#957 by GitHub stars

AVIDS2/memorix

Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.

Claude Code Gemini CLI OpenCode Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`packages/memcode/examples/extensions/dynamic-resources/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Local scripts

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills-collision/first/calendar/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills-collision/second/calendar/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/consecutive-hyphens/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/disable-model-invocation/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/invalid-name-chars/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/invalid-yaml/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/long-name/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/missing-description/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/multiline-description/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/name-mismatch/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/nested/child-skill/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/no-frontmatter/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/root-skill-preferred/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/root-skill-preferred/nested-child/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/unknown-field/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`packages/memcode/test/fixtures/skills/valid-skill/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/claude/memorix/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/claude/memorix/skills/memorix-git-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/claude/memorix/skills/memorix-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Local scripts

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/claude/memorix/skills/memorix-mini-skills/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/claude/memorix/skills/memorix-orchestrate/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/claude/memorix/skills/memorix-reasoning/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/claude/memorix/skills/memorix-sessions/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/claude/memorix/skills/memorix-troubleshooting/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codebuddy/memorix/skills/memorix-git-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codebuddy/memorix/skills/memorix-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Local scripts

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codebuddy/memorix/skills/memorix-mini-skills/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codebuddy/memorix/skills/memorix-orchestrate/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codebuddy/memorix/skills/memorix-reasoning/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codebuddy/memorix/skills/memorix-sessions/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codebuddy/memorix/skills/memorix-troubleshooting/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codex/memorix/skills/memorix-git-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codex/memorix/skills/memorix-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Local scripts

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codex/memorix/skills/memorix-mini-skills/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codex/memorix/skills/memorix-orchestrate/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codex/memorix/skills/memorix-reasoning/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codex/memorix/skills/memorix-sessions/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/codex/memorix/skills/memorix-troubleshooting/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/copilot/memorix/skills/memorix-git-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/copilot/memorix/skills/memorix-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Local scripts

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/copilot/memorix/skills/memorix-mini-skills/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/copilot/memorix/skills/memorix-orchestrate/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/copilot/memorix/skills/memorix-reasoning/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/copilot/memorix/skills/memorix-sessions/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/copilot/memorix/skills/memorix-troubleshooting/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/cursor/memorix/skills/memorix-git-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/cursor/memorix/skills/memorix-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Local scripts

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/cursor/memorix/skills/memorix-mini-skills/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/cursor/memorix/skills/memorix-orchestrate/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/cursor/memorix/skills/memorix-reasoning/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/cursor/memorix/skills/memorix-sessions/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/cursor/memorix/skills/memorix-troubleshooting/SKILL.md`

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Instructions only

4712b4dea3a1 → ab94cca6845a

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/pi/memorix/skills/memorix-git-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −26 lines

Before Not checked yet → After Not checked yet

4712b4dea3a1 → ab94cca6845a

SKILL.md was removed.

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/pi/memorix/skills/memorix-memory/SKILL.md`

Week of Oct 26, 2026 · +0 / −51 lines

Before Not checked yet → After Not checked yet

4712b4dea3a1 → ab94cca6845a

SKILL.md was removed.

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/pi/memorix/skills/memorix-mini-skills/SKILL.md`

Week of Oct 26, 2026 · +0 / −31 lines

Before Not checked yet → After Not checked yet

4712b4dea3a1 → ab94cca6845a

SKILL.md was removed.

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/pi/memorix/skills/memorix-orchestrate/SKILL.md`

Week of Oct 26, 2026 · +0 / −28 lines

Before Not checked yet → After Not checked yet

4712b4dea3a1 → ab94cca6845a

SKILL.md was removed.

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/pi/memorix/skills/memorix-reasoning/SKILL.md`

Week of Oct 26, 2026 · +0 / −30 lines

Before Not checked yet → After Not checked yet

4712b4dea3a1 → ab94cca6845a

SKILL.md was removed.

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/pi/memorix/skills/memorix-sessions/SKILL.md`

Week of Oct 26, 2026 · +0 / −25 lines

Before Not checked yet → After Not checked yet

4712b4dea3a1 → ab94cca6845a

SKILL.md was removed.

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

`plugins/pi/memorix/skills/memorix-troubleshooting/SKILL.md`

Week of Oct 26, 2026 · +0 / −27 lines

Before Not checked yet → After Not checked yet

4712b4dea3a1 → ab94cca6845a

SKILL.md was removed.

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

View on GitHub Add to my skills

Verified commit ab94cca6845a557c4b4fd38eccb42b01851bda12

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/AVIDS2/memorix.git .hotskills/avids2-memorix && git -C .hotskills/avids2-memorix checkout --detach ab94cca6845a557c4b4fd38eccb42b01851bda12
# Copy each selected skill directory from .hotskills/avids2-memorix into .claude/skills/<skill-name>/

Version-pinned installation · Gemini CLI

git clone --filter=blob:none --no-checkout https://github.com/AVIDS2/memorix.git .hotskills/avids2-memorix && git -C .hotskills/avids2-memorix checkout --detach ab94cca6845a557c4b4fd38eccb42b01851bda12
# Copy each selected skill directory from .hotskills/avids2-memorix into .gemini/skills/<skill-name>/

Version-pinned installation · OpenCode

git clone --filter=blob:none --no-checkout https://github.com/AVIDS2/memorix.git .hotskills/avids2-memorix && git -C .hotskills/avids2-memorix checkout --detach ab94cca6845a557c4b4fd38eccb42b01851bda12
# Copy each selected skill directory from .hotskills/avids2-memorix into .opencode/skills/<skill-name>/

911GitHub stars

26stars in 7 days

53skills in this repository

69commits in 30 days

Heat

7.7

Star growth, last 7 daysAhead of 93% of tracked repositories
Star growth, last 24 hoursAhead of 98% of tracked repositories
Rank movement, last 7 daysAhead of 68% of tracked repositories
Commits, last 30 daysAhead of 92% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

dynamic-resources packages/memcode/examples/extensions/dynamic-resources
calendar packages/memcode/test/fixtures/skills-collision/first/calendar
calendar packages/memcode/test/fixtures/skills-collision/second/calendar
bad--name packages/memcode/test/fixtures/skills/consecutive-hyphens
disable-model-invocation packages/memcode/test/fixtures/skills/disable-model-invocation
Invalid_Name packages/memcode/test/fixtures/skills/invalid-name-chars
invalid-yaml packages/memcode/test/fixtures/skills/invalid-yaml
this-is-a-very-long-skill-name-that-exceeds-the-sixty-four-character-limit-set-by-the-standard packages/memcode/test/fixtures/skills/long-name
missing-description packages/memcode/test/fixtures/skills/missing-description
multiline-description packages/memcode/test/fixtures/skills/multiline-description
different-name packages/memcode/test/fixtures/skills/name-mismatch
child-skill packages/memcode/test/fixtures/skills/nested/child-skill
no-frontmatter packages/memcode/test/fixtures/skills/no-frontmatter
root-skill-preferred packages/memcode/test/fixtures/skills/root-skill-preferred
nested-child packages/memcode/test/fixtures/skills/root-skill-preferred/nested-child
unknown-field packages/memcode/test/fixtures/skills/unknown-field
valid-skill packages/memcode/test/fixtures/skills/valid-skill
memorix plugins/claude/memorix
memorix-git-memory plugins/claude/memorix/skills/memorix-git-memory
memorix-memory plugins/claude/memorix/skills/memorix-memory
memorix-mini-skills plugins/claude/memorix/skills/memorix-mini-skills
memorix-orchestrate plugins/claude/memorix/skills/memorix-orchestrate
memorix-reasoning plugins/claude/memorix/skills/memorix-reasoning
memorix-sessions plugins/claude/memorix/skills/memorix-sessions
memorix-troubleshooting plugins/claude/memorix/skills/memorix-troubleshooting
memorix-git-memory plugins/codebuddy/memorix/skills/memorix-git-memory
memorix-memory plugins/codebuddy/memorix/skills/memorix-memory
memorix-mini-skills plugins/codebuddy/memorix/skills/memorix-mini-skills
memorix-orchestrate plugins/codebuddy/memorix/skills/memorix-orchestrate
memorix-reasoning plugins/codebuddy/memorix/skills/memorix-reasoning
memorix-sessions plugins/codebuddy/memorix/skills/memorix-sessions
memorix-troubleshooting plugins/codebuddy/memorix/skills/memorix-troubleshooting
memorix-git-memory plugins/codex/memorix/skills/memorix-git-memory
memorix-memory plugins/codex/memorix/skills/memorix-memory
memorix-mini-skills plugins/codex/memorix/skills/memorix-mini-skills
memorix-orchestrate plugins/codex/memorix/skills/memorix-orchestrate
memorix-reasoning plugins/codex/memorix/skills/memorix-reasoning
memorix-sessions plugins/codex/memorix/skills/memorix-sessions
memorix-troubleshooting plugins/codex/memorix/skills/memorix-troubleshooting
memorix-git-memory plugins/copilot/memorix/skills/memorix-git-memory
memorix-memory plugins/copilot/memorix/skills/memorix-memory
memorix-mini-skills plugins/copilot/memorix/skills/memorix-mini-skills
memorix-orchestrate plugins/copilot/memorix/skills/memorix-orchestrate
memorix-reasoning plugins/copilot/memorix/skills/memorix-reasoning
memorix-sessions plugins/copilot/memorix/skills/memorix-sessions
memorix-troubleshooting plugins/copilot/memorix/skills/memorix-troubleshooting
memorix-git-memory plugins/cursor/memorix/skills/memorix-git-memory
memorix-memory plugins/cursor/memorix/skills/memorix-memory
memorix-mini-skills plugins/cursor/memorix/skills/memorix-mini-skills
memorix-orchestrate plugins/cursor/memorix/skills/memorix-orchestrate
memorix-reasoning plugins/cursor/memorix/skills/memorix-reasoning
memorix-sessions plugins/cursor/memorix/skills/memorix-sessions
memorix-troubleshooting plugins/cursor/memorix/skills/memorix-troubleshooting

