CtrlK
BlogDocsLog inGet started
Tessl Logo

rr-debugger

Deterministic debugging with rr record-replay. Use when debugging crashes, ASAN faults, or when reverse execution is needed. Provides reverse-next, reverse-step, reverse-continue commands and crash trace extraction.

71

Quality

86%

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

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 body is action-dense and well-structured, giving executable command sequences for the common regular and ASAN crash workflows and a clean pointer to an automation script. Adding explicit validation/verification steps in the crash-extraction workflows would push workflow clarity higher.

Suggestions

Add a verification checkpoint after crash extraction (e.g., confirm the trace lands on the failing instruction before stepping forward) to strengthen the workflow's feedback loop.

Trim the opening restatement of the description to save tokens, since the frontmatter already covers it.

DimensionReasoningScore

Conciseness

The body is lean with command-focused bullets and assumes gdb competence, but the intro sentence ('rr provides deterministic record-replay debugging with full reverse execution capabilities') restates the description and a few inline code comments could be trimmed, fitting the 'efficient; minor instances of over-explanation' anchor.

4 / 5

Actionability

It provides fully executable, copy-paste-ready commands (rr record, rr replay, reverse-next, bt, up, break *$pc, reverse-continue, print, x/10xb) covering both regular and ASAN crash cases.

5 / 5

Workflow Clarity

Record→replay and both crash-extraction flows are clearly sequenced with an implicit loop ('up until last app frame'), but there are no explicit validation or error-recovery checkpoints; since replay is read-only the destructive cap does not apply, so this sits at 4 rather than 5.

4 / 5

Progressive Disclosure

A clear overview with well-organized sections and a single well-signaled one-level-deep reference ('Use scripts/crash_trace.py ...') to a real bundle file, with content appropriately split between inline guidance and the external script.

5 / 5

Total

18

/

20

Passed

Description

87%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.

A strong, concise description that clearly states what the skill does and when to use it with concrete, distinctive triggers. Minor gains possible by adding a few trigger synonyms and listing 'record' as an explicit action.

Suggestions

Add trigger synonyms such as 'replay debugging' or 'record-replay debugging' so users phrase the need more ways.

Consider listing 'record' explicitly as an action (e.g., 'Records, replays, and reverse-executes programs') to round out capability coverage.

DimensionReasoningScore

Specificity

Names the rr record-replay domain and lists several concrete actions ('reverse-next, reverse-step, reverse-continue commands and crash trace extraction'), matching the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.

4 / 5

Completeness

It explicitly answers both 'what' (deterministic debugging via rr with specific reverse commands and crash trace extraction) and 'when' ('Use when debugging crashes, ASAN faults, or when reverse execution is needed') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'debugging crashes, ASAN faults, or when reverse execution is needed' are natural user phrases with good coverage, but synonyms like 'replay debugging' or 'record-replay' as triggers are missing, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

rr/ASAN/reverse-execution is a sharply defined niche with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
gadievron/raptor
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.