CtrlK
BlogDocsLog inGet started
Tessl Logo

hunk-release

Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.

72

Quality

90%

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

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.

A thorough, executable release runbook with strong validation checkpoints and feedback loops appropriate to destructive publish operations. The main improvement is token efficiency: trimming a few prose passages and externalizing the large notes-template block into a reference file.

Suggestions

Tighten the explanatory prose in step 2 (install-VM) and step 5 to rely more on the commands and less on rationale Claude can infer.

Move the full release-notes markdown template (lines 205-238) into a references/ file (e.g. notes-template.md) and link to it, reducing the SKILL.md footprint.

Consider extracting the Firecracker install-VM suite block into a scripts/ or references/ file so the main workflow stays a scannable overview.

DimensionReasoningScore

Conciseness

The body is command-dense and assumes Claude's competence, but several prose paragraphs (e.g., the install-VM rationale and notes-template preamble) could be tightened without losing meaning.

4 / 5

Actionability

It provides copy-paste-ready shell blocks with set -euo pipefail, exact gh/npm invocations, and a complete fill-in release-notes template covering the common cases.

5 / 5

Workflow Clarity

Numbered sections 1–6 form a clear sequence with explicit validation gates (clean-tip check, CI wait, "Stop if versions disagree", confirmation prompts) and a Failure invariants feedback loop for recovery.

5 / 5

Progressive Disclosure

The file is well-sectioned into one-level topics with no nested references, but no bundle files exist and some sizable blocks (release-notes template, install-VM suite) could be split into reference files.

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 strong description: it states concrete release actions and pairs them with an explicit, trigger-rich "Use for" clause. The only gap is a few core release synonyms (changelog, npm, version) that would round out the trigger vocabulary.

DimensionReasoningScore

Specificity

"Prepares, publishes, verifies, and curates Hunk releases" lists four concrete, distinct actions covering the release lifecycle comprehensively, matching the multiple-specific-actions anchor.

5 / 5

Completeness

It explicitly answers what ("Prepares, publishes, verifies, and curates Hunk releases") and when ("Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery") with concrete trigger phrases.

5 / 5

Trigger Term Quality

"release metadata, benchmarks, tags, publishing, release videos, backports, or recovery" gives good natural-term coverage, but omits core synonyms a maintainer would say (changelog, npm, version bump), so it sits below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The "Hunk releases" niche plus release-specific triggers (backports, release videos, benchmarks) make it clearly distinct with minimal conflict risk against unrelated skills.

5 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
modem-dev/hunk
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.