agent-memory

Creates, queries agent expertise profiles in AGENT-EXPERTISE.md; increments file-familiarity counters after each task; ranks candidate agents by recency, task-area match. Use when deciding which agent should handle a file, checking who last worked on a module, recording task outcomes, or assigning work based on past performance.

Quality

96%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

92%

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

This is a well-crafted skill that provides concrete, executable guidance for managing agent expertise profiles. Its strengths are the actionable shell commands, clear trigger-action table, and explicit validation steps at each workflow stage. The main weakness is the reference to KNOWLEDGE-GRAPH.md without it being available in the bundle, and the inline awk command is somewhat heavy for the main skill file.

Suggestions

Include the referenced KNOWLEDGE-GRAPH.md in the bundle or remove the reference to avoid broken navigation

Consider extracting the awk familiarity-increment script into a standalone shell script referenced from the skill, improving readability

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. It avoids explaining what agent expertise tracking is or why it matters, jumping straight into the file format, triggers, and commands. Every section earns its place with no padding or unnecessary explanation.	3 / 3
Actionability	Provides fully executable shell commands for querying (grep), appending entries (printf), and incrementing familiarity counters (awk). The update triggers table is concrete with specific thresholds (2+ retries, >3 months). The example prompt block gives a copy-paste ready template.	3 / 3
Workflow Clarity	The workflow section has a clear 3-step sequence (before delegating, after task, on failure) with explicit validation checkpoints at each step. Each step includes what to validate (e.g., 'expertise file contains new entry; timestamp is today's date'), and the pruning section also includes a validation command.	3 / 3
Progressive Disclosure	References KNOWLEDGE-GRAPH.md appropriately as a one-level-deep reference, but the bundle doesn't include this file, making it unverifiable. The content is reasonably structured with clear sections, but the inline awk script is quite long and could potentially be referenced as a separate utility script for better organization.	2 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong description that clearly articulates specific capabilities (creating/querying expertise profiles, incrementing counters, ranking agents), uses natural trigger terms, and includes an explicit 'Use when...' clause with multiple concrete scenarios. The description is concise, uses third-person voice throughout, and occupies a distinctive niche that would be easily distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: creates expertise profiles, queries them, increments file-familiarity counters, ranks candidate agents by recency and task-area match. These are detailed, actionable capabilities.	3 / 3
Completeness	Clearly answers both 'what' (creates/queries expertise profiles, increments counters, ranks agents) and 'when' with an explicit 'Use when...' clause covering four distinct trigger scenarios.	3 / 3
Trigger Term Quality	Includes natural trigger terms users would say: 'which agent should handle a file', 'who last worked on a module', 'recording task outcomes', 'assigning work based on past performance', 'agent expertise', 'file-familiarity'. Good coverage of how users would phrase these requests.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche: agent expertise profiling and work assignment based on file familiarity. References a specific file (AGENT-EXPERTISE.md) and domain-specific concepts like file-familiarity counters and agent ranking, making it unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: monkilabs/opencastle
Commit: 7a69a05

Reviewed: about 1 month 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.