CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

90%Weight 40%Scale 1-5

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

A lean, highly actionable, code-forward skill with clear sequencing and an explicit debugging feedback loop; its main gap is minor inline-vs-reference organization and embedded validation checkpoints.

Suggestions

Add an explicit validation checkpoint in the test-writing steps (e.g. after authoring, run `llvm-lit <file> -v` and only proceed when it passes).

Consider moving the full FileCheck directive reference or lit.cfg.py substitution details into a one-level-deep reference file to strengthen progressive disclosure.

Add a brief "verify tools are present" gating note tying Step 0 to a fail-fast behavior before writing tests.

DimensionReasoningScore

Conciseness

The body is code-forward and lean — it does not explain what LLVM/IR/lit are, and every section (RUN lines, directives, opt/llc/frontend tests, lit.cfg.py, running/debugging) earns its place with runnable snippets. It assumes Claude's competence and avoids padded prose.

5 / 5

Actionability

Guidance is fully executable: concrete RUN lines, real IR examples, copy-paste lit.cfg.py, and exact llvm-lit/FileCheck --dump-input commands covering the common cases (opt, llc, custom pass, frontend).

5 / 5

Workflow Clarity

Steps 0–10 are clearly sequenced from tool verification through writing, running (Step 9), and debugging failing tests (Step 10), the latter forming an error-recovery feedback loop. It falls just short of 5 because the test-writing steps do not embed an explicit "run and confirm pass" validation checkpoint inline.

4 / 5

Progressive Disclosure

A single self-contained SKILL.md with well-organized, clearly headed sections and no nested references — easy to navigate. Given the breadth (ten scenarios) all inlined with no one-level-deep reference files for bulkier material (e.g. full directive reference, lit.cfg.py options), it stops just short of the 5 anchor.

4 / 5

Total

18

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with strong domain keywords and minimal conflict risk, but it lacks an explicit "Use when..." trigger clause, which caps completeness at 3.

Suggestions

Add an explicit trigger clause, e.g. "Use when adding or debugging tests for an LLVM pass, IR transform, codegen output, or compiler frontend."

Include common file extensions/synonyms such as ".ll" or "regression tests" to broaden natural trigger matching.

Consider leading with a second-person-friendly "Use when..." framing so the what/when split is unambiguous.

DimensionReasoningScore

Specificity

"Write lit tests with FileCheck for LLVM 22 IR transforms, pass output, and codegen" names the domain and several specific targets (IR transforms, pass output, codegen), plus concrete coverage topics (RUN lines, CHECK patterns, negative checks). It lists several specific actions but the active verb is essentially one ("write") applied across contexts, so it falls just below the comprehensive multi-verb anchor at 5.

4 / 5

Completeness

The description gives a clear "what" (write lit/FileCheck tests for LLVM 22 IR transforms, pass output, codegen, covering RUN lines/CHECK patterns/etc.) but contains no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Natural domain terms a user would say are present — "lit tests", "FileCheck", "LLVM 22", "IR transforms", "codegen", "llvm-lit" — giving good keyword coverage. It misses some natural variations/synonyms and file extensions (e.g. ".ll", "regression test"), so it does not reach the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

"Write lit tests with FileCheck for LLVM 22" carves out a clear, specialized niche with distinct triggers (lit, FileCheck, llvm-lit, LLVM IR) and minimal overlap risk with other skills.

5 / 5

Total

16

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

hbarve1/tessl-llvm

Path

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

Revision

a251bde

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill