CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-debug-info

Add DWARF debug info to an existing LLVM 22 IR frontend. Covers DIBuilder setup, compile unit, function subprograms, local variable declarations, source locations on instructions, and module flags.

Quality

85%

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

88%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, executable recipe: complete C++ snippets for each debug-info stage, clear step sequencing with verification gates, and a pitfalls list. It is well-structured as a single file with only minor trimming opportunities.

DimensionReasoningScore

Conciseness

The body is code-forward and assumes LLVM/DWARF competence, never explaining basics; a few inline comments and the prose intro could be trimmed slightly, keeping it just below the leanest anchor.

4 / 5

Actionability

Every step ships copy-paste-ready C++ (DIBuilder, createFunction, insertDeclare, SetCurrentDebugLocation) plus concrete shell commands (clang -c, llvm-dwarfdump, lldb), fully executable across common cases.

5 / 5

Workflow Clarity

Steps 0–9 are explicitly sequenced with validation checkpoints — verifyModule in Step 7, llvm-dwarfdump --verify in Step 8, and a debugger test in Step 9 — plus a 'Common mistakes' feedback section.

5 / 5

Progressive Disclosure

A single cohesive file with clear numbered section headers and no nested references; the one stub ('Add struct/array/pointer types similarly') and inline-only type cache are minor organization gaps rather than a need for separate files.

4 / 5

Total

18

/

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, listing six concrete sub-tasks of LLVM debug-info emission. Its main weakness is the missing explicit 'Use when...' trigger guidance, which limits completeness.

Suggestions

Append an explicit trigger clause, e.g. 'Use when adding debug symbols / source-line mapping / -g-style debuggability to an LLVM IR code generator.'

Add natural synonyms users say ('debug symbols', '-g', 'gdb', 'lldb') so the description surfaces for those phrasings.

DimensionReasoningScore

Specificity

Enumerates six concrete actions — 'DIBuilder setup, compile unit, function subprograms, local variable declarations, source locations on instructions, and module flags' — giving comprehensive coverage of the task surface.

5 / 5

Completeness

The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

'DWARF debug info' and 'LLVM ... IR frontend' are natural phrases a user would say, but common synonyms like 'debug symbols', '-g', or 'gdb/lldb' are absent from the description.

4 / 5

Distinctiveness Conflict Risk

'Add DWARF debug info to an existing LLVM 22 IR frontend' is a narrow niche with distinct triggers and minimal overlap with 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

tiles/tessl-llvm/skills/add-debug-info/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.