Conciseness

The ~30-line body is lean with no padding and no explanation of concepts Claude already knows (e.g., no "what is MCP" preamble); every sentence is a Memcode/DeepChat-specific directive such as "Do not pass a caller-chosen user ID. The server identifies the user from the OAuth credential." This matches the anchor for lean, efficient content where every token earns its place, not the 4 anchor which requires instances of over-explanation to trim.

Actionability

Concrete, executable guidance throughout: named tools ("save_memory", "get_memory_ingest_status", "search_memories", "retrieve_answer"), a specific server URL, a menu path ("Plugins > Memcode"), and explicit conditions ("use get_memory_ingest_status before claiming it was stored"). It falls at anchor 4 rather than 5 because no example invocations or parameter shapes are shown for the MCP tools — a minor gap for an otherwise actionable instruction-only skill.

Workflow Clarity

The save flow has an explicit validation checkpoint ("use get_memory_ingest_status before claiming it was stored") with a feedback loop ("Report a partial or failed ingest as such"), the recall flow handles the empty case ("Say when no relevant memory was found"), and a failure-recovery path covers a disabled or failing connection. This matches the anchor for a clear sequence with explicit validation steps and error-recovery loops; no destructive or batch operations apply, so no cap is triggered.

Progressive Disclosure

The skill is under 50 lines, has no need for external reference files (none exist in the bundle), and is organized into clear sections (connection setup, Save, Recall, failure handling). Per the simple-skill guideline, this scores 5 with well-organized sections alone.

Specificity

The description names the domain ("Memcode MCP connection", "DeepChat conversations") and exactly two concrete actions ("explicitly save approved facts" and "recall relevant memories"), which matches the anchor for naming a domain with 1-2 concrete actions but not comprehensive coverage. It is not a 4 because it does not list several specific actions — the save/recall pair exhausts the stated capabilities.

Completeness

The "what" is clear ("explicitly save approved facts and recall relevant memories across DeepChat conversations"), but there is no "Use when..." clause or equivalent explicit trigger guidance — "explicitly" and "Never... automatically" are constraints, not triggers. Per the guideline that a missing 'Use when' clause caps completeness at 3, this cannot score higher.

Trigger Term Quality

Relevant keywords are present ("save", "recall", "memories", "facts", "Memcode", "DeepChat"), but common natural user phrasings such as "remember this", "my notes", or "what did I tell you" are missing. This fits the anchor for some relevant keywords missing common variations or synonyms, rather than the good-coverage anchor at 4.

Distinctiveness Conflict Risk

"Memcode MCP connection" and "DeepChat conversations" anchor a clear, named niche, giving mostly distinct triggers. It is not a 5 because the underlying capability phrasing ("save... facts and recall... memories") has minor overlap risk with other memory or note-taking skills.