Name: multi-ai-debugging
Rating: 61.6 (1 reviews)
Author: fernandezbaptiste

multi-ai-debugging

Systematic debugging using Claude, Gemini, and Codex as specialized agents. Multi-agent root cause analysis, log analysis, error classification, and auto-fix generation. Use when debugging production issues, analyzing error logs, performing root cause analysis, troubleshooting complex systems, or implementing self-healing patterns.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/multi-ai-debugging/SKILL.md

The canonical home for this skill is multi-ai-debugging in fernandezbaptiste/Skrillz

Quality

Content

63%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 rich and actionable with well-sequenced, validated workflows, but it is verbose and keeps too much detail inline rather than pushing it into the existing reference files. Tightening the fluffy sections and signaling references inline would lift the weaker dimensions.

Suggestions

Remove the "Quality Targets" percentages and the "validated by tri-AI research" / "2024-2025 best practices" framing — they are marketing fluff that adds tokens without instruction.

Signal the reference files inline where relevant (e.g., "See references/log-analysis-patterns.md for clustering techniques") instead of only listing them at the end.

Move the full Example Debugging Session and the OpenTelemetry/Log Correlation integration code into a reference file, keeping SKILL.md a lean overview that points to them.

Dimension	Reasoning	Score
Conciseness	The ~640-line body is mostly actionable, but sections like the "Quality Targets" percentages, "validated by tri-AI research", and "Based on 2024-2025 best practices" are fluffy, and the repeated prompt-template boilerplate across six operations could be tightened.	3 / 5
Actionability	Concrete bash commands (gemini, codex, git log, grep) and Python code (playbooks, circuit breaker, OpenTelemetry) are provided throughout; prompt templates use placeholders appropriately but are not always fully copy-paste ready.	4 / 5
Workflow Clarity	Operations are clearly sequenced with validation feedback loops (RCA cross-validation, Fix→Critique→Regression test, circuit breakers), so the destructive/batch cap is avoided; only minor validation gaps remain.	4 / 5
Progressive Disclosure	Two real reference files exist and are listed, but they are only mentioned in a trailing References section rather than signaled inline, and the bulk of detail (decision trees, integration patterns, full example session) is inlined in SKILL.md instead of being split out.	3 / 5
	Total	14 / 20 Passed

Description

83%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 strong: it explicitly answers both what the skill does and when to use it with natural trigger phrases, and is clearly distinct from generic debugging skills. Minor improvements could add synonym triggers and frame more actions concretely rather than architecturally.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "root cause analysis, log analysis, error classification, and auto-fix generation" — but the "multi-agent specialized agents" framing describes architecture rather than additional concrete actions, leaving minor coverage gaps.	4 / 5
Completeness	Clearly states both what it does (the four debugging actions) and an explicit "Use when…" clause with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases are well covered ("debugging production issues", "analyzing error logs", "root cause analysis", "troubleshooting complex systems"), but common synonyms like "stack traces", "incidents", or "bugs" are missing.	4 / 5
Distinctiveness Conflict Risk	The Claude/Gemini/Codex multi-agent ensemble is a distinct niche with specific triggers, though it has minor overlap risk with general debugging or troubleshooting skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (644 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: .claude/skills/multi-ai-debugging/SKILL.md
Commit: 93ed392

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.