lit-filecheck

Write lit tests with FileCheck for LLVM 22 IR transforms, pass output, and codegen. Covers RUN lines, CHECK patterns, common directives, negative checks, and running tests with llvm-lit.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tiles/tessl-llvm/skills/lit-filecheck/SKILL.md

Quality

Content

77%Scale 1-3

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 with excellent concrete examples covering the full spectrum of LLVM lit/FileCheck testing. The workflow from setup to debugging is clear and well-sequenced. The main weaknesses are moderate verbosity (could be tightened) and a monolithic structure that would benefit from splitting reference material into separate files.

Suggestions

Consider splitting 'Common patterns', 'Common mistakes', and 'lit.cfg.py configuration' into separate reference files linked from the main skill to improve progressive disclosure and reduce the main file length.

Tighten conciseness by removing Step 0 (tool verification — Claude can infer this) and Step 7 (frontend test — very thin content that could be a one-liner in a 'Other test types' section).

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and avoids explaining basic concepts Claude would know, but it's somewhat lengthy for what it covers. Some sections like Step 7 (frontend test) and Step 0 (tools required) add marginal value, and the numbered step format creates slight overhead. The content could be tightened by ~20-30%.	2 / 3
Actionability	Every section provides fully executable, copy-paste-ready code examples. RUN lines, FileCheck directives, lit.cfg.py configuration, and debugging commands are all concrete and complete. The examples cover real LLVM patterns (instcombine, codegen, custom passes) with realistic IR.	3 / 3
Workflow Clarity	The numbered steps provide a clear sequence from setup through writing tests to running and debugging them. Step 10 explicitly covers debugging failing tests with specific commands including --dump-input=fail. The 'Common mistakes' section serves as a validation checklist. For a test-writing skill, the workflow is well-sequenced with appropriate checkpoints.	3 / 3
Progressive Disclosure	The content is well-organized with clear section headers, but it's entirely monolithic — everything is in one file with no references to external resources. The lit.cfg.py section and common patterns could be split into separate reference files. For a skill of this length (~180 lines of content), some progressive disclosure via linked files would improve navigability.	2 / 3
	Total	10 / 12 Passed

Description

82%Scale 1-3

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 strong, technically specific description that clearly identifies its domain (LLVM lit testing with FileCheck) and lists concrete capabilities. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The trigger terms are excellent for the target audience of LLVM developers.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about writing LLVM tests, FileCheck syntax, lit test configuration, or debugging test failures with llvm-lit.'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: writing lit tests with FileCheck, covering RUN lines, CHECK patterns, common directives, negative checks, and running tests with llvm-lit. These are all concrete, identifiable tasks.	3 / 3
Completeness	Clearly answers 'what does this do' (write lit tests with FileCheck for LLVM IR transforms, pass output, and codegen), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes strong natural keywords that LLVM developers would use: 'lit tests', 'FileCheck', 'LLVM 22', 'IR transforms', 'codegen', 'RUN lines', 'CHECK patterns', 'llvm-lit', 'negative checks'. These are the exact terms users would mention when needing this skill.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche targeting LLVM lit testing with FileCheck specifically. The combination of LLVM-specific terminology (lit tests, FileCheck, IR transforms, llvm-lit, RUN lines, CHECK patterns) makes it very unlikely to conflict with other skills.	3 / 3
	Total	11 / 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: hbarve1/tessl-llvm
Path: tiles/tessl-llvm/skills/lit-filecheck/SKILL.md
Commit: a251bde

Reviewed: 6 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.