writer-memory

Agentic memory system for writers - track characters, relationships, scenes, and themes

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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 commands and examples, but it is verbose and monolithic, repeating command listings and embedding a large storage schema inline rather than offloading it to reference files. Tightening redundancy and adding explicit validation checkpoints in the main workflow would raise the weaker dimensions.

Suggestions

Move the full storage-schema JSON and detailed per-type field tables into reference files (e.g. SCHEMA.md, MEMORY-TYPES.md) and link to them from SKILL.md to reduce inline bulk.

Deduplicate command listings: keep the command table as the canonical reference and have the Full Workflow example reference steps rather than re-listing every command.

Add explicit validation checkpoints to the main workflow (e.g. run '/writer-memory status' after init and '/validate' before finalizing dialogue) to turn the implicit safety nets into a clear feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is well-structured and mostly reference material rather than concept explanation, but it is long with redundancy: commands appear in the command table, the per-type sections, and the full-workflow example, and the full storage-schema JSON could be trimmed.	2 / 3
Actionability	It provides concrete executable commands throughout ('/writer-memory char add <name>', field updates, validate, query) with copy-paste-ready examples and expected outputs, matching the anchor for fully actionable guidance.	3 / 3
Workflow Clarity	The Full Workflow is clearly sequenced and safety nets exist (auto-backup, /status, /validate), but the main flow lacks explicit inline validation checkpoints and memory writes are state-modifying, which caps workflow clarity at 2 per the scoring notes.	2 / 3
Progressive Disclosure	Sections are well-organized, but no bundle/reference files exist and the skill is monolithic: the storage schema, detailed field tables, and troubleshooting are inline content that could be split into separate reference files, so it does not reach anchor 3.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 conveys a clear domain and the objects it manages, but it is missing an explicit usage trigger and leans on a single generic verb plus the buzzword 'Agentic'. Adding a 'Use when...' clause and more concrete, varied action verbs would lift all four dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when writing fiction and needing to keep characters, relationships, scenes, and themes consistent across sessions.'

Replace the generic verb 'track' with varied concrete actions (e.g. 'record, update, query, and validate characters, relationships, scenes, and themes').

Drop the buzzword 'Agentic' in favor of natural phrasing a writer would actually say, such as 'Memory for fiction writers'.

Dimension	Reasoning	Score
Specificity	Names the domain ('memory system for writers') and concrete objects ('track characters, relationships, scenes, and themes'), but relies on a single generic verb ('track') rather than multiple distinct concrete actions, so it does not reach anchor 3.	2 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Domain terms like 'characters', 'relationships', 'scenes', and 'themes' are natural for writers, but the description leads with the buzzword 'Agentic' and lacks common phrasing variations, keeping it below anchor 3.	2 / 3
Distinctiveness Conflict Risk	The fiction-writer niche is fairly distinct, yet the generic 'memory system' framing could overlap with other memory or note-taking skills and there are no explicit triggers to disambiguate.	2 / 3
	Total	8 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Commit: 6c59219

Reviewed: about 7 hours 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.