tessl-labs/best-practice-scout
Proactively searches the Tessl registry for best-practice tiles before starting work that involves frameworks, libraries, or technologies where conventions matter. Triggers automatically when about to write tests, configure CI, set up auth, handle errors, design APIs, write database migrations, configure Docker, set up linting, or work with any framework or technology. Also triggers when the agent thinks "I should check if there are established best practices for this." Do NOT use for trivial edits, renaming variables, or tasks that don't involve technology-specific conventions. Requires Tessl MCP tools: search and install.
87
Quality
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description that excels at specificity, trigger terms, and completeness. It clearly explains what the skill does, when to use it, and even when NOT to use it. The main weakness is the very broad scope which could cause conflicts with other development-related skills due to generic trigger terms like 'build' and 'create'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Searches the Tessl registry for best-practice tiles and installs them'. Also enumerates specific use cases: building apps, writing tests, configuring CI, setting up auth, designing APIs, database work, Docker setup, linting config. | 3 / 3 |
Completeness | Clearly answers both what ('Searches the Tessl registry for best-practice tiles and installs them') and when ('Use when the user says build, create, implement...'). Includes explicit 'Use when' clause with trigger terms and even specifies when NOT to use it. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'build', 'create', 'implement', 'set up', 'configure', 'write tests', 'greenfield project'. Also includes technology names users would mention: React, Express, Next.js, TypeScript, Playwright, SQLite, Docker. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies Tessl registry and MCP tools, the broad trigger terms like 'build', 'create', 'implement' could conflict with many other coding/development skills. The scope is very wide (any framework, library, or technology) which increases overlap risk. | 2 / 3 |
Total | 11 / 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-structured skill with excellent workflow clarity and actionability. The six-step process is clearly sequenced with appropriate validation checkpoints and error handling. The main weakness is some verbosity in listing activation triggers and minor redundancy between the workflow steps and the rules section.
Suggestions
Condense the 'When to Activate' bullet lists into a more concise pattern description (e.g., 'any task involving frameworks, testing, CI/CD, security, or infrastructure configuration')
Remove redundant rules that duplicate workflow guidance (e.g., rule 3 about user consent is already covered in Step 5)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundant explanations. The 'When to Activate' section lists many examples that could be condensed, and some rules repeat guidance already stated in the workflow (e.g., 'never install without consent' appears in both workflow and rules). | 2 / 3 |
Actionability | Provides concrete, executable guidance with specific MCP tool names (search, install), exact file paths to check (tessl.json, .tessl/RULES.md), and a clear template for user communication. The workflow steps are specific and actionable. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing (Steps 1-6), explicit checkpoints (check existing tiles before searching, present findings before installing), and proper error handling with fallback behaviors. Includes feedback loops for user approval. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is in a single file. For a skill of this length (~100 lines), some content like the detailed 'When to Activate' lists or error handling could potentially be split out, though the current structure is functional. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents