CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

out-of-tree-setup

Scaffold an out-of-tree LLVM 22 compiler/language project from scratch. Covers CMake configuration, finding LLVM, linking components, a minimal LLVMContext driver, and build instructions.

Quality

81%

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

The canonical home for this skill is out-of-tree-setup in hbarve1/tessl-llvm

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

The content is a tight, highly actionable scaffolding guide with complete executable code and a clear step sequence. Its main gaps are the absence of an explicit build-failure feedback loop and the lack of one-level-deep reference files for the optional advanced sections.

Suggestions

Add an explicit validation/feedback loop for the build step, e.g. 'If the build fails with undefined LLVM symbols, confirm llvm-config-22 --cmakedir points at the matching LLVM 22 install.'

Consider moving the optional optimization-pipeline (Step 5) and pass-plugin (Step 6) snippets into a references/ file (e.g. references/advanced.md) to keep SKILL.md a lean overview with one-level-deep pointers.

Tighten a few explanatory code comments (e.g. 'Initialize targets (required before any codegen or JIT)') that state facts Claude already knows.

DimensionReasoningScore

Conciseness

The body is mostly lean: code blocks dominate, prose is minimal and purposeful, and inline comments (e.g. 'InitLLVM handles signal handlers, pretty-stack-trace, and ManagedStatic') add non-obvious value. A few explanatory comments could be trimmed, keeping it just below a 5.

4 / 5

Actionability

It provides fully executable, copy-paste-ready artifacts — a complete root CMakeLists.txt, a complete src/main.cpp that compiles and prints IR, and exact cmake configure/build/run commands — with clearly marked placeholders (<ProjectName>) covering the common case.

5 / 5

Workflow Clarity

Steps 0–6 are clearly numbered and sequenced, with an in-code validation checkpoint (verifyModule with error return) and an 'Expected output' line, but there is no explicit build-failure feedback loop or recovery guidance, leaving a minor validation gap.

4 / 5

Progressive Disclosure

Content is well-organized into clearly labeled sections with optional stages (Steps 5–6) marked, and no bundle files exist to over-inline. It falls short of 5 because all advanced material is inline rather than split into one-level-deep reference files.

4 / 5

Total

17

/

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.

The description is specific and well-scoped to a distinct niche, listing concrete capabilities, but it lacks an explicit 'Use when ...' trigger clause that would tell Claude when to invoke it. Adding a trigger sentence would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when ...' clause, e.g. 'Use when setting up a new compiler, language runtime, or LLVM-based tool that links against an installed LLVM 22.'

Reframe the capability list as direct action verbs ('Scaffold, configure CMake, locate LLVM, link components, build') instead of 'Covers ...' to strengthen specificity.

Include a couple of natural user phrases ('out-of-tree LLVM build', 'link against LLVM 22') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ('out-of-tree LLVM 22 compiler/language project') and lists several concrete actions ('CMake configuration, finding LLVM, linking components, a minimal LLVMContext driver, and build instructions'), but the 'Covers ...' framing is a topic list rather than direct action verbs, leaving minor gaps.

4 / 5

Completeness

It clearly states what the skill does ('Scaffold an out-of-tree LLVM 22 ... project from scratch') but provides no explicit 'Use when ...' trigger clause, so 'when' is only weakly implied, capping completeness at 3 per the guideline.

3 / 5

Trigger Term Quality

Core natural terms a user in this space would say are present ('out-of-tree LLVM 22', 'CMake', 'LLVMContext'), with good coverage, though it leans slightly jargon-heavy and lacks some common synonyms like 'language runtime' or 'LLVM tool'.

4 / 5

Distinctiveness Conflict Risk

It targets a clear, narrow niche (out-of-tree LLVM 22 scaffolding with an LLVMContext driver) that is highly distinct from other skills, with minimal conflict risk.

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

.tessl/tiles/hbarve1/tessl-llvm/skills/out-of-tree-setup/SKILL.md

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.