go-to-bazel
Migrate gazelle:exclude lines from BUILD.bazel so that Go packages are managed by Bazel. Use when asked to migrate pkg/util, pkg/trace, pkg/tagger, or other Go packages to Bazel.
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 for a highly specialized skill. It clearly states what it does and when to use it, with domain-specific trigger terms that make it easily distinguishable. The only minor weakness is that it could list more concrete actions beyond 'migrate' (e.g., remove exclude lines, update BUILD files, add go_library targets).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names a specific domain (migrating gazelle:exclude lines from BUILD.bazel for Go packages in Bazel) but describes only one action ('migrate') rather than listing multiple concrete steps or capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (migrate gazelle:exclude lines from BUILD.bazel so Go packages are managed by Bazel) and 'when' (when asked to migrate specific Go packages like pkg/util, pkg/trace, pkg/tagger to Bazel) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes highly specific natural keywords a user would say: 'gazelle:exclude', 'BUILD.bazel', 'Go packages', 'Bazel', 'migrate', and specific package names like 'pkg/util', 'pkg/trace', 'pkg/tagger'. These are precise terms that match real user requests. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely niche and specific — gazelle:exclude migration in BUILD.bazel for Go packages is a very distinct task unlikely to conflict with any other skill. | 3 / 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 strong, highly actionable skill that provides clear executable commands, well-structured multi-step workflows with validation and fallback strategies, and thorough coverage of failure modes. Its main weakness is length—some sections could be tightened or split into referenced files to improve token efficiency. The 'Nature of these changes' section, while useful context, explains reasoning that Claude could largely infer.
Suggestions
Consider moving the 'Investigating failures' and 'Known pitfalls' sections into a separate TROUBLESHOOTING.md file, referenced from the main skill, to reduce token cost for routine runs.
Trim the 'Nature of these changes' section to 2-3 sentences—Claude doesn't need the detailed reasoning about why product regressions are impossible.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and mostly earns its length given the complexity of the migration process, but some sections are slightly verbose—e.g., the 'Nature of these changes' section explains concepts Claude could infer, and the background section restates what the description already covers. Some tightening is possible. | 2 / 3 |
Actionability | Provides fully executable bash commands for every step, concrete examples of tool invocation with flags, specific grep patterns for monitoring, a detailed table of test result meanings with actions, and exact commands for investigating failures. Highly copy-paste ready. | 3 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced with explicit validation checkpoints: the tool itself has a 3-tier fallback (full migration → partial migration → full revert), the summary output is explained, post-run re-iteration is described, and failure investigation has a clear step-by-step manual process. Feedback loops are well-defined. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers, but it's a long monolithic document (~180 lines) with no references to external files. The failure categories, known pitfalls, and detailed investigation steps could be split into separate reference files. However, since no bundle files are provided, this is somewhat expected. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- DataDog/datadog-agent
- Commit
0f36ad4
- 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.