How it works

Choose a skill

dynamic-resources

When your agent uses it

Example skill loaded from resources_discover

What it loads into context

Frontmatter

15 tokens

Always available to the agent

SKILL.md

34 tokens

When the skill is activated

Reference documents

28 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Scripts executed separately

index.ts

Files

SKILL.mdcore177 bytes
dynamic.jsonasset2,035 bytes
dynamic.mddoc160 bytes
index.tsruns442 bytes
../../../../../plugins/antigravity/memorix/hooks.jsonasset1,034 bytes
../../../../../plugins/codebuddy/memorix/hooks/hooks.jsonasset663 bytes
../../../../../plugins/codex/memorix/hooks/hooks.jsonasset1,482 bytes
../../../../../plugins/copilot/memorix/hooks/hooks.jsonasset778 bytes

Read SKILL.md


# Dynamic Resources Skill

This skill is provided by the dynamic-resources extension.

View the complete source on GitHub

calendar

When your agent uses it

First calendar skill.

What it loads into context

Frontmatter

10 tokens

Always available to the agent

SKILL.md

24 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore113 bytes

Read SKILL.md


# Calendar (First)

This is the first calendar skill.

View the complete source on GitHub

calendar

When your agent uses it

Second calendar skill.

What it loads into context

Frontmatter

10 tokens

Always available to the agent

SKILL.md

24 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore116 bytes

Read SKILL.md


# Calendar (Second)

This is the second calendar skill.

View the complete source on GitHub

bad--name

When your agent uses it

A skill with consecutive hyphens in the name.

What it loads into context

Frontmatter

19 tokens

Always available to the agent

SKILL.md

40 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore155 bytes

Read SKILL.md


# Consecutive Hyphens

This skill has consecutive hyphens in its name.

View the complete source on GitHub

disable-model-invocation

When your agent uses it

A skill that cannot be invoked by the model.

What it loads into context

Frontmatter

27 tokens

Always available to the agent

SKILL.md

50 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore218 bytes

Read SKILL.md


# Manual Only Skill

This skill can only be invoked via /skill:disable-model-invocation.

View the complete source on GitHub

Invalid_Name

When your agent uses it

A skill with invalid characters in the name.

What it loads into context

Frontmatter

16 tokens

Always available to the agent

SKILL.md

32 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore155 bytes

Read SKILL.md


# Invalid Name

This skill has uppercase and underscore in the name.

View the complete source on GitHub

invalid-yaml

When your agent uses it

What it loads into context

Frontmatter

12 tokens

Always available to the agent

SKILL.md

30 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore129 bytes

Read SKILL.md


# Invalid YAML Skill

This skill has invalid YAML in the frontmatter.

View the complete source on GitHub

this-is-a-very-long-skill-name-that-exceeds-the-sixty-four-character-limit-set-by-the-standard

When your agent uses it

A skill with a name that exceeds 64 characters.

What it loads into context

Frontmatter

38 tokens

Always available to the agent

SKILL.md

52 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore215 bytes

Read SKILL.md


# Long Name

This skill's name is too long.

View the complete source on GitHub

missing-description

When your agent uses it

What it loads into context

Frontmatter

4 tokens

Always available to the agent

SKILL.md

18 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore95 bytes

Read SKILL.md


# Missing Description

This skill has no description field.

View the complete source on GitHub

multiline-description

When your agent uses it

This is a multiline description. It spans multiple lines. And should be normalized.

What it loads into context

Frontmatter

27 tokens

Always available to the agent

SKILL.md

48 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore255 bytes

Read SKILL.md


# Multiline Description Skill

This skill tests that multiline YAML descriptions are normalized to single lines.

View the complete source on GitHub

different-name

When your agent uses it

A skill with a name that doesn't match the directory.

What it loads into context

Frontmatter

18 tokens

Always available to the agent

SKILL.md

35 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore168 bytes

Read SKILL.md


# Name Mismatch

This skill's name doesn't match its parent directory.

View the complete source on GitHub

child-skill

When your agent uses it

A nested skill in a subdirectory.

What it loads into context

Frontmatter

16 tokens

Always available to the agent

SKILL.md

31 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore129 bytes

Read SKILL.md


# Child Skill

This skill is nested in a subdirectory.

View the complete source on GitHub

When your agent uses it

What it loads into context

Frontmatter

0 tokens

Always available to the agent

SKILL.md

15 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore61 bytes

Read SKILL.md

# No Frontmatter

This skill has no YAML frontmatter at all.

View the complete source on GitHub

When your agent uses it

Root skill should win.

What it loads into context

Frontmatter

7 tokens

Always available to the agent

SKILL.md

9 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore44 bytes

Read SKILL.md

View the complete source on GitHub

When your agent uses it

Nested skill should be ignored.

What it loads into context

Frontmatter

8 tokens

Always available to the agent

SKILL.md

10 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore53 bytes

Read SKILL.md

View the complete source on GitHub

unknown-field

When your agent uses it

A skill with an unknown frontmatter field.

What it loads into context

Frontmatter

26 tokens

Always available to the agent

SKILL.md

42 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore179 bytes

Read SKILL.md


# Unknown Field

This skill has non-standard frontmatter fields.

View the complete source on GitHub

valid-skill

When your agent uses it

A valid skill for testing purposes.

What it loads into context

Frontmatter

15 tokens

Always available to the agent

SKILL.md

33 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

SKILL.mdcore153 bytes

Read SKILL.md


# Valid Skill

This is a valid skill that follows the Agent Skills standard.

View the complete source on GitHub

memorix

When your agent uses it

Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.

What it loads into context

Frontmatter

38 tokens

Always available to the agent

SKILL.md

457 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Skill Router
Default Loop

Files

.claude-plugin/plugin.jsonasset597 bytes
.mcp.jsonasset145 bytes
SKILL.mdcore2,061 bytes
hooks/hooks.jsonasset983 bytes

Read SKILL.md


# Memorix

Memorix is a shared memory layer for the active workspace when Memorix tools are available. Use this root skill as a router, then prefer the focused skill for the task.

## Skill Router

| Task | Use |
|---|---|
| Recall/store durable workspace context | `memorix-memory` |
| Record or recover why a decision was made | `memorix-reasoning` |
| Resume sessions, bind HTTP projects, or prepare handoff | `memorix-sessions` |
| Use commit history as evidence | `memorix-git-memory` |
| Promote repeated knowledge into reusable guidance | `memorix-mini-skills` |
| Coordinate explicit subagent work | `memorix-orchestrate` |

View the complete source on GitHub

memorix-git-memory

When your agent uses it

Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.

What it loads into context

Frontmatter

35 tokens

Always available to the agent

SKILL.md

292 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Retrieval Rules

Files

SKILL.mdcore1,272 bytes

Read SKILL.md


# Memorix Git Memory

Use Git Memory for repository evidence. Use reasoning memory for intent.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Search what changed | `memorix_search` with a change-focused query | `memorix memory search --query "what changed <topic>"` |
| Inspect a git-backed memory | `memorix_detail` | `memorix memory detail --id <id>` |
| Ingest current commit manually | CLI | `memorix ingest commit` |
| Ingest a specific commit | CLI | `memorix ingest commit --ref <ref>` |
| Backfill recent history | CLI | `memorix ingest log --count 20` |
| Install post-commit ingestion | CLI | `memorix git-hook --force` |

View the complete source on GitHub

memorix-memory

When your agent uses it

Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

914 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Search Rules
Store Rules

Files

SKILL.mdcore3,909 bytes
SKILL.mdcore3,909 bytes
SKILL.mdcore3,909 bytes

Read SKILL.md


# Memorix Memory

Use Memorix as the shared memory layer for the active workspace when Memorix tools are available.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Broad continuation, fresh handoff, or "what do we know?" | `memorix_project_context` with the user's task | `memorix context --task "<topic>" --fallback --brief-json` |
| Need structured refs/freshness for code-bound memories | `memorix_context_pack` | `memorix codegraph context-pack --task "<topic>"` |
| Specific past decision, bug, file, or change | `memorix_search` | `memorix memory search --query "<topic>"` |
| Need the full source for a search hit | `memorix_detail` | `memorix memory detail --id <id>` |
| Need the sequence around one memory | `memorix_timeline` | `memorix memory timeline --id <id>` |
| Check source and freshness for a memory | `memorix_evidence` | `memorix evidence list|get|events` |

View the complete source on GitHub

memorix-mini-skills

When your agent uses it

Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

367 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Promote When
Do Not Promote

Files

SKILL.mdcore1,594 bytes

Read SKILL.md


# Memorix Mini-Skills

Promote memories into mini-skills only when they are reusable instructions, not just historical notes.

The standard setup uses the `lite` MCP profile. `memorix_skills` and `memorix_promote` are full-profile tools, so use the CLI fallback unless the current server was explicitly started with `MEMORIX_MODE=full` or `--mode full`. Do not probe hidden MCP tools repeatedly.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Preview/discover existing project skills | `memorix_skills` action `list` | `memorix skills list` |
| Generate skills from memory patterns | `memorix_skills` action `generate` | `memorix skills generate` |
| Write generated skills to an agent | `memorix_skills` action `generate`, `write: true` | `memorix skills generate --write --target codex` |
| Promote selected memories permanently | `memorix_promote` action `promote` | `memorix memory promote --ids 42,43` |

View the complete source on GitHub

memorix-orchestrate

When your agent uses it

Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.

What it loads into context

Frontmatter

41 tokens

Always available to the agent

SKILL.md

390 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Boundaries

Files

SKILL.mdcore1,663 bytes

Read SKILL.md


# Memorix Orchestrate

Use Memorix coordination for explicit subagent workflows with joined identities, tasks, handoffs, messages, file locks, and orchestrated workers.

The standard setup uses the `lite` MCP profile. Coordination MCP tools are exposed only by `team` or `full`; use the CLI fallback for ordinary installations, or explicitly start the server with `--mode team`. Do not probe unavailable team tools in a loop.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Run managed subagent execution | CLI | `memorix orchestrate --goal "<goal>" --agents claude:1,codex:1` |
| Register coordination identity | `team_manage` action `join` | `memorix team join --agentType <agent>` |
| Create or inspect tasks | `team_task` | `memorix task create|list|claim|complete` |
| Send or read coordination messages | `team_message` | `memorix message send|broadcast|inbox` |

View the complete source on GitHub

memorix-reasoning

When your agent uses it

Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

320 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Use Reasoning When
Do Not Use Reasoning For

Files

SKILL.mdcore1,409 bytes

Read SKILL.md


# Memorix Reasoning

Use reasoning memory for why a decision was made. Use ordinary memory for what happened.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Store why a decision was made | `memorix_store_reasoning` | `memorix reasoning store --entity <name> --decision "<decision>" --rationale "<why>"` |
| Find earlier rationale | `memorix_search_reasoning` | `memorix reasoning search --query "<topic>"` |
| Need a stable evolving topic key | `memorix_suggest_topic_key` | `memorix memory suggest-topic-key --type decision --title "<title>"` |
| Link rationale to commit evidence | `relatedCommits` on reasoning store | `memorix reasoning store ... --relatedCommits <sha>` |

## Use Reasoning When

View the complete source on GitHub

memorix-sessions

When your agent uses it

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether session_start is useful.

What it loads into context

Frontmatter

35 tokens

Always available to the agent

SKILL.md

317 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Decision Rules

Files

SKILL.mdcore1,378 bytes

Read SKILL.md


# Memorix Sessions

`memorix_session_start` is optional. Use it when session semantics help; do not make memory-only work heavier than needed.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Resume a prior long-running task | `memorix_session_start` | `memorix session start --agent <name>` |
| HTTP control plane needs project binding | `memorix_session_start` with `projectRoot` | `memorix session start --projectRoot <absolute-path>` |
| Need recent handoff/session summaries | `memorix_session_context` | `memorix session context` |
| End a real working session | `memorix_session_end` | `memorix session end --sessionId <id> --summary "<summary>"` |
| Need explicit subagent coordination identity | `memorix_session_start` with `joinTeam: true` | `memorix session start --joinTeam --agentType <agent>` |

View the complete source on GitHub

memorix-troubleshooting

When your agent uses it

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

What it loads into context

Frontmatter

40 tokens

Always available to the agent

SKILL.md

335 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Diagnostic Router
Mode Rules

Files

SKILL.mdcore1,529 bytes

Read SKILL.md


# Memorix Troubleshooting

Prefer direct CLI diagnostics first. MCP is an integration surface, not the only way to operate Memorix.

## Diagnostic Router

| Symptom | Check | CLI fallback |
|---|---|---|
| MCP tools missing | host MCP config and restart | `memorix setup --agent <agent>` |
| Unsure project is bound | project status | `memorix status` and `git status` |
| HTTP MCP stale or unbound | background health and explicit session bind | `memorix background status`; then `memorix session start --projectRoot <path>` |
| Hooks not firing | hook status | `memorix hooks status` |
| Need to inspect generated files | preview | `memorix hooks preview --agent <agent>` |
| Setup looks incomplete | reinstall host integration | `memorix setup --agent <agent>` |

View the complete source on GitHub

memorix-git-memory

When your agent uses it

Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.

What it loads into context

Frontmatter

35 tokens

Always available to the agent

SKILL.md

292 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Retrieval Rules

Files

SKILL.mdcore1,272 bytes

Read SKILL.md


# Memorix Git Memory

Use Git Memory for repository evidence. Use reasoning memory for intent.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Search what changed | `memorix_search` with a change-focused query | `memorix memory search --query "what changed <topic>"` |
| Inspect a git-backed memory | `memorix_detail` | `memorix memory detail --id <id>` |
| Ingest current commit manually | CLI | `memorix ingest commit` |
| Ingest a specific commit | CLI | `memorix ingest commit --ref <ref>` |
| Backfill recent history | CLI | `memorix ingest log --count 20` |
| Install post-commit ingestion | CLI | `memorix git-hook --force` |

View the complete source on GitHub

memorix-memory

When your agent uses it

Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

914 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Search Rules
Store Rules

Files

SKILL.mdcore3,909 bytes
SKILL.mdcore3,909 bytes
SKILL.mdcore3,909 bytes

Read SKILL.md


# Memorix Memory

Use Memorix as the shared memory layer for the active workspace when Memorix tools are available.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Broad continuation, fresh handoff, or "what do we know?" | `memorix_project_context` with the user's task | `memorix context --task "<topic>" --fallback --brief-json` |
| Need structured refs/freshness for code-bound memories | `memorix_context_pack` | `memorix codegraph context-pack --task "<topic>"` |
| Specific past decision, bug, file, or change | `memorix_search` | `memorix memory search --query "<topic>"` |
| Need the full source for a search hit | `memorix_detail` | `memorix memory detail --id <id>` |
| Need the sequence around one memory | `memorix_timeline` | `memorix memory timeline --id <id>` |
| Check source and freshness for a memory | `memorix_evidence` | `memorix evidence list|get|events` |

View the complete source on GitHub

memorix-mini-skills

When your agent uses it

Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

367 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Promote When
Do Not Promote

Files

SKILL.mdcore1,594 bytes

Read SKILL.md


# Memorix Mini-Skills

Promote memories into mini-skills only when they are reusable instructions, not just historical notes.

The standard setup uses the `lite` MCP profile. `memorix_skills` and `memorix_promote` are full-profile tools, so use the CLI fallback unless the current server was explicitly started with `MEMORIX_MODE=full` or `--mode full`. Do not probe hidden MCP tools repeatedly.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Preview/discover existing project skills | `memorix_skills` action `list` | `memorix skills list` |
| Generate skills from memory patterns | `memorix_skills` action `generate` | `memorix skills generate` |
| Write generated skills to an agent | `memorix_skills` action `generate`, `write: true` | `memorix skills generate --write --target codex` |
| Promote selected memories permanently | `memorix_promote` action `promote` | `memorix memory promote --ids 42,43` |

View the complete source on GitHub

memorix-orchestrate

When your agent uses it

Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.

What it loads into context

Frontmatter

41 tokens

Always available to the agent

SKILL.md

390 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Boundaries

Files

SKILL.mdcore1,663 bytes

Read SKILL.md


# Memorix Orchestrate

Use Memorix coordination for explicit subagent workflows with joined identities, tasks, handoffs, messages, file locks, and orchestrated workers.

The standard setup uses the `lite` MCP profile. Coordination MCP tools are exposed only by `team` or `full`; use the CLI fallback for ordinary installations, or explicitly start the server with `--mode team`. Do not probe unavailable team tools in a loop.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Run managed subagent execution | CLI | `memorix orchestrate --goal "<goal>" --agents claude:1,codex:1` |
| Register coordination identity | `team_manage` action `join` | `memorix team join --agentType <agent>` |
| Create or inspect tasks | `team_task` | `memorix task create|list|claim|complete` |
| Send or read coordination messages | `team_message` | `memorix message send|broadcast|inbox` |

View the complete source on GitHub

memorix-reasoning

When your agent uses it

Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

320 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Use Reasoning When
Do Not Use Reasoning For

Files

SKILL.mdcore1,409 bytes

Read SKILL.md


# Memorix Reasoning

Use reasoning memory for why a decision was made. Use ordinary memory for what happened.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Store why a decision was made | `memorix_store_reasoning` | `memorix reasoning store --entity <name> --decision "<decision>" --rationale "<why>"` |
| Find earlier rationale | `memorix_search_reasoning` | `memorix reasoning search --query "<topic>"` |
| Need a stable evolving topic key | `memorix_suggest_topic_key` | `memorix memory suggest-topic-key --type decision --title "<title>"` |
| Link rationale to commit evidence | `relatedCommits` on reasoning store | `memorix reasoning store ... --relatedCommits <sha>` |

## Use Reasoning When

View the complete source on GitHub

memorix-sessions

When your agent uses it

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether session_start is useful.

What it loads into context

Frontmatter

35 tokens

Always available to the agent

SKILL.md

317 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Decision Rules

Files

SKILL.mdcore1,378 bytes

Read SKILL.md


# Memorix Sessions

`memorix_session_start` is optional. Use it when session semantics help; do not make memory-only work heavier than needed.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Resume a prior long-running task | `memorix_session_start` | `memorix session start --agent <name>` |
| HTTP control plane needs project binding | `memorix_session_start` with `projectRoot` | `memorix session start --projectRoot <absolute-path>` |
| Need recent handoff/session summaries | `memorix_session_context` | `memorix session context` |
| End a real working session | `memorix_session_end` | `memorix session end --sessionId <id> --summary "<summary>"` |
| Need explicit subagent coordination identity | `memorix_session_start` with `joinTeam: true` | `memorix session start --joinTeam --agentType <agent>` |

View the complete source on GitHub

memorix-troubleshooting

When your agent uses it

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

What it loads into context

Frontmatter

40 tokens

Always available to the agent

SKILL.md

335 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Diagnostic Router
Mode Rules

Files

SKILL.mdcore1,529 bytes

Read SKILL.md


# Memorix Troubleshooting

Prefer direct CLI diagnostics first. MCP is an integration surface, not the only way to operate Memorix.

## Diagnostic Router

| Symptom | Check | CLI fallback |
|---|---|---|
| MCP tools missing | host MCP config and restart | `memorix setup --agent <agent>` |
| Unsure project is bound | project status | `memorix status` and `git status` |
| HTTP MCP stale or unbound | background health and explicit session bind | `memorix background status`; then `memorix session start --projectRoot <path>` |
| Hooks not firing | hook status | `memorix hooks status` |
| Need to inspect generated files | preview | `memorix hooks preview --agent <agent>` |
| Setup looks incomplete | reinstall host integration | `memorix setup --agent <agent>` |

View the complete source on GitHub

memorix-git-memory

When your agent uses it

Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.

What it loads into context

Frontmatter

35 tokens

Always available to the agent

SKILL.md

292 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Retrieval Rules

Files

SKILL.mdcore1,272 bytes

Read SKILL.md


# Memorix Git Memory

Use Git Memory for repository evidence. Use reasoning memory for intent.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Search what changed | `memorix_search` with a change-focused query | `memorix memory search --query "what changed <topic>"` |
| Inspect a git-backed memory | `memorix_detail` | `memorix memory detail --id <id>` |
| Ingest current commit manually | CLI | `memorix ingest commit` |
| Ingest a specific commit | CLI | `memorix ingest commit --ref <ref>` |
| Backfill recent history | CLI | `memorix ingest log --count 20` |
| Install post-commit ingestion | CLI | `memorix git-hook --force` |

View the complete source on GitHub

memorix-memory

When your agent uses it

Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

925 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Search Rules
Store Rules

Files

SKILL.mdcore3,962 bytes
SKILL.mdcore3,962 bytes
SKILL.mdcore3,962 bytes

Read SKILL.md


# Memorix Memory

Use Memorix as the shared memory layer for the active workspace when Memorix tools are available.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Broad continuation, fresh handoff, or "what do we know?" | `memorix_project_context` with the user's task | `memorix context --task "<topic>" --fallback --brief-json` |
| Need structured refs/freshness for code-bound memories | `memorix_context_pack` | `memorix codegraph context-pack --task "<topic>"` |
| Explicit memory graph question | `memorix_graph_context` | `memorix memory graph-context --query "<topic>"` |
| Specific past decision, bug, file, or change | `memorix_search` | `memorix memory search --query "<topic>"` |
| Need the full source for a search hit | `memorix_detail` | `memorix memory detail --id <id>` |
| Need the sequence around one memory | `memorix_timeline` | `memorix memory timeline --id <id>` |

View the complete source on GitHub

memorix-mini-skills

When your agent uses it

Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

367 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Promote When
Do Not Promote

Files

SKILL.mdcore1,594 bytes

Read SKILL.md


# Memorix Mini-Skills

Promote memories into mini-skills only when they are reusable instructions, not just historical notes.

The standard setup uses the `lite` MCP profile. `memorix_skills` and `memorix_promote` are full-profile tools, so use the CLI fallback unless the current server was explicitly started with `MEMORIX_MODE=full` or `--mode full`. Do not probe hidden MCP tools repeatedly.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Preview/discover existing project skills | `memorix_skills` action `list` | `memorix skills list` |
| Generate skills from memory patterns | `memorix_skills` action `generate` | `memorix skills generate` |
| Write generated skills to an agent | `memorix_skills` action `generate`, `write: true` | `memorix skills generate --write --target codex` |
| Promote selected memories permanently | `memorix_promote` action `promote` | `memorix memory promote --ids 42,43` |

View the complete source on GitHub

memorix-orchestrate

When your agent uses it

Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.

