjacent release/dev skills. Trigger-term coverage is thorough but not exhaustive of every synonym.

Dimension	Reasoning	Score
Specificity	Names the concrete action ('Verify a released archon binary works end-to-end') plus three specific install paths (brew, curl-mac, curl-vps) with comprehensive coverage of what each exercises.	5 / 5
Completeness	Explicitly answers 'what' (verify released binary end-to-end via a specific install path) and 'when' (Use when: cutting a new release, reproducing a user bug, validating a hotfix) plus a 'NOT for' clause bounding scope — all with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases are abundant ('test the release', 'smoke test the binary', 'verify the curl install') but a few common synonyms a user might naturally say (e.g. 'check the release') are absent.	4 / 5
Distinctiveness Conflict Risk	A narrow niche (released binary smoke-testing via brew/curl install paths) with explicit 'NOT for' exclusions (dev testing, unreleased changes, full validate suite) minimizes conflict with the /release and bun-validate workflows.	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: d1ada87

Reviewed: 4 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.