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.

69

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A concise, actionable reference for rr-based debugging with clear command coverage for both regular and ASAN crashes and a bundled automation script. Weak spots are the thin automation-script pointer and the absence of a worked script invocation.

Suggestions

Expand the 'Automation Script' section with a concrete invocation example, e.g. `python scripts/crash_trace.py --steps 100 --asan <trace-dir>`, and list its key flags.

Replace the 'next\nnext\n...' placeholder in both crash-extraction sections with an explicit instruction like 'repeat `next` until you reach the crashing instruction' to avoid ambiguity.

De-duplicate the repeated 'rr replay' line across the crash-extraction sections by referencing the Core Workflow once.

DimensionReasoningScore

Conciseness

The body is lean with terse command listings and no padding about what gdb/rr is, but the two crash-extraction sections lightly repeat 'rr replay' and the 'next/next/...' pattern, leaving minor trimming opportunities.

4 / 5

Actionability

Concrete executable gdb commands ('rr record <program> [args]', 'reverse-next 100', 'break *$pc', 'x/10xb <addr>') cover regular and ASAN cases, but the bundled script has no worked invocation example and 'next\n...' is a placeholder pattern.

4 / 5

Workflow Clarity

Core record→replay sequence and the regular/ASAN extraction sub-workflows are clearly sequenced; these are read-only inspection flows so no validation checkpoint is required, though no explicit error-recovery loop is given.

4 / 5

Progressive Disclosure

Well-organized section headers with one real one-level-deep reference (scripts/crash_trace.py, verified present), but the automation pointer is a bare sentence without usage/args, leaving a minor signaling gap.

4 / 5

Total

16

/

20

Passed

Description

92%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, well-targeted description that clearly conveys both capability and trigger conditions with concrete command names. Adding a few more natural synonyms (e.g. 'segfault', 'replay') would round out trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'reverse-next, reverse-step, reverse-continue commands and crash trace extraction' — alongside the rr record-replay domain, matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly states both what it does ('Deterministic debugging with rr record-replay... Provides reverse-next... commands and crash trace extraction') and when to use it ('Use when debugging crashes, ASAN faults, or when reverse execution is needed').

5 / 5

Trigger Term Quality

Natural user-facing terms like 'debugging crashes', 'ASAN faults', 'reverse execution', and 'crash trace' are present, but a few common synonyms (e.g. 'segfault', 'replay debugging') are missing, so it sits just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The rr/ASAN/reverse-execution niche is specific with distinct triggers and minimal overlap risk against general debugging skills.

5 / 5

Total

19

/

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.