CtrlK
BlogDocsLog inGet started
Tessl Logo

release-publish

Publish an approved Orchard release

43

Quality

54%

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 ./projects/skill-router/examples/skills/release-publish/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

37%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 maximally lean but almost entirely hollow: two abstract behavioral constraints with no executable steps, no defined terms ("evidence", "source paths in the result"), and no validation checkpoints for an outward-facing publish operation. It needs a concrete, sequenced workflow with verification steps.

Suggestions

Provide the actual publish workflow as ordered, executable steps or commands (e.g., verify approval evidence, tag the version, run the publish command) instead of two abstract constraints.

Define the vague terms concretely: what counts as "evidence" of approval, and what "keep source paths in the result" means operationally.

Add explicit validation checkpoints and stop/error-recovery behavior — publishing is an outward-facing operation, and the current body's missing validation caps workflow clarity.

DimensionReasoningScore

Conciseness

The body is two terse sentences with zero padding and zero explanation of concepts Claude already knows. Every token present earns its place, matching the 'Lean and efficient; assumes Claude's competence' anchor; the lack of any substance is an actionability problem, not a verbosity one.

5 / 5

Actionability

"Keep source paths in the result. Stop when evidence is missing." provides no concrete code, commands, or steps for how to actually publish a release — the two constraints are entirely abstract about execution. This matches 'Entirely vague or abstract; no concrete code or commands'; it is not a 2 because even a rough high-level procedure is absent.

1 / 5

Workflow Clarity

Publishing a release is a multi-step, outward-facing operation, yet the body contains no sequence, no checkpoints, and no validation loop. "Stop when evidence is missing" gestures at a stop condition but defines neither the evidence nor the steps, fitting 'Steps missing or incoherent; no sequence; no validation for risky operations.'

1 / 5

Progressive Disclosure

The single heading is reasonable structure for such a tiny body, and nothing is buried or nested, but the skill is a skeleton: the how-to material that belongs in references or scripts is simply absent rather than appropriately split, and the body is not a clear overview of the publishing process. This fits 'Some structure but could be better organized.'

3 / 5

Total

10

/

20

Passed

Description

48%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 concise and names a specific niche (approved Orchard releases), but it provides no trigger guidance for when the skill should be used and only a single generic action verb. Adding an explicit 'Use when...' clause and enumerating the concrete publish actions would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to publish, deploy, or ship an approved Orchard release."

Enumerate the concrete actions involved (e.g., verify approval evidence, tag the version, publish artifacts) instead of the single generic verb "Publish".

Include natural synonyms such as "deploy", "ship", or "roll out" so users' phrasing matches the description.

DimensionReasoningScore

Specificity

The description "Publish an approved Orchard release" names the domain but offers only one generic action verb. It does not list any concrete sub-actions (e.g., verifying approval evidence, tagging a version, uploading artifacts), matching the 'Names the domain but actions are minimal or generic' anchor; it falls short of a 3 because not even 1-2 concrete actions are spelled out.

2 / 5

Completeness

The 'what' is clear (publish an approved Orchard release) but there is no 'Use when...' clause or any trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

"Publish" and "release" are natural terms a user would say when needing this skill, but there are no synonyms or variations ("deploy", "ship", "roll out") or artifact/extension terms, fitting 'Some relevant keywords but missing common variations or synonyms.' It is above a 2 because the keywords present are domain-relevant rather than purely generic.

3 / 5

Distinctiveness Conflict Risk

"approved Orchard release" carves a fairly specific niche with distinct triggers, giving mostly distinct behavior with only minor overlap risk against generic publish/deploy skills. It is not a 5 because "publish" is a common action verb that could still collide with other release-publishing skills.

4 / 5

Total

12

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rohitg00/ai-engineering-from-scratch
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.