What it loads into context

Frontmatter

41 tokens

Always available to the agent

SKILL.md

390 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Boundaries

Files

SKILL.mdcore1,663 bytes

Read SKILL.md


# Memorix Orchestrate

Use Memorix coordination for explicit subagent workflows with joined identities, tasks, handoffs, messages, file locks, and orchestrated workers.

The standard setup uses the `lite` MCP profile. Coordination MCP tools are exposed only by `team` or `full`; use the CLI fallback for ordinary installations, or explicitly start the server with `--mode team`. Do not probe unavailable team tools in a loop.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Run managed subagent execution | CLI | `memorix orchestrate --goal "<goal>" --agents claude:1,codex:1` |
| Register coordination identity | `team_manage` action `join` | `memorix team join --agentType <agent>` |
| Create or inspect tasks | `team_task` | `memorix task create|list|claim|complete` |
| Send or read coordination messages | `team_message` | `memorix message send|broadcast|inbox` |

View the complete source on GitHub

memorix-reasoning

When your agent uses it

Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

320 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Use Reasoning When
Do Not Use Reasoning For

Files

SKILL.mdcore1,409 bytes

Read SKILL.md


# Memorix Reasoning

Use reasoning memory for why a decision was made. Use ordinary memory for what happened.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Store why a decision was made | `memorix_store_reasoning` | `memorix reasoning store --entity <name> --decision "<decision>" --rationale "<why>"` |
| Find earlier rationale | `memorix_search_reasoning` | `memorix reasoning search --query "<topic>"` |
| Need a stable evolving topic key | `memorix_suggest_topic_key` | `memorix memory suggest-topic-key --type decision --title "<title>"` |
| Link rationale to commit evidence | `relatedCommits` on reasoning store | `memorix reasoning store ... --relatedCommits <sha>` |

## Use Reasoning When

View the complete source on GitHub

memorix-sessions

When your agent uses it

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether session_start is useful.

What it loads into context

Frontmatter

35 tokens

Always available to the agent

SKILL.md

317 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Decision Rules

Files

SKILL.mdcore1,378 bytes

Read SKILL.md


# Memorix Sessions

`memorix_session_start` is optional. Use it when session semantics help; do not make memory-only work heavier than needed.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Resume a prior long-running task | `memorix_session_start` | `memorix session start --agent <name>` |
| HTTP control plane needs project binding | `memorix_session_start` with `projectRoot` | `memorix session start --projectRoot <absolute-path>` |
| Need recent handoff/session summaries | `memorix_session_context` | `memorix session context` |
| End a real working session | `memorix_session_end` | `memorix session end --sessionId <id> --summary "<summary>"` |
| Need explicit subagent coordination identity | `memorix_session_start` with `joinTeam: true` | `memorix session start --joinTeam --agentType <agent>` |

View the complete source on GitHub

memorix-troubleshooting

When your agent uses it

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

What it loads into context

Frontmatter

40 tokens

Always available to the agent

SKILL.md

335 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Diagnostic Router
Mode Rules

Files

SKILL.mdcore1,529 bytes

Read SKILL.md


# Memorix Troubleshooting

Prefer direct CLI diagnostics first. MCP is an integration surface, not the only way to operate Memorix.

## Diagnostic Router

| Symptom | Check | CLI fallback |
|---|---|---|
| MCP tools missing | host MCP config and restart | `memorix setup --agent <agent>` |
| Unsure project is bound | project status | `memorix status` and `git status` |
| HTTP MCP stale or unbound | background health and explicit session bind | `memorix background status`; then `memorix session start --projectRoot <path>` |
| Hooks not firing | hook status | `memorix hooks status` |
| Need to inspect generated files | preview | `memorix hooks preview --agent <agent>` |
| Setup looks incomplete | reinstall host integration | `memorix setup --agent <agent>` |

View the complete source on GitHub

memorix-git-memory

When your agent uses it

Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.

What it loads into context

Frontmatter

35 tokens

Always available to the agent

SKILL.md

292 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Retrieval Rules

Files

SKILL.mdcore1,272 bytes

Read SKILL.md


# Memorix Git Memory

Use Git Memory for repository evidence. Use reasoning memory for intent.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Search what changed | `memorix_search` with a change-focused query | `memorix memory search --query "what changed <topic>"` |
| Inspect a git-backed memory | `memorix_detail` | `memorix memory detail --id <id>` |
| Ingest current commit manually | CLI | `memorix ingest commit` |
| Ingest a specific commit | CLI | `memorix ingest commit --ref <ref>` |
| Backfill recent history | CLI | `memorix ingest log --count 20` |
| Install post-commit ingestion | CLI | `memorix git-hook --force` |

View the complete source on GitHub

memorix-memory

When your agent uses it

Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

925 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Search Rules
Store Rules

Files

SKILL.mdcore3,962 bytes
SKILL.mdcore3,962 bytes
SKILL.mdcore3,962 bytes

Read SKILL.md


# Memorix Memory

Use Memorix as the shared memory layer for the active workspace when Memorix tools are available.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Broad continuation, fresh handoff, or "what do we know?" | `memorix_project_context` with the user's task | `memorix context --task "<topic>" --fallback --brief-json` |
| Need structured refs/freshness for code-bound memories | `memorix_context_pack` | `memorix codegraph context-pack --task "<topic>"` |
| Explicit memory graph question | `memorix_graph_context` | `memorix memory graph-context --query "<topic>"` |
| Specific past decision, bug, file, or change | `memorix_search` | `memorix memory search --query "<topic>"` |
| Need the full source for a search hit | `memorix_detail` | `memorix memory detail --id <id>` |
| Need the sequence around one memory | `memorix_timeline` | `memorix memory timeline --id <id>` |

View the complete source on GitHub

memorix-mini-skills

When your agent uses it

Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

367 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Promote When
Do Not Promote

Files

SKILL.mdcore1,594 bytes

Read SKILL.md


# Memorix Mini-Skills

Promote memories into mini-skills only when they are reusable instructions, not just historical notes.

The standard setup uses the `lite` MCP profile. `memorix_skills` and `memorix_promote` are full-profile tools, so use the CLI fallback unless the current server was explicitly started with `MEMORIX_MODE=full` or `--mode full`. Do not probe hidden MCP tools repeatedly.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Preview/discover existing project skills | `memorix_skills` action `list` | `memorix skills list` |
| Generate skills from memory patterns | `memorix_skills` action `generate` | `memorix skills generate` |
| Write generated skills to an agent | `memorix_skills` action `generate`, `write: true` | `memorix skills generate --write --target codex` |
| Promote selected memories permanently | `memorix_promote` action `promote` | `memorix memory promote --ids 42,43` |

View the complete source on GitHub

memorix-orchestrate

When your agent uses it

Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.

What it loads into context

Frontmatter

41 tokens

Always available to the agent

SKILL.md

390 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Boundaries

Files

SKILL.mdcore1,663 bytes

Read SKILL.md


# Memorix Orchestrate

Use Memorix coordination for explicit subagent workflows with joined identities, tasks, handoffs, messages, file locks, and orchestrated workers.

The standard setup uses the `lite` MCP profile. Coordination MCP tools are exposed only by `team` or `full`; use the CLI fallback for ordinary installations, or explicitly start the server with `--mode team`. Do not probe unavailable team tools in a loop.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Run managed subagent execution | CLI | `memorix orchestrate --goal "<goal>" --agents claude:1,codex:1` |
| Register coordination identity | `team_manage` action `join` | `memorix team join --agentType <agent>` |
| Create or inspect tasks | `team_task` | `memorix task create|list|claim|complete` |
| Send or read coordination messages | `team_message` | `memorix message send|broadcast|inbox` |

View the complete source on GitHub

memorix-reasoning

When your agent uses it

Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

320 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Use Reasoning When
Do Not Use Reasoning For

Files

SKILL.mdcore1,409 bytes

Read SKILL.md


# Memorix Reasoning

Use reasoning memory for why a decision was made. Use ordinary memory for what happened.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Store why a decision was made | `memorix_store_reasoning` | `memorix reasoning store --entity <name> --decision "<decision>" --rationale "<why>"` |
| Find earlier rationale | `memorix_search_reasoning` | `memorix reasoning search --query "<topic>"` |
| Need a stable evolving topic key | `memorix_suggest_topic_key` | `memorix memory suggest-topic-key --type decision --title "<title>"` |
| Link rationale to commit evidence | `relatedCommits` on reasoning store | `memorix reasoning store ... --relatedCommits <sha>` |

## Use Reasoning When

View the complete source on GitHub

memorix-sessions

When your agent uses it

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether session_start is useful.

