CtrlK
BlogDocsLog inGet started
Tessl Logo

gdb-cli

GDB debugging assistant for AI agents - analyze core dumps, debug live processes, investigate crashes and deadlocks with source code correlation

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/gdb-cli/SKILL.md

The canonical home for this skill is gdb-cli in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 highly actionable with executable commands and well-organized sections, but the multi-step workflow lacks explicit validation checkpoints for risky operations like attaching to live processes, which caps workflow clarity at 3.

Suggestions

Add explicit validation checkpoints after risky steps — e.g. verify the session loaded successfully before gathering info, and confirm attach succeeded before running commands — to lift workflow_clarity above 3.

Include an error-recovery feedback loop (e.g. if a session fails to load or attach is denied, diagnose ptrace_scope/permissions and retry) for the destructive/inspective operations.

Trim minor over-explanation such as 'Store this for subsequent commands' and redundant 'CRITICAL' labels to push conciseness toward 5.

DimensionReasoningScore

Conciseness

The body is mostly efficient — concrete commands with minimal concept explanation and little padding — but has minor over-explanation ('Store this for subsequent commands', 'CRITICAL' labels, repeated session usage) that could be trimmed, fitting level 4 rather than a fully lean 5.

4 / 5

Actionability

Provides fully executable, copy-paste-ready gdb-cli commands throughout and concrete worked examples covering common cases (null deref, deadlock, memory corruption), matching the 'fully executable, copy-paste ready, common cases covered' anchor.

5 / 5

Workflow Clarity

The 5-step sequence is clearly listed, but attaching to live processes and inspecting core dumps is risky and the workflow lacks explicit validation/verification checkpoints and error-recovery feedback loops, so the rubric's destructive/batch cap holds it at 3.

3 / 5

Progressive Disclosure

Content is well organized into clear sections (Overview, When/Do-Not-Use, Prerequisites, 5-step How It Works, Patterns, Examples, Best Practices) with no nested references and useful Links/Related-Skills navigation, fitting level 4 with only minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

66%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 states several concrete, distinguishable capabilities with natural trigger terms, but lacks 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 debugging C/C++ crashes, analyzing core dumps, or investigating deadlocks with GDB') to lift completeness above 3.

Include common synonyms and signal terms users actually say — 'segfault', 'hang', 'stack trace', 'core file' — to broaden trigger-term coverage toward 5.

Tighten the niche phrasing to further reduce overlap with general debugging skills, e.g. emphasize the source-code-correlation angle over generic debugging.

DimensionReasoningScore

Specificity

Lists several concrete actions ('analyze core dumps', 'debug live processes', 'investigate crashes and deadlocks', 'source code correlation') with only minor coverage gaps, matching the 'several specific actions' anchor rather than the fully comprehensive level 5.

4 / 5

Completeness

Has a clear 'what' but no explicit 'Use when...' trigger clause; the 'when' is only weakly implied via the action verbs, and the rubric caps completeness at 3 for a missing explicit trigger guidance.

3 / 5

Trigger Term Quality

Includes natural terms users say ('core dumps', 'crashes', 'deadlocks', 'live processes') with good coverage, but misses common synonyms like 'segfault', 'hang', 'stack trace' and any file extensions, fitting level 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (GDB debugging for AI agents with core-dump/deadlock triggers) that is mostly distinct with only minor overlap risk against general debugging skills, matching level 4.

4 / 5

Total

15

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.