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

76%

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 ./src/orchestrator/skills/agent-memory/SKILL.md

Quality

Content

65%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.

A tight, actionable protocol body with concrete shell commands and explicit validation checkpoints for its batch file mutations. The two gaps are a missing explicit error-recovery loop in the workflow and a dangling reference to KNOWLEDGE-GRAPH.md, which is not present alongside the skill.

Suggestions

Add an explicit error-recovery loop (e.g., "If the rg pruning check still shows stale paths, re-run pruning and re-validate") to raise workflow clarity from a clear sequence to a self-correcting one.

Either ship the referenced KNOWLEDGE-GRAPH.md alongside SKILL.md or remove/inline the reference so progressive-disclosure navigation does not dead-end.

Dimension	Reasoning	Score
Conciseness	Lean, table-driven body with no padding or explanations of concepts Claude already knows; every section (entry format, update triggers, retrieval, pruning) earns its place with dense, purposeful content.	5 / 5
Actionability	Provides copy-paste-ready, executable commands — the grep retrieval, printf append, awk familiarity increment, and rg pruning check — covering the common update/retrieval cases concretely.	5 / 5
Workflow Clarity	A dedicated Validation Checkpoints section supplies before-delegating, after-completion, and after-pruning checks (satisfying the batch/destructive validation requirement), but there is no explicit "if validation fails, fix and re-run" error-recovery loop and the end-to-end sequence is organized by topic rather than as a numbered flow.	4 / 5
Progressive Disclosure	Well-organized into clear sections with a clearly signaled one-level-deep reference ("See [KNOWLEDGE-GRAPH.md](./KNOWLEDGE-GRAPH.md)"), but that referenced file does not exist in the bundle, leaving a broken navigation path.	4 / 5
	Total	18 / 20 Passed

Description

88%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.

A strong, third-person description that names concrete capabilities and provides explicit, natural use-when triggers covering delegation and task-assignment scenarios. The main weakness is occasional internal jargon that slightly blunts the natural trigger terms and a modest overlap risk with adjacent agent-management skills.

Suggestions

Soften internal jargon ("file-familiarity counters", "task-area match") into phrasings a user would actually say, or pair each with a plain-language synonym.

Add a disambiguating cue that separates this skill from generic agent-memory or task-tracking skills (e.g., emphasize the AGENT-EXPERTISE.md file as the unique source of truth).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Creates, queries agent expertise profiles", "increments file-familiarity counters", "ranks candidate agents by recency, task-area match" — giving comprehensive coverage rather than generic language.	5 / 5
Completeness	Explicitly states what it does (creates/queries profiles, increments counters, ranks agents) and when to use it ("Use when deciding which agent should handle a file... recording task outcomes, or assigning work based on past performance") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural triggers ("deciding which agent should handle a file", "who last worked on a module", "assigning work based on past performance"), but interleaved with internal jargon ("file-familiarity counters", "task-area match") a user would not naturally say, leaving a few natural synonyms uncovered.	4 / 5
Distinctiveness Conflict Risk	A clear niche (agent expertise/delegation memory) with distinct triggers, but "agent expertise profiles" could overlap with sibling agent-management or memory skills, so minor overlap risk remains.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/agent-memory/SKILL.md
Commit: fa0c341

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.