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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and concise, with executable SQL and specific error codes for PostgreSQL and MySQL. Its weaknesses are the absence of explicit validation checkpoints in the database workflow and a monolithic structure that ignores the bundled scripts and references.

Suggestions

Add explicit validation/verification checkpoints to the workflow — after applying a lock-ordering or isolation-level fix, verify the deadlock no longer reproduces by re-running the step-1/step-8 monitoring queries and re-checking logs. The procedure is well-sequenced but lacks the validate->fix->retry feedback loops the rubric expects for database operations.

Use progressive disclosure: the ~150-line body never points to the bundled scripts. Reference scripts/analyze_deadlocks.py for the diagnostic queries and move the Examples and Error-Handling detail into reference files rather than inlining everything.

Resolve the MongoDB scope mismatch — the Overview promises 'PostgreSQL, MySQL, and MongoDB' but the instructions only cover PostgreSQL and MySQL. Either add MongoDB diagnostic guidance or drop MongoDB from the scope statement.

Dimension	Reasoning	Score
Conciseness	The body is dense with specifics (executable SQL, error codes 40P01/1213, concrete patterns) and avoids explaining concepts Claude already knows; every section earns its place despite the length, matching the 'lean and efficient' anchor; not a 2 because there is no basic-concept padding and the redundancy between steps and examples reinforces rather than merely repeats.	3 / 3
Actionability	Step 1 gives full copy-paste SQL for PostgreSQL and MySQL, step 2 gives 'SHOW ENGINE INNODB STATUS\G', and steps 5/7/9 give specific error codes, retry counts, and function names, matching 'fully executable code/commands; copy-paste ready'; not a 2 because the guidance is concrete rather than pseudocode.	3 / 3
Workflow Clarity	The ten steps are clearly sequenced, but there are no explicit validation/verification checkpoints (e.g., confirm the deadlock no longer reproduces after a fix), and only step 7's retry offers a feedback loop; per the rubric, missing validation in a database-operation workflow caps this at 2; not a 3 because checkpoints are implicit/absent, and not a 1 because the sequence itself is clear.	2 / 3
Progressive Disclosure	The body is well-organized into sections but is effectively monolithic (~150 lines all inline) and never references the bundled scripts/ or references/ files (e.g., scripts/analyze_deadlocks.py), matching 'some structure but content that should be separate is inline'; not a 3 because the >50-line skill with bundle files fails the well-organized-sections escape, and not a 1 because sections are clearly organized rather than a disorganized wall.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 clearly states a distinct niche and includes explicit, natural trigger phrases that answer both 'what' and 'when'. Its main weakness is specificity, where a fluffy 'comprehensive guidance and automation' phrase replaces a concrete enumeration of capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and two actions ('deadlock detection and resolution') but pads with vague fluff ('comprehensive guidance and automation') rather than listing multiple concrete capabilities, matching the 'names domain and some actions, but not comprehensive' anchor; not a 3 because it lacks a comprehensive set of specific actions like the PDF example.	2 / 3
Completeness	Answers both what ('deadlock detection and resolution') and when (an explicit 'use when you need to work with deadlock detection' clause plus a 'Trigger with phrases like' list); not a 2 because the explicit 'Use when' trigger guidance is present rather than merely implied.	3 / 3
Trigger Term Quality	Explicit trigger phrases 'detect deadlocks', 'resolve deadlocks', 'prevent deadlocks' are natural terms a user would actually say, giving good coverage of natural phrasings; not a 2 because the enumerated phrases go beyond a single generic keyword.	3 / 3
Distinctiveness Conflict Risk	The database-deadlock niche with distinct triggers (detect/resolve/prevent deadlocks) is clearly distinguishable and unlikely to fire for unrelated skills; not a 2 because the triggers are specific enough to avoid overlap with generic database skills.	3 / 3
	Total	11 / 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
Commit: 2cafb23

Reviewed: 2 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.