CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./encyclopedia/scripts/anime-mori/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The body is an efficient, well-sectioned overview with concrete commands and a clear architecture diagram. It falls short on execution guidance: no sequenced getting-started workflow, no validation/verification checkpoint, and five of eight CLI commands lack invocation examples, with the full documentation pointer buried rather than clearly signaled.

Suggestions

Add a short "Quick start" sequence, e.g. 1. `npx anime-mori learn ./my-project` 2. verify with `npx anime-mori status` 3. `npx anime-mori server` to connect your AI tool — this supplies both sequence and a validation checkpoint.

Give the remaining commands (analyze, insights, patterns, predict, status) one-line `npx` invocation examples like the first three have.

Move setup/integration details and the 13-tool breakdown into a reference file (or clearly link the README with setup steps) and reference it prominently near the top instead of burying it in the Files list.

DimensionReasoningScore

Conciseness

The body is mostly lean (compact tables, short command blocks, tight file listing), with only minor trimmable padding: the tagline quote and the "solves session amnesia" paragraph restate a problem Claude can infer from the description. Matches anchor 4 (efficient, minor over-explanation); not 5 due to that marketing-flavored padding, not 3 because the excess is isolated rather than pervasive.

4 / 5

Actionability

Three commands (learn, server, search) ship executable `npx anime-mori` invocations and tool names are concrete. Not 5: five commands (analyze, insights, patterns, predict, status) get only one-line descriptions with no invocation examples, and setup/integration steps for connecting the MCP server to an AI tool are absent.

4 / 5

Workflow Clarity

Commands are listed individually with no explicit sequence (learn, then start server, then integrate) and no validation checkpoints; `status` exists but is never framed as a verify step. Matches anchor 3 (steps listed, checkpoints missing or implicit); not 2 because concrete commands and a rough implicit order exist, not 4 because nothing signals when to check health or confirm learning succeeded.

3 / 5

Progressive Disclosure

Sections are well-labeled, but the only external reference ("README.md — Full documentation with setup guides") is weakly signaled at the bottom of the Files list, the 13-tool table and per-command details are inlined where a reference file could carry them, and no bundle files (references/, scripts/) exist to back the listed src/ and rust-core/ paths. Matches anchor 3 (structure present, references not clearly signaled, content that could be separate is inline).

3 / 5

Total

14

/

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 communicates a clear, fairly specific capability set in third person, with good technical distinctiveness. Its main weaknesses are the complete absence of "when to use" trigger guidance and a jargon-heavy vocabulary that underuses the natural phrases a user would say when needing persistent codebase memory.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user wants the AI to remember their codebase across sessions, mentions codebase memory/conventions, or asks for semantic code search or coding-pattern predictions."

Swap some jargon for natural synonyms: add plain terms like "remembers your code between chats" and "codebase memory" alongside "tree-sitter" and "MCP server".

Clarify the vague capability "file routing" (what does it route, and for whom?) or drop it in favor of a more self-explanatory action.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Learns patterns, conventions, and architecture", "semantic search, pattern prediction, file routing, and project blueprints") with concrete technical grounding (tree-sitter, 12 languages, 13 tools). Not 5 because the abstract opener "Persistent codebase intelligence" and unexplained "file routing" leave minor coverage gaps; not 3 because it goes well beyond 1-2 actions.

4 / 5

Completeness

The "what" is clear (learns and persists codebase patterns; 13 MCP tools for search, prediction, routing, blueprints), but there is no "Use when..." clause or any equivalent trigger guidance, capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Contains some relevant natural keywords (codebase, patterns, conventions, architecture, semantic search) but is weighted toward technical jargon ("tree-sitter AST parsing", "MCP server") and misses natural user phrasings like "remembers my code", "forgets between sessions", or "codebase memory". Matches anchor 3: relevant keywords present, common variations/synonyms missing.

3 / 5

Distinctiveness Conflict Risk

Specific technical framing (tree-sitter AST parsing across 12 languages, 13 MCP tools, cross-session persistence) carves a fairly distinct niche with only minor overlap risk against generic code-search or indexing skills. Not 5 because the trigger surface isn't explicit enough to fully disambiguate from adjacent codebase-analysis skills.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.