bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
81
59%
Does it follow best practices?
Impact
95%
1.15xAverage score across 6 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/developer-essentials/skills/bazel-build-optimization/SKILL.mdQuality
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 solid skill description that clearly identifies its niche (Bazel build optimization) and includes an explicit 'Use when' clause with relevant trigger terms. The main weakness is that the capability listing could be more granular—specifying concrete actions like writing BUILD files, configuring caching, or setting up sandboxing would strengthen the specificity dimension.
Suggestions
Expand the capabilities with more concrete actions, e.g., 'write BUILD/BZLMOD files, configure remote caching, optimize build graph dependencies, set up sandboxed execution' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Bazel builds, monorepos) and some actions (configuring, implementing remote execution, optimizing build performance), but doesn't list multiple concrete specific actions like 'configure caching strategies, set up remote execution, tune build graph dependencies, write BUILD files'. | 2 / 3 |
Completeness | Clearly answers both 'what' (optimize Bazel builds for large-scale monorepos) and 'when' with an explicit 'Use when...' clause covering configuring Bazel, implementing remote execution, and optimizing build performance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Bazel', 'monorepo', 'remote execution', 'build performance', 'enterprise codebases'. These are terms a developer working with Bazel would naturally use in requests. | 3 / 3 |
Distinctiveness Conflict Risk | Bazel is a very specific build system, and the combination of 'Bazel', 'monorepo', and 'remote execution' creates a clear niche that is unlikely to conflict with other skills like general CI/CD or other build tool skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent concrete code examples and templates for Bazel configuration, but suffers from being a monolithic reference dump rather than an actionable guide. It lacks workflow sequencing, validation steps, and progressive disclosure — critical for a complex build system topic. The verbose explanations of basic Bazel concepts waste tokens on knowledge Claude already possesses.
Suggestions
Add a clear multi-step workflow (e.g., '1. Set up WORKSPACE → 2. Configure .bazelrc → 3. Validate with `bazel build //...` → 4. If errors, check with `bazel query`') with explicit validation checkpoints between steps.
Remove the 'Key Concepts' table and 'When to Use This Skill' section — Claude already knows what Bazel targets, packages, and labels are, and the trigger conditions add no value.
Split the content: keep a concise quick-start in SKILL.md and move detailed templates (WORKSPACE, remote execution, custom rules) into separate referenced files like TEMPLATES.md or REMOTE_EXECUTION.md.
Add verification commands after each major configuration step (e.g., 'After setting up WORKSPACE, verify with `bazel build //...` and check for dependency resolution errors').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines, with significant padding. The 'Key Concepts' table explains basic Bazel terminology Claude already knows (what a target, package, label, rule, and aspect are). The 'When to Use This Skill' section is unnecessary filler. Many templates are overly long with boilerplate that doesn't add instructional value. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code across multiple languages and configurations. The WORKSPACE, .bazelrc, BUILD files, custom rules, and query commands are all concrete and specific with real syntax. | 3 / 3 |
Workflow Clarity | There is no clear multi-step workflow or sequencing. Templates are presented as isolated blocks without guidance on order of operations, validation checkpoints, or error recovery. For a skill involving build system configuration (which can be destructive/complex), there are no feedback loops or verification steps. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of templates with no references to external files. All content is inline regardless of complexity, and there's no navigation structure or separation of quick-start vs. advanced material. A skill this large desperately needs content split across files. | 1 / 3 |
Total | 6 / 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
- wshobson/agents
- Commit
70444e5
- 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.