Ext Ops Panel
Open dashboard
Comparison

compounded vs skillmem

compounded is a plugin bundle for AI coding tools published by ankitkr3. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). skillmem is an MCP server published by liza-studio. Marketplaces we read that list it: 2 (Official MCP Registry, Community GitHub marketplaces). As of our marketplace pass on 2026-10-14. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplacecompoundedskillmem
Claude Code: claude-plugins-community Listed
Version: 9feb758
Forks (GitHub): 0
Stars (GitHub): 5
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 0.12.1
Downloads/month (PyPI): 4 269
Downloads/week (PyPI): 112
Forks (GitHub): 4
Stars (GitHub): 9
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

compounded vs skillmem
Factcompoundedskillmem
Marketplaces that list it (differs)1 (worse)2 (better)
Stars (GitHub) (differs)5 (worse)9 (better)
Forks (GitHub) (differs)0 (worse)4 (better)
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleOn your machine (skillmem)
Transport (differs)Not statedstdio
Tools it declaresNot publishedNot published
Environment variables it asks for (differs)Not published1, secrets among them: 0
Hooks it runs (differs)48
Parts of the bundle (differs)187
Licence (differs)MITApache-2.0
Repository (differs)github.com/ankitkr3/compoundedgithub.com/liza-studio/skillmem
Changes in the last 7 days (differs)02
First seen2026-10-112026-10-11

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

compounded

In its own words, on Claude Code: claude-plugins-community:

compounded turns Claude Code skills into a trust-gradient system: every skill earns its autonomy through demonstrated reliability. New skills the agent proposes start as .proposed/, get replayed on a real follow-up task by a verifier subagent (Haiku 4.5) to graduate to .verified/, build a track record to reach .trusted/, and finally graduate to .autonomous/ after 10+ uses with a clean recent run. One correction sends a skill back a tier. Three corrections in 30 days drop it to .proposed. Includes cross-project memory (a user-global USER.md auto-injected into every session) and a portable .tar.gz archive for moving your earned skills across machines. v1.1 adds an auto-proposer hook that scores each turn (tool calls, distinct file edits, recovery from failure) and nudges the agent to save high-signal procedures — so you don't have to remember to ask. No daemon. No cloud. No telemetry. Python stdlib only. All state in ~/.claude/compounded/ (SQLite + flat files). MIT licensed.

skillmem

In its own words, on Official MCP Registry:

Skill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.

How to run each

compounded As a Claude Code plugin

Claude Code
/plugin marketplace add anthropics/claude-plugins-community
/plugin install compounded@claude-community

skillmem As a local MCP server: PyPI package

Claude Code
claude mcp add --transport stdio skillmem -- uvx skillmem mcp

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

The marketplaces of compounded publish no settings it asks for, so we do not compare settings.

What it can do: compounded · What it can do: skillmem · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built