bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
78
52%
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. Its main weakness is that the capability description could be more specific—listing concrete actions like configuring remote caching, writing BUILD files, debugging dependency graphs, or tuning build parallelism would strengthen it.
Suggestions
Expand the 'what' portion with more concrete actions, e.g., 'configure remote caching, write BUILD/WORKSPACE files, debug dependency graphs, tune parallelism and worker pools'.
Add a few more trigger term variations such as 'BUILD files', 'WORKSPACE', 'Starlark', 'bazelrc', or 'build graph' to capture more user query patterns.
| 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 remote caching, set up build rules, debug dependency graphs, tune worker pools'. | 2 / 3 |
Completeness | Clearly answers both 'what' (optimize Bazel builds for large-scale monorepos) and 'when' (Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases) with an explicit 'Use when...' clause. | 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', 'remote execution', and 'enterprise codebases' creates a clear niche that is unlikely to conflict with other build tool or general CI/CD skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a Bazel reference cheat sheet than an optimization guide. It is extremely verbose, dumping extensive boilerplate templates without a coherent workflow for actually optimizing builds. It lacks validation steps, feedback loops, progressive disclosure, and assumes Claude doesn't know basic Bazel concepts while simultaneously providing advanced configuration without context on when to apply it.
Suggestions
Add a clear diagnostic workflow: profile build → identify bottleneck type (cache misses, slow actions, dependency graph size) → apply specific optimization → validate improvement with re-profiling.
Split templates into separate bundle files (e.g., WORKSPACE_SETUP.md, REMOTE_EXECUTION.md, QUERY_PATTERNS.md) and reference them from a concise SKILL.md overview.
Remove the 'Key Concepts' table and basic architecture explanation—Claude knows what Bazel targets, packages, and labels are. Focus tokens on non-obvious optimization patterns and gotchas.
Add explicit validation checkpoints after configuration changes (e.g., 'After enabling remote cache, verify with `bazel build //... --remote_cache=... 2>&1 | grep remote` to confirm cache hits').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300 lines. Includes a concept table explaining what targets, packages, labels, and rules are—things Claude already knows. The WORKSPACE template includes boilerplate with placeholder sha256 values, and the .bazelrc template is exhaustive rather than focused on key optimization patterns. Much of this is reference material that could be in separate files or omitted entirely. | 1 / 3 |
Actionability | Templates are mostly concrete and copy-paste ready (BUILD files, .bazelrc, query commands), but many contain placeholder values (sha256='...', grpcs://cache.example.com) without guidance on how to fill them. The custom Docker rule references a //tools/docker:builder that doesn't exist. The skill provides templates but lacks guidance on when to apply specific optimizations or how to diagnose which optimization is needed. | 2 / 3 |
Workflow Clarity | For a skill about 'optimizing builds,' there is no clear workflow or sequence of steps. Templates are presented as isolated blocks without a coherent process for diagnosing performance issues, applying optimizations, and validating improvements. The Performance Optimization section lists profiling commands but has no feedback loop (profile → identify bottleneck → apply fix → re-profile). No validation checkpoints exist for any of the configuration changes. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files despite the content being long enough to warrant splitting. All seven templates are inline. There's no bundle structure to offload detailed templates (WORKSPACE config, .bazelrc, platform setup) into separate referenced files. The 'When to Use' section lists six different use cases but all content is dumped into one file. | 1 / 3 |
Total | 5 / 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
112197c
- 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.