CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

release

Create a release from dev branch. Generates changelog entries from commits, bumps version, and creates a PR to main. TRIGGERS - Use this skill when user says: - "/release" - create a patch release (default) - "/release minor" - create a minor release - "/release major" - create a major release - "make a release", "cut a release", "ship it", "release to main"

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 exceptionally actionable and well-guarded release runbook: every step has executable commands, explicit validation checkpoints, and error-recovery loops built from real past incidents. Its weaknesses are length and monolithic structure — repeated warnings and inlined reference material (formula template, recovery runbook) load ~200 lines into context that could live in bundle files.

Suggestions

Move the Homebrew formula template (Step 10) and the deterministic-CI-failure recovery runbook into reference files (e.g. references/formula-template.rb, references/ci-failure-recovery.md) and link them from SKILL.md, cutting ~150 lines from the always-loaded context.

Deduplicate the repeated rules: the --no-rebase rationale, the main..dev warning, and Homebrew SHA atomicity each appear with full justification in both their step and 'Important Rules' — keep the rationale in one place and a one-line rule in the checklist.

Generalize the version-specific incident anecdotes (0.7.1's 61-vs-25 commits, v0.3.10's +6626/-300 PR ballooning) into the lesson they support, or collect them in a short 'Past incidents' reference, to reduce time-sensitive tokens that will rot as versions age.

DimensionReasoningScore

Conciseness

The body is dense with project-specific, non-obvious operational detail and never explains concepts Claude already knows, but at ~830 lines it repeats several warnings across both their step and the 'Important Rules' section (--no-rebase rationale, the main..dev warning, Homebrew SHA atomicity) and inlines version-specific incident anecdotes ('On 0.7.1 it returned 61 commits when only 25 were new', 'PRs went from +80/-1 to +6626/-300') rather than generalizing or collecting them in a past-incidents section. Mostly efficient but could be tightened; not 4 because the repetition and time-sensitive version narratives exceed 'minor instances of over-explanation'.

3 / 5

Actionability

Every step ships complete, executable bash — the git log --grep release-boundary pipeline, the pre-flight 'bun build --compile' smoke test with crash-marker grep, awk checksum parsing with non-empty sanity checks, the full Homebrew formula template, and a digest-position-aware verification script. Commands are copy-paste ready with sensible parameterization (x.y.z, <N>) and cover the common cases including failure paths.

5 / 5

Workflow Clarity

Steps 1-12 are clearly sequenced with explicit validation checkpoints at every risky point (dev-contains-main drift check, mandatory pre-flight binary smoke, changelog boundary cross-check against the previous version, user review gate in Step 7, post-sync convergence verification, formula verification against published checksums, end-to-end /test-release). Feedback loops are explicit: rerun failed CI jobs once, a dedicated deterministic-failure recovery runbook, and the fix-and-re-release-as-next-patch path.

5 / 5

Progressive Disclosure

Section structure and step organization are clear, but the skill is a single monolithic file — no references/ directory exists — and content that clearly belongs in separate files is inlined, notably the ~70-line Homebrew formula template and the ~70-line CI-failure recovery runbook. Not 4 because for a skill of this size that split is more than a minor organization gap; not 2 because headers and navigation within the file are good.

3 / 5

Total

16

/

20

Passed

Description

83%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: concise third-person statement of concrete capabilities plus an explicit trigger list with natural synonyms and slash-command variants. Its only gaps are incomplete coverage of the full workflow (post-merge tagging, Homebrew, verification are invisible from the description alone) and a couple of missing natural trigger phrases.

DimensionReasoningScore

Specificity

'Generates changelog entries from commits, bumps version, and creates a PR to main' lists three concrete actions in third person. Not 5 because it omits significant parts of the skill's actual scope (tagging, GitHub release creation, Homebrew formula/tap sync, release verification); not 3 because it goes well beyond 1-2 actions.

4 / 5

Completeness

A clear 'what' ('Create a release from dev branch. Generates changelog entries from commits, bumps version, and creates a PR to main') is paired with an explicit 'TRIGGERS - Use this skill when user says:' clause listing concrete trigger phrases, matching the top anchor's structure exactly. Not 4 because the 'when' is fully explicit with concrete triggers, not merely present or generic.

5 / 5

Trigger Term Quality

Triggers include '/release', '/release minor', '/release major', 'make a release', 'cut a release', 'ship it', and 'release to main' — natural synonyms users would say, plus slash-command variants. Not 5 because a few plausible natural terms ('publish a release', 'version bump') are absent; not 3 because synonyms and variations are well covered rather than missing.

4 / 5

Distinctiveness Conflict Risk

The dev-to-main release workflow with changelog generation and version bumping is a clear niche unlikely to fire for unrelated skills. Not 5 because 'ship it' is a fairly generic phrase that could overlap with a deploy/ship skill; not 3 because the combination of triggers and described actions is well-differentiated.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (848 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository

coleam00/Archon

Path

.claude/skills/release/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.