Skip to main content
Glama
permanu

SuperSkill

by permanu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

learn

Destructive

Capture discoveries from AI sessions and query them later with add or list actions, storing notes per project so agent context persists across sessions.

Instructions

Capture and query learnings. Learnings persist discoveries across sessions. Stored as individual files in projects//learnings/.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagNoFilter learnings by tag (for list)
tagsNoTags
limitNoMax items for list (default 50, cap 500)
titleNoLearning title (required for add)
actionYesLearning action
sourceNoSource tool
projectNoProject slug (auto-detected if omitted)
discoveryNoWhat was discovered (required for add)
confidenceNoConfidence level (default medium)
session_idNoSession ID that captured this learning
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. Changed1 schema field changedv0.15.1
    • 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. Changed1 schema field changedv0.13.0
    • addedInput schema / properties / limit
      Added value: +{
+  "description": "Max items for list (default 50, cap 500)",
+  "type": "number"
+}
  3. First observedv0.6.1

TDQS

B3.2/5.0
Behavior3/5

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

The destructiveHint=true annotation is not contradicted; the description corroborates that this tool writes state by stating learnings are 'stored as individual files in projects/<slug>/learnings/'. It adds the persistence model and storage location beyond the annotation, but says nothing about reversibility, permissions, or how add vs list differ behaviorally.

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

Conciseness4/5

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

Three compact sentences with the core purpose front-loaded and no filler. The final storage-path sentence is slightly more implementation detail than selection aid, which keeps it short of a 5.

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 an 11-parameter tool with only one required field and no output schema, the description is thin: it does not explain the two action modes ('add' vs 'list'), what add persists, or what list returns. The schema covers parameters, but behavioral completeness for a multi-action tool is only partially met.

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 all 11 parameters, including the action enum and requireds for add. The description adds no parameter-level detail (e.g. how tag differs from tags, or what the action values return), so the baseline of 3 applies.

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?

The description names specific verbs and a resource: 'Capture and query learnings', and adds scope with 'persist discoveries across sessions' and the storage location. It is clear what the tool does, but it never distinguishes itself from plausible siblings such as capture, decide, knowledge_rebuild, or search, so an agent must infer the boundary.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named. The persistence sentence implies the intended context (recording discoveries across sessions), but any routing decision against sibling tools like capture, decide, or knowledge_rebuild is left entirely to inference.

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