indices
Use this skill whenever the user wants to interact with a website – scraping data, filling forms, logging in, navigating flows, extracting structured information, or running any task a human would do in a browser.
85
79%
Does it follow best practices?
Impact
96%
4.57xAverage score across 3 eval scenarios
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/indices/SKILL.mdQuality
Discovery
82%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 covers both what the skill does and when to use it, with good natural trigger terms. However, it uses second-person voice ('Use this skill whenever the user wants...') which is acceptable but the breadth of 'any task a human would do in a browser' makes it overly broad and potentially conflicting with more specialized skills. The specificity could be improved by mentioning concrete tools or techniques used.
Suggestions
Narrow the scope or add more specific capabilities to reduce conflict risk with other web-related skills (e.g., mention specific tools like Puppeteer/Playwright, or specify output formats)
Rephrase to third person voice: 'Automates browser interactions including scraping data, filling forms...' instead of 'Use this skill whenever the user wants to...'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists several actions (scraping data, filling forms, logging in, navigating flows, extracting structured information) but they are somewhat generic browser automation tasks rather than deeply specific concrete capabilities. It names the domain and multiple actions but lacks detail on how they're performed. | 2 / 3 |
Completeness | Explicitly answers both 'what' (scraping data, filling forms, logging in, navigating flows, extracting structured information, running browser tasks) and 'when' ('whenever the user wants to interact with a website'). The 'Use this skill whenever...' clause serves as a clear trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'scraping', 'filling forms', 'logging in', 'navigating', 'extracting structured information', 'browser', 'website'. These cover a good range of how users would naturally describe browser automation tasks. | 3 / 3 |
Distinctiveness Conflict Risk | While browser automation is a fairly distinct niche, the description is broad enough ('any task a human would do in a browser') that it could conflict with web scraping-specific skills, form-filling skills, or general web interaction tools. The phrase 'extracting structured information' could overlap with data extraction skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
77%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 with excellent actionability and workflow clarity — the step-by-step task lifecycle is clearly documented with concrete commands, state descriptions, and error recovery. The main weaknesses are moderate verbosity (repeated auth section, explanatory 'When To Use' section that Claude doesn't need) and a monolithic structure that could benefit from splitting detailed reference material into separate files.
Suggestions
Remove or significantly trim the 'When To Use' section — Claude can infer appropriate use cases from the description and commands; the bullet list of examples adds tokens without adding actionable information.
Consolidate the duplicated auth commands — they appear both in 'Setup > Authenticate' and in the standalone 'Auth' section; keep only one.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary explanation (e.g., the introductory paragraph explaining what Indices does conceptually, the 'When To Use' section with examples Claude could infer, and some repeated information like auth commands appearing twice). The setup notes about PATH are thorough but somewhat verbose. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready commands throughout — task creation, run creation, secret management, authentication, and installation. Flag tables, JSON input alternatives, and specific CLI patterns are all concrete and immediately usable. | 3 / 3 |
Workflow Clarity | The multi-step workflow (check existing tasks → create → demonstrate → poll → run) is clearly sequenced with explicit steps numbered 1-4. State transitions are documented with specific states and actions, polling intervals are specified, and the 'Common Fixes' table provides error recovery guidance. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers and logical grouping, but it's a fairly long monolithic document (~200 lines) with no references to external files for advanced topics. The auth section is duplicated (appears in both Setup and its own section), and some content like detailed JSON input alternatives could be split out. | 2 / 3 |
Total | 10 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- indicesio/cli
- Commit
f711026
- 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.