CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

new-target-backend

Add a new target backend skeleton to LLVM 22. Covers CMake registration, TargetInfo, TargetMachine, MCTargetDesc, minimal TableGen register/instruction defs, and wiring into the LLVM build.

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 new-target-backend in hbarve1/tessl-llvm

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 well-sequenced with a build verification step, but it is a long monolithic file with no reference splitting. Extracting the larger code templates into reference files would improve progressive disclosure.

Suggestions

Move the full C++/TableGen file templates into files under references/ and link to them from SKILL.md to improve progressive disclosure.

Add an explicit fix-retry feedback loop in Step 8 (e.g. "if `grep myisa` returns nothing, re-check Triple.h/Triple.cpp registration and the LLVM_ALL_TARGETS list, then rebuild").

Tighten minor explanatory comments and prose to push conciseness toward a lean 5.

DimensionReasoningScore

Conciseness

The body is largely lean code blocks with minimal padding, though a few inline comments ("return address register", "adjust for your ISA") and short prose could be trimmed slightly.

4 / 5

Actionability

It provides copy-paste-ready CMake, TableGen, C++, and shell snippets covering the common skeleton cases, with concrete file names and build commands.

5 / 5

Workflow Clarity

Steps 0–8 are clearly sequenced and Step 8 includes a validation checkpoint (`llc --version | grep myisa`), but there is no explicit fix-and-retry feedback loop if registration fails.

4 / 5

Progressive Disclosure

No bundle files exist, so all content is inlined in a ~400-line SKILL.md with good section headers but no one-level-deep references or signaled navigation to separate files.

3 / 5

Total

16

/

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 highly distinctive, but omits an explicit "Use when..." trigger clause, which caps its completeness score. Adding a natural-language trigger phrase would raise the overall score.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user wants to add a new ISA target to LLVM 22."

Include a couple of natural synonyms users might say (e.g. "LLVM backend", "new architecture") to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — "CMake registration, TargetInfo, TargetMachine, MCTargetDesc, minimal TableGen register/instruction defs, and wiring into the LLVM build" — giving comprehensive coverage of the backend layers.

5 / 5

Completeness

It clearly states what the skill does but contains no explicit "Use when..." trigger clause, so per the rubric guideline a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural domain phrases like "new target backend", "LLVM", and "TableGen" appear, but synonym/extension variations are thin and the vocabulary leans technical rather than colloquial.

4 / 5

Distinctiveness Conflict Risk

"Add a new target backend skeleton to LLVM 22" carves out a highly specific niche with minimal overlap risk against other skills.

5 / 5

Total

17

/

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/new-target/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.