take-doc-screenshots
Take screenshots of the running pgconsole app for documentation. Use when updating docs with screenshots or adding images to .mdx files.
84
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
75%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 functional and clearly scoped to a specific app and task, with explicit 'Use when' guidance that makes it easy for Claude to know when to select it. Its main weakness is that it could be more specific about the concrete actions involved (e.g., how screenshots are taken, what formats are supported) and could include more natural trigger term variations.
Suggestions
Add more specific concrete actions, e.g., 'Launches pgconsole, captures browser screenshots, saves PNG images, and embeds them in documentation files.'
Include additional natural trigger terms like 'screen capture', 'snapshot', 'capture UI', or 'documentation images' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (screenshots of pgconsole app) and one action (take screenshots for documentation), but doesn't list multiple concrete actions like capturing specific views, annotating, resizing, or saving in particular formats. | 2 / 3 |
Completeness | Clearly answers both 'what' (take screenshots of the running pgconsole app for documentation) and 'when' (when updating docs with screenshots or adding images to .mdx files) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'screenshots', 'pgconsole', 'docs', '.mdx files', and 'images', but misses natural variations users might say such as 'screen capture', 'snapshot', 'capture UI', or 'documentation images'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific to a particular app (pgconsole) and a particular task (screenshots for documentation/.mdx files), making it very unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that provides highly specific, actionable guidance for a niche task. It excels at documenting app-specific quirks (CodeMirror interaction, auth flow, overlay dismissal) that Claude couldn't infer. The main weakness is the lack of validation checkpoints — particularly verifying authentication succeeded before proceeding to screenshots, and verifying screenshot output before image conversion.
Suggestions
Add a validation step after authentication (e.g., verify the cookie was set correctly by hitting an authenticated endpoint before proceeding to screenshots)
Add a verification step after screenshot capture (e.g., check file exists and has non-zero size) before proceeding to WebP conversion
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section provides specific, necessary information that Claude wouldn't inherently know — app-specific auth flow, CodeMirror quirks, file paths, and image conventions. No unnecessary explanations of general concepts. | 3 / 3 |
Actionability | Provides executable curl commands, specific JSON structures, concrete Playwright API calls, exact CSS selectors, and specific button text to target. The CodeMirror interaction section is particularly valuable with copy-paste ready code patterns. | 3 / 3 |
Workflow Clarity | The overall flow (auth → screenshot → process) is clear and well-sequenced, but there are no explicit validation checkpoints — no step to verify the auth token works, no verification that screenshots were captured correctly before conversion, and no feedback loop for handling failures in the Playwright script. | 2 / 3 |
Progressive Disclosure | Content is well-organized into logical sections (Prerequisites, Authentication, Taking Screenshots, Image Processing, Image Convention) with appropriate subsections. For a skill of this size (~80 lines), everything is appropriately inline without needing external references. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- pgplex/pgconsole
- Commit
cb70fa0
- 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.