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.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/update-screenshots/SKILL.md

Quality

Content

72%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 lean, well-sectioned body whose main weakness is workflow clarity: the body's core message is that baseline updates happen automatically, contradicting the description's download-and-commit promise, and the investigation path omits how to get the run-id or what to do with the downloaded screenshots. Progressive disclosure is excellent for a short single-purpose skill.

Suggestions

Reconcile the body with the description: either state explicitly that the skill's action when invoked is to verify/investigate (not commit), or restore download-and-commit instructions.

Add the concrete step for obtaining the run-id, e.g. `gh run list --workflow "Checking Component Screenshots" --limit 1`.

Specify what to do after downloading the artifacts (where to view diffs, when to escalate) so the investigation loop has a defined endpoint.

Dimension	Reasoning	Score
Conciseness	The ~30-line body is efficient — a lean explanation of the new baseline storage model plus a numbered investigation procedure with one command. Minor trims possible (e.g. "Compare locally if needed. The artifact contains the full set of captured screenshots." and some of the historical "What Changed" context), so it sits just below the 'every token earns its place' anchor.	4 / 5
Actionability	The gh command is concrete and executable ("gh run download <run-id> --name screenshots --dir .tmp/screenshots") and the investigation steps are actionable, but <run-id> is never specified and 'Compare locally if needed' gives no method. Not a 3 because the guidance is genuinely executable, not pseudocode; not a 5 because obtaining the run-id and the comparison method are missing gaps.	4 / 5
Workflow Clarity	The investigation sequence (check PR comment → download artifact → compare) is numbered, but the central workflow is muddied: the frontmatter promises download-and-commit while the body states "No manual baseline updates are needed — the screenshots on the main branch commit become the new baselines automatically after merge", leaving the invoked agent without a clear primary action. Gaps include how to find the run-id and what to do after comparing. Not a 4 because these gaps are more than minor; not a 2 because a rough, readable sequence is present.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no external references needed (no references/, scripts/, or assets/ directories exist, and none are required), and it is organized into clearly labeled sections ("What Changed", "If Screenshots Need Investigation"). Per the simple-skill guideline, well-organized sections alone merit the top score.	5 / 5
	Total	16 / 20 Passed

Description

82%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 well-formed description: concrete actions, an explicit 'Use when' clause with synonyms, and a tightly scoped niche that avoids conflicts with other skills. The only gaps are the thin action list and a few missing natural trigger variations.

Suggestions

Add one more concrete action detail (e.g. where baselines land or how the commit is made) to lift specificity beyond two actions.

Include additional natural trigger phrasings such as "snapshot tests" or "visual regression" to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and exactly two concrete actions — "Download screenshot baselines from the latest CI run and commit them" — but offers nothing more specific about how. This matches the '1-2 concrete actions, not comprehensive' anchor; it is not a 4 because 'several' specific actions are not listed, and not a 2 because the actions given are concrete rather than generic.	3 / 5
Completeness	It 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 component screenshot baselines from CI, or after the screenshot-test GitHub Action reports differences"). Both halves are concrete, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural-language coverage: "update, accept, or refresh component screenshot baselines from CI", "screenshot-test GitHub Action reports differences" — including synonyms (update/accept/refresh). Not a 5 because common variations users might say (e.g. "snapshot tests", "visual regression", "flaky screenshots") are absent; not a 3 because synonym and trigger coverage goes well beyond merely 'relevant keywords'.	4 / 5
Distinctiveness Conflict Risk	A clear niche — component screenshot baselines from a specific CI workflow — with distinct triggers tied to the screenshot-test GitHub Action. Virtually no other skill would trigger on these phrases, so conflict risk is minimal.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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: posit-dev/positron
Path: .github/skills/update-screenshots/SKILL.md
Commit: b0258bc

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.