continual-learning — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited continual-learning (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Your agent forgets everything between sessions. Continual learning fixes that.
Experience → Capture → Reflect → Persist → Apply
↑ │
└───────────────────────────────────────┘Install the hook (one step):
cp -r hooks/continual-learning .github/hooks/Auto-initializes on first session. No config needed.
Global (~/.copilot/learnings.db) — follows you across all projects:
Local (.copilot-memory/learnings.db) — stays with this repo:
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 approachThe 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
For human-readable, version-controlled knowledge:
# .copilot-memory/conventions.md
- Use DefaultAzureCredential for all Azure auth
- Parameter is semantic_configuration_name=, not semantic_configuration=Learnings decay over time:
This prevents unbounded growth while preserving what matters.
cp -r, it won't get adopted"Use semantic_configuration_name=" beats "use the right parameter"~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.