What it loads into context

Frontmatter

35 tokens

Always available to the agent

SKILL.md

317 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Decision Rules

Files

SKILL.mdcore1,378 bytes

Read SKILL.md


# Memorix Sessions

`memorix_session_start` is optional. Use it when session semantics help; do not make memory-only work heavier than needed.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Resume a prior long-running task | `memorix_session_start` | `memorix session start --agent <name>` |
| HTTP control plane needs project binding | `memorix_session_start` with `projectRoot` | `memorix session start --projectRoot <absolute-path>` |
| Need recent handoff/session summaries | `memorix_session_context` | `memorix session context` |
| End a real working session | `memorix_session_end` | `memorix session end --sessionId <id> --summary "<summary>"` |
| Need explicit subagent coordination identity | `memorix_session_start` with `joinTeam: true` | `memorix session start --joinTeam --agentType <agent>` |

View the complete source on GitHub

memorix-troubleshooting

When your agent uses it

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

What it loads into context

Frontmatter

40 tokens

Always available to the agent

SKILL.md

335 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Diagnostic Router
Mode Rules

Files

SKILL.mdcore1,529 bytes

Read SKILL.md


# Memorix Troubleshooting

Prefer direct CLI diagnostics first. MCP is an integration surface, not the only way to operate Memorix.

## Diagnostic Router

| Symptom | Check | CLI fallback |
|---|---|---|
| MCP tools missing | host MCP config and restart | `memorix setup --agent <agent>` |
| Unsure project is bound | project status | `memorix status` and `git status` |
| HTTP MCP stale or unbound | background health and explicit session bind | `memorix background status`; then `memorix session start --projectRoot <path>` |
| Hooks not firing | hook status | `memorix hooks status` |
| Need to inspect generated files | preview | `memorix hooks preview --agent <agent>` |
| Setup looks incomplete | reinstall host integration | `memorix setup --agent <agent>` |

View the complete source on GitHub

memorix-git-memory

When your agent uses it

Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.

What it loads into context

Frontmatter

35 tokens

Always available to the agent

SKILL.md

292 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Retrieval Rules

Files

SKILL.mdcore1,272 bytes

Read SKILL.md


# Memorix Git Memory

Use Git Memory for repository evidence. Use reasoning memory for intent.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Search what changed | `memorix_search` with a change-focused query | `memorix memory search --query "what changed <topic>"` |
| Inspect a git-backed memory | `memorix_detail` | `memorix memory detail --id <id>` |
| Ingest current commit manually | CLI | `memorix ingest commit` |
| Ingest a specific commit | CLI | `memorix ingest commit --ref <ref>` |
| Backfill recent history | CLI | `memorix ingest log --count 20` |
| Install post-commit ingestion | CLI | `memorix git-hook --force` |

View the complete source on GitHub

memorix-memory

When your agent uses it

Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

925 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Search Rules
Store Rules

Files

SKILL.mdcore3,962 bytes
SKILL.mdcore3,962 bytes
SKILL.mdcore3,962 bytes

Read SKILL.md


# Memorix Memory

Use Memorix as the shared memory layer for the active workspace when Memorix tools are available.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Broad continuation, fresh handoff, or "what do we know?" | `memorix_project_context` with the user's task | `memorix context --task "<topic>" --fallback --brief-json` |
| Need structured refs/freshness for code-bound memories | `memorix_context_pack` | `memorix codegraph context-pack --task "<topic>"` |
| Explicit memory graph question | `memorix_graph_context` | `memorix memory graph-context --query "<topic>"` |
| Specific past decision, bug, file, or change | `memorix_search` | `memorix memory search --query "<topic>"` |
| Need the full source for a search hit | `memorix_detail` | `memorix memory detail --id <id>` |
| Need the sequence around one memory | `memorix_timeline` | `memorix memory timeline --id <id>` |

View the complete source on GitHub

memorix-mini-skills

When your agent uses it

Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

367 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Promote When
Do Not Promote

Files

SKILL.mdcore1,594 bytes

Read SKILL.md


# Memorix Mini-Skills

Promote memories into mini-skills only when they are reusable instructions, not just historical notes.

The standard setup uses the `lite` MCP profile. `memorix_skills` and `memorix_promote` are full-profile tools, so use the CLI fallback unless the current server was explicitly started with `MEMORIX_MODE=full` or `--mode full`. Do not probe hidden MCP tools repeatedly.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Preview/discover existing project skills | `memorix_skills` action `list` | `memorix skills list` |
| Generate skills from memory patterns | `memorix_skills` action `generate` | `memorix skills generate` |
| Write generated skills to an agent | `memorix_skills` action `generate`, `write: true` | `memorix skills generate --write --target codex` |
| Promote selected memories permanently | `memorix_promote` action `promote` | `memorix memory promote --ids 42,43` |

View the complete source on GitHub

memorix-orchestrate

When your agent uses it

Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.

What it loads into context

Frontmatter

41 tokens

Always available to the agent

SKILL.md

390 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Boundaries

Files

SKILL.mdcore1,663 bytes

Read SKILL.md


# Memorix Orchestrate

Use Memorix coordination for explicit subagent workflows with joined identities, tasks, handoffs, messages, file locks, and orchestrated workers.

The standard setup uses the `lite` MCP profile. Coordination MCP tools are exposed only by `team` or `full`; use the CLI fallback for ordinary installations, or explicitly start the server with `--mode team`. Do not probe unavailable team tools in a loop.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Run managed subagent execution | CLI | `memorix orchestrate --goal "<goal>" --agents claude:1,codex:1` |
| Register coordination identity | `team_manage` action `join` | `memorix team join --agentType <agent>` |
| Create or inspect tasks | `team_task` | `memorix task create|list|claim|complete` |
| Send or read coordination messages | `team_message` | `memorix message send|broadcast|inbox` |

View the complete source on GitHub

memorix-reasoning

When your agent uses it

Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.

What it loads into context

Frontmatter

34 tokens

Always available to the agent

SKILL.md

320 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Use Reasoning When
Do Not Use Reasoning For

Files

SKILL.mdcore1,409 bytes

Read SKILL.md


# Memorix Reasoning

Use reasoning memory for why a decision was made. Use ordinary memory for what happened.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Store why a decision was made | `memorix_store_reasoning` | `memorix reasoning store --entity <name> --decision "<decision>" --rationale "<why>"` |
| Find earlier rationale | `memorix_search_reasoning` | `memorix reasoning search --query "<topic>"` |
| Need a stable evolving topic key | `memorix_suggest_topic_key` | `memorix memory suggest-topic-key --type decision --title "<title>"` |
| Link rationale to commit evidence | `relatedCommits` on reasoning store | `memorix reasoning store ... --relatedCommits <sha>` |

## Use Reasoning When

View the complete source on GitHub

memorix-sessions

When your agent uses it

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether session_start is useful.

What it loads into context

Frontmatter

35 tokens

Always available to the agent

SKILL.md

317 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Tool Router
Decision Rules

Files

SKILL.mdcore1,378 bytes

Read SKILL.md


# Memorix Sessions

`memorix_session_start` is optional. Use it when session semantics help; do not make memory-only work heavier than needed.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Resume a prior long-running task | `memorix_session_start` | `memorix session start --agent <name>` |
| HTTP control plane needs project binding | `memorix_session_start` with `projectRoot` | `memorix session start --projectRoot <absolute-path>` |
| Need recent handoff/session summaries | `memorix_session_context` | `memorix session context` |
| End a real working session | `memorix_session_end` | `memorix session end --sessionId <id> --summary "<summary>"` |
| Need explicit subagent coordination identity | `memorix_session_start` with `joinTeam: true` | `memorix session start --joinTeam --agentType <agent>` |

View the complete source on GitHub

memorix-troubleshooting

When your agent uses it

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

What it loads into context

Frontmatter

40 tokens

Always available to the agent

SKILL.md

335 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Diagnostic Router
Mode Rules

Files

SKILL.mdcore1,529 bytes

Read SKILL.md


# Memorix Troubleshooting

Prefer direct CLI diagnostics first. MCP is an integration surface, not the only way to operate Memorix.

