CtrlK
BlogDocsLog inGet started
Tessl Logo

codew-release-qa-sweep

Use before claiming CodeWhale release work is done: run the full gate sweep and list the manual QA targets.

65

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./docs/skills/codew-release-qa-sweep/SKILL.md
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.

The body is highly actionable and well-sequenced with explicit validation checkpoints, and is well-structured for navigation; it is largely concise with only minor trim opportunities.

DimensionReasoningScore

Conciseness

The body is dense with executable commands and concrete QA steps and assumes Claude's competence; the explanatory prose around release_runtime_qa and a few overlapping "don't" bullets could be trimmed, matching the efficient-with-minor-over-explanation anchor.

4 / 5

Actionability

Copy-paste-ready bash commands, exact test binaries, specific issue numbers, and concrete keyboard-shortcut QA steps fully cover the common cases with executable guidance.

5 / 5

Workflow Clarity

A clearly numbered 0–8 gate sequence with an explicit "Stop on the first failure and report it" checkpoint, a merge-tree validation step, and a reporting checklist provide explicit validation and feedback loops for this release operation.

5 / 5

Progressive Disclosure

Content is well organized into clearly signaled sections (When to use, Automated gate sweep, Manual QA targets, Reporting format, Red flags) with no nested or buried references; no bundle files exist, and the few inline manual-QA details are appropriately placed with only minor organization gaps.

4 / 5

Total

18

/

20

Passed

Description

66%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 clearly states what to do and when, and is tightly scoped to a distinct niche, but its trigger language is project-jargon-heavy and it enumerates only two concrete actions.

Suggestions

Add a couple more concrete actions (e.g., verify version drift, confirm mergeability against the real release head) to lift specificity.

Broaden trigger phrasing with more natural user-facing terms (e.g., "release readiness," "pre-publish check") beyond project-internal jargon.

DimensionReasoningScore

Specificity

Names two concrete actions — "run the full gate sweep" and "list the manual QA targets" — but stops at two rather than enumerating several; matches the anchor for domain plus 1-2 concrete actions.

3 / 5

Completeness

Explicitly answers both what ("run the full gate sweep and list the manual QA targets") and when ("Use before claiming CodeWhale release work is done"), with the "when" explicit but slightly narrow in trigger phrasing.

4 / 5

Trigger Term Quality

Relevant terms like "release work is done," "gate sweep," and "manual QA targets" are present, but the phrasing is project-specific jargon and lacks common synonyms a user would naturally vary.

3 / 5

Distinctiveness Conflict Risk

Scoped tightly to CodeWhale release QA with distinct triggers ("claiming release work is done," "gate sweep"), giving it a clear niche and minimal overlap with other skills.

5 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Hmbown/CodeWhale
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.