Kilo-Kit

Overview Schema Source Related Servers Discussions Admin

Record Learning Reflection & Self-Improvement

kilo_record_reflection

Records correct approaches, pitfalls, skill ratings, and lessons learned in SQLite so Kilo-Kit can improve across sessions.

Instructions

Record correct approaches, wrong paths/pitfalls encountered, skill ratings, and lessons learned into SQLite to drive Kilo-Kit's continuous self-improvement across sessions.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "taskMode": "<taskMode>",
      "taskSummary": "<taskSummary>",
      "correctApproach": "<correctApproach>",
      "wrongPathsEncountered": "<wrongPathsEncountered>",
      "lessonsLearned": "<lessonsLearned>"
    },
    "name": "kilo_record_reflection"
  }
}

Input Schema

Name	Required	Description	Default
`format`	No		markdown
`taskMode`	Yes	Task mode (e.g. 'bug', 'architecture', 'ui', 'feature-build').
`sessionId`	No	Optional session ID.
`taskSummary`	Yes	Summary of the problem solved.
`lessonsLearned`	Yes	Key invariant or takeaway for future tasks.
`correctApproach`	Yes	The successful strategy, fix, or architectural pattern used.
`skillsEvaluated`	No	Ratings and feedback for specific skills used.
`autoSynthesizeSkill`	No	Hermes-inspired: If true, automatically synthesize this reflection into a reusable SKILL.md in skills/learned/
`wrongPathsEncountered`	Yes	Mistakes, wrong assumptions, or pitfalls encountered.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.9.1Oct 25, 2026

addedInput schema / properties / autoSynthesizeSkill

Added value: +{
+  "description": "Hermes-inspired: If true, automatically synthesize this reflection into a reusable SKILL.md in skills/learned/",
+  "type": "boolean"
+}

First observedv0.1.0Sep 13, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and the description is consistent with them (it records/writes). It adds that data lands in SQLite and persists across sessions, which is useful, but says nothing about overwrite behavior, duplicate handling, or side effects of autoSynthesizeSkill writing a SKILL.md.

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?

A single front-loaded sentence that packs purpose, content, storage, and rationale with no wasted clauses. Efficient, though the dense enumeration slightly burdens readability.

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 9-parameter mutation tool with no output schema, the description covers intent and content categories but omits when to invoke it versus siblings, what autoSynthesizeSkill actually produces, and whether repeated calls create duplicates. Adequate but with clear gaps.

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 89%, so the schema already explains nearly every field. The description enumerates the same categories (approaches, wrong paths, ratings, lessons) without adding format, relationship, or edge-case guidance (e.g., how skillsEvaluated interacts with autoSynthesizeSkill). Baseline 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?

Specific verb (Record) plus a clear set of resources (correct approaches, wrong paths, skill ratings, lessons learned) and a storage target (SQLite). It doesn't explicitly distinguish itself from sibling tools like kilo_remember_fact or kilo_synthesize_skill, which is what keeps it from a 5.

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

Usage Guidelines3/5

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

The phrase 'across sessions' and 'continuous self-improvement' imply when the tool matters, but there is no explicit when-to-use, no when-not-to-use, and no mention of how it relates to kilo_remember_fact or kilo_synthesize_skill. Usage is left to inference.

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