## Diagnostic Router

| Symptom | Check | CLI fallback |
|---|---|---|
| MCP tools missing | host MCP config and restart | `memorix setup --agent <agent>` |
| Unsure project is bound | project status | `memorix status` and `git status` |
| HTTP MCP stale or unbound | background health and explicit session bind | `memorix background status`; then `memorix session start --projectRoot <path>` |
| Hooks not firing | hook status | `memorix hooks status` |
| Need to inspect generated files | preview | `memorix hooks preview --agent <agent>` |
| Setup looks incomplete | reinstall host integration | `memorix setup --agent <agent>` |

View the complete source on GitHub

Skills included

dynamic-resources
calendar
calendar
bad--name
disable-model-invocation
Invalid_Name
invalid-yaml
this-is-a-very-long-skill-name-that-exceeds-the-sixty-four-character-limit-set-by-the-standard
missing-description
multiline-description
different-name
child-skill
unknown-field
valid-skill
memorix
memorix-git-memory
memorix-memory
memorix-mini-skills
memorix-orchestrate
memorix-reasoning
memorix-sessions
memorix-troubleshooting
memorix-git-memory
memorix-memory
memorix-mini-skills
memorix-orchestrate
memorix-reasoning
memorix-sessions
memorix-troubleshooting
memorix-git-memory
memorix-memory
memorix-mini-skills
memorix-orchestrate
memorix-reasoning
memorix-sessions
memorix-troubleshooting
memorix-git-memory
memorix-memory
memorix-mini-skills
memorix-orchestrate
memorix-reasoning
memorix-sessions
memorix-troubleshooting
memorix-git-memory
memorix-memory
memorix-mini-skills
memorix-orchestrate
memorix-reasoning
memorix-sessions
memorix-troubleshooting

Repository facts

License: Apache-2.0
Created: Feb 14, 2026
Last pushed: Nov 5, 2026
Forks: 75
Open issues: 4
Project activity: Active

Rank over the last 12 weeks

Now #957 · best #717 · down 170 in 30 days

#957 on Nov 1
#965 on Nov 2
#963 on Nov 3
#973 on Nov 4
#960 on Nov 5
#957 since Nov 6

78 earlier periods

#754 on Aug 2
#747 on Aug 7
#746 on Aug 8
#790 on Aug 10
#787 on Aug 11
#785 on Aug 12
#786 on Aug 13
#764 on Aug 14
#732 on Aug 15
#750 on Aug 16
#758 on Aug 17
#775 on Aug 18
#760 on Aug 19
#751 on Aug 20
#753 on Aug 21
#717 on Aug 22
#761 on Aug 23
#780 on Aug 24
#794 on Aug 25
#771 on Aug 26
#777 on Aug 27
#804 on Aug 28
#747 on Aug 30
#781 on Aug 31
#799 on Sep 1
#771 on Sep 2
#782 on Sep 3
#756 on Sep 4
#733 on Sep 5
#761 on Sep 6
#774 on Sep 7
#793 on Sep 8
#775 on Sep 9
#786 on Sep 10
#758 on Sep 11
#751 on Sep 12
#752 on Sep 13
#777 on Sep 14
#767 on Sep 15
#772 on Sep 16
#770 on Sep 17
#754 on Sep 18
#728 on Sep 19
#738 on Sep 20
#765 on Sep 21
#786 on Sep 22
#774 on Sep 23
#740 on Sep 24
#721 on Sep 25
#722 on Sep 26
#750 on Sep 27
#771 on Sep 28
#803 on Sep 29
#785 on Sep 30
#749 on Oct 2
#730 on Oct 3
#757 on Oct 4
#771 on Oct 6
#787 on Oct 7
#834 on Oct 8
#797 on Oct 9
#779 from Oct 10 to Oct 11
#803 on Oct 12
#807 on Oct 13
#819 on Oct 14
#805 on Oct 15
#811 on Oct 16
#787 on Oct 17
#774 on Oct 18
#817 on Oct 19
#826 on Oct 20
#839 on Oct 21
#819 on Oct 22
#824 on Oct 23
#777 on Oct 24
#951 on Oct 25
#954 on Oct 28
#956 from Oct 29 to Oct 31

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 10 notes

plugins/claude/memorix/skills/memorix-memory/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/claude/memorix/skills/memorix-memory/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/codebuddy/memorix/skills/memorix-memory/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/codebuddy/memorix/skills/memorix-memory/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/codex/memorix/skills/memorix-memory/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/codex/memorix/skills/memorix-memory/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/copilot/memorix/skills/memorix-memory/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/copilot/memorix/skills/memorix-memory/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/cursor/memorix/skills/memorix-memory/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/cursor/memorix/skills/memorix-memory/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
9 network referencesin 2 files: memorix/.claude-plugin/plugin.json:1 dynamic-resources/dynamic.json:1
No hidden or obfuscated text
No instruction overrides
1 executable scriptin 1 file: dynamic-resources/index.ts:1
No access to secrets
No requests to vote in Hot

Show all 10 signals by file

`packages/memcode/examples/extensions/dynamic-resources/dynamic.json`

Network accessline 1

{ 	"$schema": "https://raw.githubusercontent.com/earendil-works/pi/main/packages/coding-agent/src/modes/interactive/theme/theme-schema.json",

Network accessline 2

"$schema": "https://raw.githubusercontent.com/earendil-works/pi/main/packages/coding-agent/src/modes/interactive/theme/theme-schema.json",

`packages/memcode/examples/extensions/dynamic-resources/index.ts`

Executable scriptline 1
```
Executable file
```

`plugins/claude/memorix/.claude-plugin/plugin.json`

Network accessline 1

{   "$schema": "https://anthropic.com/claude-code/plugin.schema.json",

Network accessline 2

"$schema": "https://anthropic.com/claude-code/plugin.schema.json",

Network accessline 6

"author": {     "name": "AVIDS2",     "url": "https://github.com/AVIDS2"

