CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-calling-convention

Add or wire a calling convention in an LLVM 22 in-tree target or document IR-level ABI choices for out-of-tree frontends. Covers CallingConv IDs, TableGen CallingConv.td, CCState/CCValAssign hooks, ISel lowering, and tests.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./.tessl/tiles/hbarve1/tessl-llvm/skills/add-calling-convention/SKILL.md

The canonical home for this skill is add-calling-convention in hbarve1/tessl-llvm

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 body is lean, well-sequenced, and actionable with concrete LLVM artifacts and validation checkpoints, but its progressive-disclosure structure depends on references that do not exist, and its single inline code example is not copy-paste ready.

Suggestions

Create or restore the referenced files (docs/calling-conventions.md, codegen.md, tablegen.md) or inline the essential terminology so the skill is not dependent on missing resources.

Replace the 'ParamAttrBuilder...' placeholder with a complete, executable parameter-attribute snippet covering the common sret/byval cases.

Add an explicit validate→fix→retry feedback loop around TableGen regeneration and ISel lowering (e.g., rebuild, run lit, on mismatch re-check CCState/CCValAssign) to raise workflow clarity.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's LLVM knowledge without padding; the Scope boundary and Out-of-tree summary restate the same in-tree-vs-out-of-tree point, a minor redundancy that could be tightened.

4 / 5

Actionability

Concrete file paths, function names (LowerFormalArguments/LowerCall/LowerReturn), and commands (cmake --build, llvm-lit, verifyModule, llc); not a 5 because the one inline snippet uses a 'ParamAttrBuilder...' placeholder and is not copy-paste ready.

4 / 5

Workflow Clarity

Clear Step 0–7 sequence with validation checkpoints (verifyModule, lit, exhaustiveness warnings) and a review checklist; not a 5 because feedback loops for TableGen/lowering mismatches are only warned about ('silent ABI bugs') rather than expressed as validate→fix→retry.

4 / 5

Progressive Disclosure

Sections are well-organized and references are clearly signaled one level deep, but every referenced path (calling-conventions.md, codegen.md, tablegen.md, add-intrinsic/SKILL.md) is missing — including the terminology doc Step 0 defers to — so the disclosure structure has real holes.

3 / 5

Total

15

/

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, domain-distinctive, and lists concrete actions and coverage areas, but it omits an explicit 'Use when…' trigger clause, which caps its completeness at 3.

Suggestions

Add an explicit 'Use when…' clause naming concrete triggers (e.g., 'Use when adding or customizing a target calling convention, reserving a CallingConv ID, or choosing ABI attributes for an out-of-tree frontend').

Include natural synonyms a user might say (e.g., 'function calling convention', 'calling convention ID', 'ABI lowering') to broaden trigger coverage toward a 5.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Add or wire a calling convention', 'document IR-level ABI choices') plus a comprehensive coverage list (CallingConv IDs, TableGen, CCState/CCValAssign hooks, ISel lowering, tests); falls short of 5 because the distinct action verbs are fewer than the score-5 example.

4 / 5

Completeness

Has a clear 'what' but no explicit 'Use when…' trigger clause; per the rubric guideline a missing explicit trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

Natural domain terms a user would say are present ('calling convention', 'ABI', 'frontend', 'LLVM'); not a 5 because some common synonyms/variations are missing.

4 / 5

Distinctiveness Conflict Risk

Highly specific niche (LLVM 22 in-tree calling conventions / ABI) with distinct triggers and minimal overlap risk; clearly distinguishable from sibling skills.

5 / 5

Total

16

/

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: 5 suspicious

Warning

Total

15

/

16

Passed

Repository

hbarve1/tessl-llvm

Path

.tessl/tiles/hbarve1/tessl-llvm/skills/add-calling-convention/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.