Index of every page on this site: llms.txt
All skills
microsoft avatar

/continual-learning

@0d60658
by microsoftmicrosoft/skills3.2k stars
373
Run it yourself

Guide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up learning infrastructure for agents.

Use this Skill: https://skilld.dev/gh/microsoft/skills/continual-learning

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈46 tokens for metadata: the name and description. ≈595 when used: this file.

Description uses 2.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈184 characters, or 2.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Continual Learning for AI Coding Agents

Your agent forgets everything between sessions. Continual learning fixes that.

The Loop

Experience → Capture → Reflect → Persist → Apply
     ↑                                       │
     └───────────────────────────────────────┘

Quick Start

Install the hook (one step):

cp -r hooks/continual-learning .github/hooks/

Auto-initializes on first session. No config needed.

Two-Tier Memory

Global (~/.copilot/learnings.db) — follows you across all projects:

  • Tool patterns (which tools fail, which work)
  • Cross-project conventions
  • General coding preferences

Local (.copilot-memory/learnings.db) — stays with this repo:

  • Project-specific conventions
  • Common mistakes for this codebase
  • Team preferences

How Learnings Get Stored

Automatic (via hooks)

The hook observes tool outcomes and detects failure patterns:

Session 1: bash tool fails 4 times → learning stored: "bash frequently fails"
Session 2: hook surfaces that learning at start → agent adjusts approach

Agent-native (via store_memory / SQL)

The agent can write learnings directly:

INSERT INTO learnings (scope, category, content, source)
VALUES ('local', 'convention', 'This project uses Result<T> not exceptions', 'user_correction');

Categories: pattern, mistake, preference, tool_insight

Manual (memory files)

For human-readable, version-controlled knowledge:

# .copilot-memory/conventions.md
- Use DefaultAzureCredential for all Azure auth
- Parameter is semantic_configuration_name=, not semantic_configuration=

Compaction

Learnings decay over time:

  • Entries older than 60 days with low hit count are pruned
  • High-value learnings (frequently referenced) persist indefinitely
  • Tool logs are pruned after 7 days

This prevents unbounded growth while preserving what matters.

Best Practices

  1. One step to install — if it takes more than cp -r, it won't get adopted
  2. Scope correctly — global for tool patterns, local for project conventions
  3. Be specific — "Use semantic_configuration_name=" beats "use the right parameter"
  4. Let it compound — small improvements per session create exponential gains over weeks

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning2mo5 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    This skill provides documentation and infrastructure patterns for implementing memory persistence in AI agents. It includes instructions for setting up hooks and managing local and global memory files to improve agent performance over time.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

  • Runlayer8mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 0d60658. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 9 months ago

README badge

README badge for microsoft/skills/continual-learning