anime-mori

Persistent codebase intelligence. Learns patterns, conventions, and architecture from your codebase via tree-sitter AST parsing (12 languages) and remembers across sessions. MCP server with 13 tools for semantic search, pattern prediction, file routing, and project blueprints.

Quality

63%

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 ./encyclopedia/scripts/anime-mori/SKILL.md

Quality

Content

68%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.

The body is a well-structured, mostly executable reference, but it lacks validation steps for the batch `learn` operation and leaves several commands without invocation examples.

Suggestions

Add a verification checkpoint after `learn` (e.g. run `npx anime-mori status` to confirm the codebase was indexed and check staleness).

Provide `npx` invocation examples for the remaining commands (analyze, insights, patterns, predict, status), not just learn/server/search.

Replace the generic 'README.md — Full documentation' pointer with topic-specific references (e.g. setup, tool reference, language support).

Dimension	Reasoning	Score
Conciseness	The body is mostly lean reference material (commands, tools table, file map) with only minor over-explanation such as the opening quote and the 'session amnesia' motivation sentence.	4 / 5
Actionability	Three commands ship executable `npx anime-mori ...` examples, but `analyze`, `insights`, `patterns`, `predict`, and `status` list only one-line descriptions with no invocation examples.	4 / 5
Workflow Clarity	`learn` is a batch operation that parses an entire codebase, yet there is no validation or verification step, so workflow clarity is capped at 3 per the batch-operation guideline.	3 / 5
Progressive Disclosure	Clear section structure with a one-level-deep pointer to README.md and source directories; minor gaps since the README reference is generic ('Full documentation') without per-topic navigation.	4 / 5
	Total	15 / 20 Passed

Description

58%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.

The description conveys concrete capabilities with reasonable specificity and a distinct niche, but it omits explicit 'when to use' trigger guidance and leans on technical jargon over natural user phrasing.

Suggestions

Add a 'Use when...' clause naming natural triggers (e.g. 'Use when you need persistent codebase memory across sessions, semantic code search, or pattern-based recommendations').

Swap some jargon for terms users actually say, e.g. 'remembers your project across sessions' alongside 'persistent codebase intelligence'.

Briefly state the output of the headline tools so 'file routing' and 'pattern prediction' are not left abstract.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('semantic search, pattern prediction, file routing, and project blueprints', 'tree-sitter AST parsing (12 languages)', '13 tools'), with minor gaps since it does not state what each tool produces.	4 / 5
Completeness	It clearly states what the skill does but provides no 'Use when...' trigger clause, so per the missing-trigger guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Keywords are present but technical ('codebase intelligence', 'pattern prediction') and miss the natural phrases a user would say (e.g. 'remember my codebase', 'learn my project') and any file extensions.	3 / 5
Distinctiveness Conflict Risk	The persistent-memory-plus-AST-parsing niche is mostly distinct from generic code-search skills, with only minor overlap risk.	4 / 5
	Total	14 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: Raudbjorn/cognitive-construct
Path: encyclopedia/scripts/anime-mori/SKILL.md
Commit: 319f646

Reviewed: 6 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.