CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

jit-setup

Set up an ORC JIT v2 execution engine for a language runtime using LLVM 22. Covers LLJIT, LLLazyJIT, ThreadSafeModule, symbol exposure, optimization pipeline, and calling JIT'd functions.

Quality

83%

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 jit-setup in hbarve1/tessl-llvm

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 highly actionable and concise — copy-paste-ready code across a clear Step 0–9 sequence with a useful common-mistakes checklist. Its main weakness is progressive disclosure: everything is inlined in one file with no references to separate materials for the advanced/optional topics.

Suggestions

Split optional/advanced topics (lazy JIT, the optimization pipeline, multiple JITDylibs) into reference files under ./references/ and link to them from the main steps to improve progressive disclosure.

Add explicit validation checkpoints (e.g., 'lookup a trivial function and call it to confirm the JIT works before proceeding') to strengthen workflow clarity beyond implicit ExitOnError handling.

Consider a short 'Quick start' overview at the top pointing to the per-step detail, so the body reads as an overview with signaled one-level-deep references.

DimensionReasoningScore

Conciseness

The body is lean and code-forward with no padding or explanations of basic LLVM concepts; brief inline comments ('Must be called before any JIT is constructed', 'Each module needs its own context for thread-safety') earn their place and assume Claude's competence.

5 / 5

Actionability

Provides copy-paste-ready CMake and C++ for every step (eager LLJIT, lazy JIT, symbol exposure, optimization pipeline, REPL loop, multiple JITDylibs), covering the common cases with fully executable code.

5 / 5

Workflow Clarity

Steps are clearly sequenced Step 0 through Step 9 with ExitOnError providing implicit error checkpoints and a 'Common mistakes' checklist, but there are no explicit validate-then-proceed verification gates, leaving minor validation gaps.

4 / 5

Progressive Disclosure

All ~240 lines live inline in SKILL.md with no bundle/reference files and no pointers to separate materials; the optional/advanced sections (lazy JIT, optimization pipeline, multiple JITDylibs) could be split out, so structure is present but content that could be separate is inlined.

3 / 5

Total

17

/

20

Passed

Description

75%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 distinctive, naming concrete LLVM ORC v2 APIs and a precise toolchain version. Its main weakness is the absence of an explicit 'Use when...' trigger clause in the frontmatter, which caps completeness.

Suggestions

Add an explicit 'Use when...' trigger clause to the frontmatter description (e.g., 'Use when JIT-compiling LLVM IR at runtime for a REPL, scripting engine, or language runtime') so completeness is not capped at 3.

Soften API-name jargon (LLJIT, LLLazyJIT, ThreadSafeModule) or pair it with natural synonyms like 'JIT compilation' and 'runtime execution' to improve trigger-term quality.

Consider using third-person voice ('Sets up an ORC JIT v2...') to align with the recommended description voice.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'Set up an ORC JIT v2 execution engine', 'Covers LLJIT, LLLazyJIT, ThreadSafeModule, symbol exposure, optimization pipeline, and calling JIT'd functions' — giving comprehensive coverage of the domain's specific APIs.

5 / 5

Completeness

Has a clear 'what' but no explicit 'Use when...' trigger clause in the description, so per the missing-trigger-guidance rule completeness is capped at 3; the body carries the 'when' but the frontmatter does not.

3 / 5

Trigger Term Quality

Includes natural domain terms a user would say ('ORC JIT', 'LLVM 22', 'JIT', 'execution engine', 'language runtime') but leans on API-name jargon (LLJIT, LLLazyJIT, ThreadSafeModule) rather than broader natural synonyms like 'JIT compilation' or 'runtime execution'.

4 / 5

Distinctiveness Conflict Risk

The 'ORC JIT v2 execution engine ... using LLVM 22' niche is highly specific and unlikely to overlap with or wrongly trigger other skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository

hbarve1/tessl-llvm

Path

.tessl/tiles/hbarve1/tessl-llvm/skills/jit-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.