build-fix
Incrementally fixes TypeScript and build errors with verification and rollback capabilities
56
45%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/build-fix/SKILL.mdQuality
Discovery
32%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 conveys the general purpose—fixing TypeScript and build errors with rollback—but lacks explicit trigger guidance ('Use when...') and specific concrete actions. It would benefit from more natural user-facing keywords and a clear 'when to use' clause to help Claude select it appropriately from a large skill set.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user encounters TypeScript compilation errors, tsc failures, or build errors that need incremental fixing.'
Include more natural trigger term variations such as 'tsc errors', 'type errors', 'compile errors', 'build failures', '.ts files'.
List more specific concrete actions, e.g., 'Parses TypeScript compiler output, applies targeted fixes one at a time, verifies each fix compiles, and rolls back changes that introduce new errors.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TypeScript/build errors) and mentions some actions (fixes, verification, rollback), but doesn't list specific concrete actions like 'runs tsc', 'reverts failed patches', or 'parses compiler output'. | 2 / 3 |
Completeness | Describes what it does (fixes TypeScript/build errors incrementally with verification and rollback) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also not very detailed, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'TypeScript', 'build errors', 'rollback', and 'verification', but misses common user variations like 'tsc errors', 'compile errors', 'type errors', 'build failures', or '.ts files'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'TypeScript errors', 'incremental', and 'rollback' provides some distinctiveness, but 'build errors' is broad enough to overlap with general build/CI skills or other TypeScript-related skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is concise and well-structured with a clear workflow outline, but critically lacks actionable, concrete guidance. The steps read as a high-level description of what to do rather than specific instructions Claude can execute—there are no code examples for parsing errors, no regex patterns for grouping errors by file, no concrete rollback mechanism, and no example of what a fix cycle looks like in practice.
Suggestions
Add concrete code or command examples for parsing build error output (e.g., regex patterns to extract file, line number, and error message from tsc output)
Include a concrete example of a fix cycle: show a sample TypeScript error, the proposed fix, and the verification step with expected output
Add explicit rollback instructions (e.g., using git stash or git checkout to revert a failed fix), since rollback is mentioned in the skill description but absent from the content
Specify the exact commands for verification steps rather than just 'Re-run build' and 'Verify error resolved'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every line serves a purpose, there's no explanation of what TypeScript is or how build tools work, and it assumes Claude's competence throughout. | 3 / 3 |
Actionability | The skill provides only abstract descriptions of steps without any concrete code, commands beyond the initial build command, or executable examples. 'Parse error output', 'Show error context', and 'Propose fix' are vague directions, not actionable instructions. | 1 / 3 |
Workflow Clarity | Steps are listed in a logical sequence with some validation (re-run build, verify error resolved) and stop conditions, but lacks explicit feedback loops for error recovery and specific validation commands. The rollback capability mentioned in the description is not addressed in the content. | 2 / 3 |
Progressive Disclosure | For a simple, short skill under 50 lines with a single focused task, the content is well-organized with clear numbered sections and no need for external references. | 3 / 3 |
Total | 9 / 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
- sc30gsw/claude-code-customes
- Commit
7aff694
- 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.