AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Evolve

skill-hknc-claude-evolve-evolve · by hknc

Use when user says "/evolve", "manage my toolkit", "initialize toolkit", "release my changes", "switch toolkits", "toolkit status", "setup my toolkit", "sync my setup", or asks about toolkit management and cross-machine synchronization.

No reviews yet
0 installs
6 views
0.0% view→install

Install

$ agentstack add skill-hknc-claude-evolve-evolve

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-hknc-claude-evolve-evolve)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
6mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Evolve? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Claude Evolve Toolkit Management

Action

Parse subcommand and invoke appropriate agent via Task tool.

Routing

| Command | Handler | Notes | |---------|---------|-------| | /evolve | claude-evolve:evolve-toolkit-manager action=status | Show toolkit status | | /evolve init | Command wizard first | Command handles AskUserQuestion, then spawns agent | | /evolve learn | claude-evolve:evolve-learning-extractor | Auto-detects scope | | /evolve audit | claude-evolve:evolve-setup-auditor | Returns suggestions | | /evolve migrate | claude-evolve:evolve-toolkit-manager action=migrate | Copy $HOME/.claude/ content | | /evolve prepare | (use prepare-task skill) | - | | /evolve release | Command confirms first | Command uses AskUserQuestion, then spawns agent | | /evolve switch {name} | claude-evolve:evolve-toolkit-manager action=switch | Switch toolkits | | /evolve context | claude-evolve:evolve-context-detector | Analyze project | | /evolve status | claude-evolve:evolve-toolkit-manager action=status | Show status | | /evolve consolidate | claude-evolve:evolve-setup-auditor action=consolidate | Merge similar components | | /evolve signal [desc] | Bash command | Flag insight for /learn capture |

Architecture Note

Commands handle ALL user interaction. Agents CANNOT use AskUserQuestion.

For /evolve init and /evolve release, the command collects user choices via AskUserQuestion BEFORE spawning the agent. See commands/evolve.md for the full wizard flow.

Critical Rules

  • Never write to $HOME/.claude/
  • All writes go to $HOME/.claude-evolve/toolkits/{name}/ (FLAT structure)

Structure (FLAT - Toolkit IS the Plugin)

$HOME/.claude-evolve/
├── .claude-plugin/
│   └── marketplace.json              <- For Claude Code plugin discovery
├── active                            <- Current toolkit name
└── toolkits/
    └── {name}/                       <- THE PLUGIN DIRECTLY
        ├── .claude-plugin/plugin.json
        ├── .claude-toolkit/toolkit.yaml
        ├── agents/                   <- Learned agents
        ├── skills/                   <- Learned skills
        ├── rules/                    <- Learned patterns
        ├── understanding/
        │   ├── understanding.md      <- Universal user patterns (<2000 tokens)
        │   ├── observations/         <- Raw session observations with project tags
        │   │   └── YYYY-MM.yaml
        │   └── projects/             <- Project-specific patterns (SHAREABLE)
        │       ├── my-api.md         <- Can be shared with team
        │       └── web-dashboard.md
        └── history/
            ├── events.json           <- Event tracking (stats computed on-demand)
            └── archive/              <- Monthly archives

Registration: {name}-toolkit@claude-evolve-local

See ${CLAUDE_PLUGIN_ROOT}/skills/evolve/references/subcommands.md and ${CLAUDE_PLUGIN_ROOT}/skills/evolve/references/configuration.md for details.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.