evo-engineering
Evolution Engineering plugin and skill for recursive self-improvement of documents, code, and skills via multi-agent proposal, isolation, critique, and champion selection.
Install
$ dsh plugin --profile web add "github:vlln/evo-engineering#main" # 装Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Workspace initialization and baseline snapshotting via /evo init and evo_init
- Multi-agent iterative refinement with isolated actors and independent critics via /evo round and evo_round
- Regression probing and ledger tracking to protect baseline quality across improvement rounds
- Round history tracking and champion evaluation via /evo status and evo_status
- Safe workspace-level rollback to previous checkpoints via /evo rollback and evo_rollback
- Portable evo skill specification for cross-harness execution
Useful For
- Iteratively improving prompts, skills, documentation, or code using structured multi-agent competition and scoring
- Evaluating candidate implementations against strict evaluation criteria without actor collusion
- Guarding against regression while evolving critical codebase assets or instructions
Who It Fits
- DeepSeek Harness developers and agent engineers needing structured, reproducible iterative self-improvement pipelines
- Teams seeking automated multi-agent peer review and champion selection for generated artifacts
Documented Limitations
- Requires the host profile to provide the official workflowEngine service to run workflow scripts
- Actor sub-agents resolve paths based on their own cwd, requiring post-round workspace absorption
- Small score differentials may represent evaluation noise rather than deterministic improvement
- Vague evaluation criteria trigger human escalation (needsHuman) by design
- Execution cost scales by round according to the number of proposals, actors, and critics
- Operations are strictly bounded to the configured workspace directory
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- vlln/evo-engineering
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 1831393 · 2026-09-24
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 1GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-21
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →Multi-agent team collaboration plugin for DeepSeek Harness enabling coordinated sub-agents, dependency-aware task graphs, and web UI monitoring.
View plugin →