Skip to main content
Glama
permanu

SuperSkill

by permanu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

extract

Destructive

Split a source document into separate vault files, each holding one decision, learning, or item with a backlink to its origin.

Instructions

Extract decisions, learnings, or other items from a source document into individual vault files. Each extracted item gets its own file with a backlink to the source.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYesItems to extract from the source document
sourceYesRelative path to the source vault note
projectNoProject slug (auto-detected if omitted)
workspace_pathNoAbsolute thread workspace directory; must map to this project. Omit only when the server cwd is the thread workspace.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.15.1
    • addedInput schema / properties / items / items / additionalProperties
      Added value: +false
    • addedInput schema / properties / workspace_path
      Added value: +{
+  "description": "Absolute thread workspace directory; must map to this project. Omit only when the server cwd is the thread workspace.",
+  "type": "string"
+}
  2. First observedv0.6.1

TDQS

B3.3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare destructiveHint=true, so the description usefully adds that output is one file per item with a backlink to the source. However it never explains what is destructive about the operation (e.g. overwriting existing files or mutating the source), leaving the flagged risk unexplained. Some added context, but a notable gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, purpose front-loaded, and the second sentence carries genuine output-structure information rather than padding. No waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-param mutation tool with destructiveHint and no output schema, the description covers purpose and output shape but omits what destructive behavior to expect and what the call returns (counts, paths). Complete enough to attempt the call, but leaves the risk profile and return unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents source, items, project, and workspace_path. The description only maps loosely to 'source document' and output files, adding no syntax, format, or constraint detail beyond what the schema provides. Baseline 3 for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (extract) and resource (decisions, learnings, items) plus the output shape (individual vault files with a backlink). An agent can tell it transforms one source note into many item files, distinct from single-item siblings like decide or learn. It doesn't explicitly name the alternatives it competes with, so it stops short of 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description says what happens but never when to choose extract over decide, learn, or capture, nor any prerequisite such as needing a source note to exist. No exclusions or trigger conditions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools