CtrlK
BlogDocsLog inGet started
Tessl Logo

update-screenshots

Download screenshot baselines from the latest CI run and commit them. Use when asked to update, accept, or refresh component screenshot baselines from CI, or after the screenshot-test GitHub Action reports differences. This skill should be run as a subagent.

70

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-organized with a concrete investigation command, but its core task workflow contradicts the frontmatter description — promising a download-and-commit action that the body says is no longer needed — which hurts actionability and workflow clarity.

Suggestions

Reconcile the description and body: either update the description to reflect that baselines now update automatically after merge (no manual download/commit), or add the actual download-and-commit steps if that path is still sometimes required.

If manual baseline updates are truly obsolete, make the 'no action needed' outcome the explicit first instruction so the agent knows the primary workflow is to merge the PR rather than searching for steps that don't exist.

Add a brief verification checkpoint in the investigation workflow (e.g., confirm the downloaded artifact matches the run-id before comparing) to elevate workflow clarity.

DimensionReasoningScore

Conciseness

The body is lean — every line conveys a change-of-state fact or a concrete command, with no padding explaining concepts Claude already knows. Not a 2 because there is no unnecessary explanation to tighten; the 'What Changed' bullets each earn their place.

3 / 3

Actionability

Provides one fully executable command ('gh run download <run-id> --name screenshots --dir .tmp/screenshots') for investigation, but the body never gives executable steps for the skill's stated purpose of downloading and committing baselines — instead it states 'no manual baseline updates are needed.' It is not a 1 because the investigation command is concrete and copy-paste ready, but not a 3 because the core task guidance is essentially 'do nothing / merge' rather than actionable steps.

2 / 3

Workflow Clarity

The investigation steps are a clear numbered 1-2-3 sequence, but the primary workflow contradicts the description (description says download and commit; body says baselines update automatically after merge), creating ambiguity about which workflow applies. Not a 1 because a sequence is present, and not a 3 because the description/body mismatch leaves the intended workflow unclear and there are no checkpoints reconciling the two.

2 / 3

Progressive Disclosure

At well under 50 lines with no external references and no bundle files, the two well-organized sections ('What Changed', 'If Screenshots Need Investigation') provide clear navigation appropriate to a simple skill. Per the rubric's simple-skills note, this qualifies for a 3 without external file references.

3 / 3

Total

10

/

12

Passed

Description

100%

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, specific, and explicitly pairs what the skill does with clear trigger conditions, using natural user phrasing and a distinct niche. It is among the strongest examples in the rubric.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Download screenshot baselines from the latest CI run and commit them' — naming specific operations rather than vague language. It is not a 2 because it enumerates more than one discrete, copy-ready action.

3 / 3

Completeness

Explicitly answers both what ('Download screenshot baselines from the latest CI run and commit them') and when ('Use when asked to update, accept, or refresh... or after the screenshot-test GitHub Action reports differences'). Not a 2 because the 'Use when' trigger clause is explicit, not merely implied.

3 / 3

Trigger Term Quality

Covers natural phrasings a user would say — 'update, accept, or refresh component screenshot baselines from CI' and 'after the screenshot-test GitHub Action reports differences'. Good coverage of common variations rather than just a single keyword.

3 / 3

Distinctiveness Conflict Risk

The narrow niche of 'component screenshot baselines from CI' tied to a specific GitHub Action is unlikely to collide with other skills. Not a 2 because the triggers are specific enough to avoid overlap with generic CI or git skills.

3 / 3

Total

12

/

12

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
posit-dev/positron
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.