Skip to main content

Skill Evolution

Myrm’s Skill Evolution engine automatically turns your successful interactions into reusable skills. Unlike simple prompt storage, the engine runs a full pipeline: trace analysis → extraction → screening → sandbox validation → LLM review → human approval via GUI.

How it works

  1. Trace Analysis — After each conversation, the TraceAnalyzer extracts execution trajectories using 5-level progressive disclosure, identifying patterns worth turning into skills.
  2. Structured Extraction — The StructuredExtractor uses an LLM to capture skill definitions with confidence scores, ensuring only high-quality patterns are promoted.
  3. Automatic Screening — Low-quality or duplicate extractions are filtered before reaching you.
  4. Sandbox Validation — Candidate skills are executed in a safe sandbox environment to verify they actually work.
  5. LLM Review — An automated reviewer checks for edge cases, security issues, and correctness.
  6. Human Approval — Nothing deploys without your say-so. Review in the Pending Evolutions Dashboard.

Review pending skills

  1. Go to Settings → Skills → Pending Evolutions.
  2. Browse proposals in List or Grid view.
  3. For each proposal:
    • Approve — Deploy the skill immediately.
    • Reject — Discard the proposal.
    • Revise — Edit the skill in a Monaco diff editor before approving.
  4. Approved skills become available to the Agent in future conversations.

Variant testing

When Myrm detects a skill could be improved, it generates variants and runs A/B comparisons. You can review variant results in the Shadow GUI panel before promoting a variant to production.

Version history & rollback

Every skill change is tracked:
  • History panel — Full evolution timeline with diffs.
  • Versions panel — Compare any two versions side by side.
  • One-click rollback — Revert to any previous version instantly.

Batch optimization

For large skill libraries:
  1. Go to Settings → Skills → Batch Optimization.
  2. Click Run Optimization — the engine evaluates all skills for improvement opportunities.
  3. Review the batch snapshot and approve/reject changes individually.
  4. Mid-batch rollback is supported if something goes wrong.

Background review

Myrm runs 4 types of background async tasks during idle sessions:
  • Silent skill extraction from successful interactions
  • Compression of verbose skills for lower token usage
  • Frustration detection → automatic fix variant generation
  • Pruning of low-quality skills
All background changes still require your approval before deployment.

Per-session skill scope

When your Agent Profile has many skills bound, not every skill is relevant to every conversation. Per-session skill scoping lets you visually select which skills to load for the current chat, reducing token consumption and improving AI focus.
  1. Open any chat in Agent mode.
  2. Click the sparkle icon (✦) next to the message input — the Session Skills toggle.
  3. A popover lists all globally enabled skills. Uncheck skills you don’t need for this conversation.
  4. Your selection is persisted server-side and survives page reloads, conversation compaction, and even conversation forks.
  5. To restore all skills, click Clear Override at the top of the popover.
When you switch to a different Agent, the session skill override is automatically cleared — so you always start fresh with the new Agent’s full skill set.

Built-in prebuilt skills

Beyond self-evolving skills, Myrm ships with 36+ prebuilt skills ready to use out of the box. Notable examples:
  • Data Analysis — A six-phase workflow (Ingest → Clean → Explore → Analyze → Visualize → Report) with automatic data quality checks and risk alerts. Supports CSV, JSON, Excel, and database queries.
  • Data Analysis Pipeline — Multi-agent version: four specialized roles (Collector → Analyst → Visualizer → Reporter) collaborate in parallel. Outputs HTML reports, PDF, Jupyter Notebooks, Markdown, or PPT outlines.
  • Deep Research — Multi-step web research with source verification.
  • Code Review — Automated code review with security and performance checks.
  • Frontend Development, Test-Driven Development, Systematic Debugging — Development workflow skills.
Prebuilt skills are automatically synced on startup and can be customized, disabled, or reset to defaults via the Settings GUI.
Matplotlib charts render inline with zero-copy vault:// pointers — no Jupyter server required. This gives you Jupyter-quality visualization without the infrastructure overhead.

Key numbers

MetricValue
Evolution engine tests385 passed
Safety layers15 (Harness 6 + Server 6 + Service 3)
Patch formats3 (fuzzy match with 8-level progressive + Unicode normalization)
Routing strategies4 (including Correction Propagation)
Background task types4

Skill marketplace

Myrm integrates 7 discovery sources in a unified GUI — search, filter by tags, sort by stars/downloads, preview with security scan, and install with one click:
SourceCoverage
ClawHubLargest open skill marketplace
GitHubPublic skill repositories
LobeHubLobeChat plugin ecosystem
ModelScope80K+ Chinese AI community models/skills
AliyunAlibaba Cloud Agent Explorer
skills.shCurated skill directory
Prebuilt36+ built-in skills shipped with Myrm
Additional marketplace capabilities:
  • URL Import — Install from any URL (GitHub repo, ZIP archive, etc.)
  • Auto-update — Checks for upstream updates with quarantine-based safe update flow
  • Skill Sync — Push/pull synchronization across devices
  • Curator — Automatic lifecycle management (stale detection, archive, cleanup)
  • Consolidation — Merges duplicate or overlapping skills automatically
  • Export with Redaction — Download skills as ZIP with automatic secret stripping

vs competitors

CapabilityMyrmHermes
Auto-extract skillsFull pipelineSingle CLI command
Sandbox validationYesNo
GUI review dashboardYesNo (auto-applies)
Confidence scoringYesNo
Variant A/B testingYesNo
Version rollback GUIYesCLI only
Background optimizationYes (4 types)Basic
Cross-agent experience sharingYesNo
One-click extract from chatYes (message-level button)No
Skill retrieval layers3-layer (semantic+env hybrid, deterministic scorer, progressive loading)2-layer (semantic search, playbook synthesis)
Execution transparencyFull (skill badges + reason + tool chain + error diagnostics)Partial (tool list only)
Marketplace sources7 integrated sources3 (ClawHub + GitHub + custom tap)
Marketplace UIFull GUI (search/filter/sort/install)CLI only
Auto lifecycle managementCurator (stale/archive/cleanup via Settings + Smart Prune — not chat-only text suggestions)Manual
Skill consolidationAuto-merge duplicatesNo
Per-session skill scopeVisual toggle (pick skills per chat, ~1800 tokens/turn saved)No