check-compiler-errors

Run compile and type-check commands and report failures

Quality

31%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./cursor-team-kit/skills/check-compiler-errors/SKILL.md

Quality

Content

29%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is essentially a high-level outline rather than actionable guidance. It lacks any concrete commands, examples of common compile/type-check tools (tsc, gcc, cargo, etc.), strategies for discovering the repo's build system, or specific error-handling patterns. While the structure is clean and concise, the content doesn't provide Claude with anything it wouldn't already know how to do.

Suggestions

Add concrete examples of discovering and running compile/type-check commands (e.g., checking package.json for scripts, looking for tsconfig.json, Makefile, Cargo.toml, etc.)

Include a specific example of error output parsing and how to summarize/prioritize errors (e.g., a sample tsc output and the expected grouped summary)

Add a validation feedback loop with explicit criteria for when to stop retrying (e.g., max iterations, when errors are in generated code or external dependencies)

Provide guidance on common patterns like 'run `npm run build 2>&1 | head -50` to capture initial errors without flooding output'

Dimension	Reasoning	Score
Conciseness	The content is relatively brief and doesn't over-explain concepts Claude already knows, but it's also quite thin — the brevity comes from lack of substance rather than efficient information density.	2 / 3
Actionability	No concrete commands, code examples, or specific tool references are provided. The workflow is entirely abstract — 'run the repo's compile and type-check commands' gives no executable guidance on how to discover or run those commands.	1 / 3
Workflow Clarity	While steps are listed in sequence, they are vague and lack any validation checkpoints or error recovery details. 'Re-run checks until clean or blocked' is not a meaningful feedback loop without specifying what 'blocked' means or how to handle it.	1 / 3
Progressive Disclosure	For a simple, short skill with no bundle files, the content is organized into clear sections (Trigger, Workflow, Output) and doesn't need external references. The structure is appropriate for its scope.	3 / 3
	Total	7 / 12 Passed

Description

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 is functional but minimal. It communicates the core action (compile, type-check, report failures) but lacks a 'Use when' clause, specific toolchain/language context, and natural trigger term variations that would help Claude reliably select this skill from a large pool. It reads more like a task label than a skill description.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to compile code, check for type errors, run a build, or diagnose build failures.'

Include natural trigger term variations such as 'build', 'build errors', 'compiler errors', 'tsc', 'typescript check', or specific language/tool names relevant to the skill.

Expand the 'what' portion with more concrete actions, e.g., 'Runs project compile and type-check commands (e.g., tsc, gcc), parses error output, and reports categorized failures with file locations.'

Dimension	Reasoning	Score
Specificity	Names specific actions ('compile', 'type-check', 'report failures') but doesn't elaborate on what languages, tools, or environments are supported, nor does it list multiple concrete sub-actions beyond the basic compile/check/report cycle.	2 / 3
Completeness	Describes what the skill does (run compile/type-check and report failures) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also fairly thin, warranting a 1.	1 / 3
Trigger Term Quality	Includes relevant terms like 'compile', 'type-check', and 'failures', which users might naturally say. However, it misses common variations like 'build', 'tsc', 'typescript', 'build errors', 'compiler errors', or specific tool names.	2 / 3
Distinctiveness Conflict Risk	Somewhat specific to compilation and type-checking, which narrows the domain, but could overlap with general build skills, linting skills, or CI/CD skills. The lack of language or toolchain specificity increases conflict risk.	2 / 3
	Total	7 / 12 Passed

Validation

100%

Warnings & errors only

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: cursor/plugins
Commit: cfd81b3

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.