detecting-database-deadlocks

Process use when you need to work with deadlock detection. This skill provides deadlock detection and resolution with comprehensive guidance and automation. Trigger with phrases like "detect deadlocks", "resolve deadlocks", or "prevent deadlocks".

Quality

66%

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 ./plugins/database/database-deadlock-detector/skills/detecting-database-deadlocks/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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 concrete queries, error codes, and fix patterns, and it stays free of basic-concept padding. Its weaknesses are mild redundancy across sections, a missing verify-the-fix feedback loop, and no navigation to the bundled scripts and references that exist alongside it.

Suggestions

Add an explicit validation checkpoint after step 6, e.g. re-run the deadlock log query / monitoring script to confirm the fix eliminated the deadlock before documenting it.

De-duplicate error codes and root-cause patterns between the Instructions, Error Handling table, and Examples so each appears in one canonical place.

Reference the bundled scripts in the body (e.g. 'Run scripts/analyze_deadlocks.py to capture the current lock wait graph') so progressive disclosure points to the assets that exist.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but error codes (40P01, 1213) and root-cause patterns are repeated across the Instructions, Error Handling table, and Examples sections, so it could be tightened.	2 / 3
Actionability	It provides copy-paste-ready SQL queries (the pg_stat_activity/pg_locks join, SHOW ENGINE INNODB STATUS), specific error codes, and concrete fixes for each root-cause pattern, matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	The 10-step sequence is clear, but for database operations the rubric expects an explicit validate-fix-retry feedback loop; step 7 covers retry and step 8 monitoring, yet there is no checkpoint verifying that a prevention change actually eliminated the deadlock, capping clarity at 2.	2 / 3
Progressive Disclosure	The body is well-sectioned but monolithic within SKILL.md and never signals the bundled scripts (e.g. analyze_deadlocks.py) or reference files, leaving content like the error table and examples inline when it could be split out.	2 / 3
	Total	9 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 covers both what the skill does and when to trigger it, but it is padded with vague fluff and lacks the 'database' qualifier that would sharpen its niche and trigger coverage. Tightening the action list and adding database-specific trigger terms would lift the weaker dimensions.

Suggestions

Replace 'comprehensive guidance and automation' with concrete actions, e.g. 'Detect, analyze, and prevent database deadlocks in PostgreSQL, MySQL, and MongoDB by inspecting lock wait graphs and deadlock logs.'

Add database-specific trigger phrases such as 'database deadlock', 'lock wait graph', 'InnoDB deadlock', and 'pg_locks' so users naturally invoke this skill over generic concurrency skills.

Fix the malformed opening clause 'Process use when...' to a clean 'Use when...' statement.

Dimension	Reasoning	Score
Specificity	The description names the domain and a couple of actions ('deadlock detection and resolution') but pads them with fluff ('comprehensive guidance and automation') rather than listing multiple concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It answers both what ('deadlock detection and resolution') and when via an explicit trigger clause ('Trigger with phrases like ...'), satisfying the anchor that requires both an explicit 'what' and 'when'.	3 / 3
Trigger Term Quality	It offers three natural phrases ('detect deadlocks', 'resolve deadlocks', 'prevent deadlocks'), but coverage is limited to variations of the word 'deadlocks' and omits common variations a user might say like 'database deadlock', 'lock wait', or 'deadlock log'.	2 / 3
Distinctiveness Conflict Risk	The deadlock niche is fairly specific, but the description never qualifies it as 'database' deadlocks, so 'detect/resolve deadlocks' could overlap with thread or OS-level deadlock skills, fitting 'somewhat specific but could still overlap'.	2 / 3
	Total	9 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/database/database-deadlock-detector/skills/detecting-database-deadlocks/SKILL.md
Commit: c4eafaf

Reviewed: 5 days 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.