Network accessline 7

"name": "AVIDS2",     "url": "https://github.com/AVIDS2"   },

Network accessline 8
```
"url": "https://github.com/AVIDS2"
```

Network accessline 9

},   "homepage": "https://mem.rglens.com",   "skills": [

Network accessline 10
```
"homepage": "https://mem.rglens.com",
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 1 fact

Executable script in code of a file that runsdynamic-resources/index.ts:1High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Manifest plugins/claude/memorix/.claude-plugin/plugin.json	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md packages/memcode/examples/extensions/dynamic-resources/SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md packages/memcode/examples/extensions/dynamic-resources/SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Native	Manifest plugins/gemini/memorix/gemini-extension.json	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md packages/memcode/examples/extensions/dynamic-resources/SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Native	Path .opencode/plugins/memorix.js	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![AVIDS2/memorix on hotskills](https://hotskills.dev/badge/avids2-memorix.svg)](https://hotskills.dev/skill/avids2-memorix/)

AVIDS2/memorix

History

packages/memcode/examples/extensions/dynamic-resources/SKILL.md

packages/memcode/test/fixtures/skills-collision/first/calendar/SKILL.md

packages/memcode/test/fixtures/skills-collision/second/calendar/SKILL.md

packages/memcode/test/fixtures/skills/consecutive-hyphens/SKILL.md

packages/memcode/test/fixtures/skills/disable-model-invocation/SKILL.md

packages/memcode/test/fixtures/skills/invalid-name-chars/SKILL.md

packages/memcode/test/fixtures/skills/invalid-yaml/SKILL.md

packages/memcode/test/fixtures/skills/long-name/SKILL.md

packages/memcode/test/fixtures/skills/missing-description/SKILL.md

packages/memcode/test/fixtures/skills/multiline-description/SKILL.md

packages/memcode/test/fixtures/skills/name-mismatch/SKILL.md

packages/memcode/test/fixtures/skills/nested/child-skill/SKILL.md

packages/memcode/test/fixtures/skills/no-frontmatter/SKILL.md

packages/memcode/test/fixtures/skills/root-skill-preferred/SKILL.md

packages/memcode/test/fixtures/skills/root-skill-preferred/nested-child/SKILL.md

packages/memcode/test/fixtures/skills/unknown-field/SKILL.md

packages/memcode/test/fixtures/skills/valid-skill/SKILL.md

plugins/claude/memorix/SKILL.md

plugins/claude/memorix/skills/memorix-git-memory/SKILL.md

plugins/claude/memorix/skills/memorix-memory/SKILL.md

plugins/claude/memorix/skills/memorix-mini-skills/SKILL.md

plugins/claude/memorix/skills/memorix-orchestrate/SKILL.md

plugins/claude/memorix/skills/memorix-reasoning/SKILL.md

plugins/claude/memorix/skills/memorix-sessions/SKILL.md

plugins/claude/memorix/skills/memorix-troubleshooting/SKILL.md

plugins/codebuddy/memorix/skills/memorix-git-memory/SKILL.md

plugins/codebuddy/memorix/skills/memorix-memory/SKILL.md

plugins/codebuddy/memorix/skills/memorix-mini-skills/SKILL.md

plugins/codebuddy/memorix/skills/memorix-orchestrate/SKILL.md

plugins/codebuddy/memorix/skills/memorix-reasoning/SKILL.md

plugins/codebuddy/memorix/skills/memorix-sessions/SKILL.md

plugins/codebuddy/memorix/skills/memorix-troubleshooting/SKILL.md

plugins/codex/memorix/skills/memorix-git-memory/SKILL.md

plugins/codex/memorix/skills/memorix-memory/SKILL.md

plugins/codex/memorix/skills/memorix-mini-skills/SKILL.md

plugins/codex/memorix/skills/memorix-orchestrate/SKILL.md

plugins/codex/memorix/skills/memorix-reasoning/SKILL.md

plugins/codex/memorix/skills/memorix-sessions/SKILL.md

plugins/codex/memorix/skills/memorix-troubleshooting/SKILL.md

plugins/copilot/memorix/skills/memorix-git-memory/SKILL.md

plugins/copilot/memorix/skills/memorix-memory/SKILL.md

plugins/copilot/memorix/skills/memorix-mini-skills/SKILL.md

plugins/copilot/memorix/skills/memorix-orchestrate/SKILL.md

plugins/copilot/memorix/skills/memorix-reasoning/SKILL.md

plugins/copilot/memorix/skills/memorix-sessions/SKILL.md

plugins/copilot/memorix/skills/memorix-troubleshooting/SKILL.md

plugins/cursor/memorix/skills/memorix-git-memory/SKILL.md

plugins/cursor/memorix/skills/memorix-memory/SKILL.md

plugins/cursor/memorix/skills/memorix-mini-skills/SKILL.md

plugins/cursor/memorix/skills/memorix-orchestrate/SKILL.md

plugins/cursor/memorix/skills/memorix-reasoning/SKILL.md

plugins/cursor/memorix/skills/memorix-sessions/SKILL.md

plugins/cursor/memorix/skills/memorix-troubleshooting/SKILL.md

plugins/pi/memorix/skills/memorix-git-memory/SKILL.md

plugins/pi/memorix/skills/memorix-memory/SKILL.md

plugins/pi/memorix/skills/memorix-mini-skills/SKILL.md

plugins/pi/memorix/skills/memorix-orchestrate/SKILL.md

plugins/pi/memorix/skills/memorix-reasoning/SKILL.md

plugins/pi/memorix/skills/memorix-sessions/SKILL.md

plugins/pi/memorix/skills/memorix-troubleshooting/SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

dynamic-resources

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

calendar

Frontmatter

SKILL.md

Reference documents

The playbook

Files

`packages/memcode/examples/extensions/dynamic-resources/SKILL.md`

`packages/memcode/test/fixtures/skills-collision/first/calendar/SKILL.md`

`packages/memcode/test/fixtures/skills-collision/second/calendar/SKILL.md`

`packages/memcode/test/fixtures/skills/consecutive-hyphens/SKILL.md`

`packages/memcode/test/fixtures/skills/disable-model-invocation/SKILL.md`

`packages/memcode/test/fixtures/skills/invalid-name-chars/SKILL.md`

`packages/memcode/test/fixtures/skills/invalid-yaml/SKILL.md`

`packages/memcode/test/fixtures/skills/long-name/SKILL.md`

`packages/memcode/test/fixtures/skills/missing-description/SKILL.md`

`packages/memcode/test/fixtures/skills/multiline-description/SKILL.md`

`packages/memcode/test/fixtures/skills/name-mismatch/SKILL.md`

`packages/memcode/test/fixtures/skills/nested/child-skill/SKILL.md`

`packages/memcode/test/fixtures/skills/no-frontmatter/SKILL.md`

`packages/memcode/test/fixtures/skills/root-skill-preferred/SKILL.md`

`packages/memcode/test/fixtures/skills/root-skill-preferred/nested-child/SKILL.md`

`packages/memcode/test/fixtures/skills/unknown-field/SKILL.md`

`packages/memcode/test/fixtures/skills/valid-skill/SKILL.md`

`plugins/claude/memorix/SKILL.md`

`plugins/claude/memorix/skills/memorix-git-memory/SKILL.md`

`plugins/claude/memorix/skills/memorix-memory/SKILL.md`

`plugins/claude/memorix/skills/memorix-mini-skills/SKILL.md`

`plugins/claude/memorix/skills/memorix-orchestrate/SKILL.md`

`plugins/claude/memorix/skills/memorix-reasoning/SKILL.md`

`plugins/claude/memorix/skills/memorix-sessions/SKILL.md`

`plugins/claude/memorix/skills/memorix-troubleshooting/SKILL.md`

`plugins/codebuddy/memorix/skills/memorix-git-memory/SKILL.md`

`plugins/codebuddy/memorix/skills/memorix-memory/SKILL.md`

`plugins/codebuddy/memorix/skills/memorix-mini-skills/SKILL.md`

`plugins/codebuddy/memorix/skills/memorix-orchestrate/SKILL.md`

`plugins/codebuddy/memorix/skills/memorix-reasoning/SKILL.md`

`plugins/codebuddy/memorix/skills/memorix-sessions/SKILL.md`

`plugins/codebuddy/memorix/skills/memorix-troubleshooting/SKILL.md`

`plugins/codex/memorix/skills/memorix-git-memory/SKILL.md`

`plugins/codex/memorix/skills/memorix-memory/SKILL.md`

`plugins/codex/memorix/skills/memorix-mini-skills/SKILL.md`

`plugins/codex/memorix/skills/memorix-orchestrate/SKILL.md`

`plugins/codex/memorix/skills/memorix-reasoning/SKILL.md`

`plugins/codex/memorix/skills/memorix-sessions/SKILL.md`

`plugins/codex/memorix/skills/memorix-troubleshooting/SKILL.md`

`plugins/copilot/memorix/skills/memorix-git-memory/SKILL.md`

`plugins/copilot/memorix/skills/memorix-memory/SKILL.md`

`plugins/copilot/memorix/skills/memorix-mini-skills/SKILL.md`

`plugins/copilot/memorix/skills/memorix-orchestrate/SKILL.md`

`plugins/copilot/memorix/skills/memorix-reasoning/SKILL.md`

`plugins/copilot/memorix/skills/memorix-sessions/SKILL.md`

`plugins/copilot/memorix/skills/memorix-troubleshooting/SKILL.md`

`plugins/cursor/memorix/skills/memorix-git-memory/SKILL.md`

`plugins/cursor/memorix/skills/memorix-memory/SKILL.md`

`plugins/cursor/memorix/skills/memorix-mini-skills/SKILL.md`

`plugins/cursor/memorix/skills/memorix-orchestrate/SKILL.md`

`plugins/cursor/memorix/skills/memorix-reasoning/SKILL.md`

`plugins/cursor/memorix/skills/memorix-sessions/SKILL.md`

`plugins/cursor/memorix/skills/memorix-troubleshooting/SKILL.md`

`plugins/pi/memorix/skills/memorix-git-memory/SKILL.md`

`plugins/pi/memorix/skills/memorix-memory/SKILL.md`

`plugins/pi/memorix/skills/memorix-mini-skills/SKILL.md`

`plugins/pi/memorix/skills/memorix-orchestrate/SKILL.md`

`plugins/pi/memorix/skills/memorix-reasoning/SKILL.md`

`plugins/pi/memorix/skills/memorix-sessions/SKILL.md`

`plugins/pi/memorix/skills/memorix-troubleshooting/SKILL.md`