add-memory
Add a memory system to an agent — file awareness, knowledge graph, structured state, or multi-session tracking
Skill by Ability.ai
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/abilityai-add-memory
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/add-memory
Tools it pre-approves 6
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Write,Bash,Glob,Grep,AskUserQuestion
What's inside
- Skill name
add-memory- Description
- Add a memory system to an agent — file awareness, knowledge graph, structured state, or multi-session tracking
- License
- Apache-2.0
- Allowed tools
- Read,, Write,, Bash,, Glob,, Grep,, AskUserQuestion
- Metadata
- author: Ability.ai · mirror: abilities@716a45a plugins/agent-dev/skills/add-memory · created: 2026-04-16 · updated: 2026-05-16 · version: 1.1.1
- Instructions
- 122 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (1)
- SKILL.md
SKILL.md (first lines)
# Add Memory
> ℹ️ **First, set expectations:** before anything else, print one short line with this skill's version and its most recent change — the top entry of `metadata.changelog` above — e.g. `add-memory vX.Y — recent: <summary>`. Then proceed.
Add a memory system to an existing agent. Memory skills are COPIED into the agent's `.claude/skills/` directory — the agent becomes self-contained with no plugin dependency.
## Memory Types
| Type | Description | Skills Installed |
|------|-------------|------------------|
| **file-index** | File system awareness — creates and maintains a searchable file index | setup-index, refresh-index, search-files |
| **brain** | Zettelkasten-style knowledge graph — atomic notes with connections | setup-brain, create-note, search-brain, find-connections |
| **json-state** | Structured JSON state with jq-based updates and action logging | setup-memory, load-memory, update-memory, memory-jq |
| **workspace** | Multi-session project tracking — organized folders, sessions, archives | setup-projects, create-project, create-session, archive-project |
## Process
### Step 1: Determine Agent Directory
Check if we're in an agent directory (has CLAUDE.md) or if user specified a path.
```bash
# Check current directory
if [ -f "CLAUDE.md" ]; then
AGENT_DIR="$(pwd)"
else
# Ask user for agent path
fi
```
If no CLAUDE.md found, ask:
- **Question:** "What agent should I add memory to?"
- **Hint:** "Enter the path to the agent directory (should contain CLAUDE.md)"
### Step 2: Check Argument or Ask Memory Type
If user provided an argument (e.g., `/agent-dev:add-memory brain`), use that.
Otherwise, use AskUserQuestion:
- **Question:** "What kind of memory does this agent need?"
- **Header:** "Add Memory"
- **Options:**
1. **File awareness (file-index)** — "I need the agent aware of workspace files"
- Creates a searchable index of files in the workspace
- Good for: agents that need to find and reference files
2. **Knowledge graph (brain)** — "I need connected notes, evolving knowledge"
- Zettelkasten-style atomic notes with connections
- Good for: research agents, knowledge management, idea linking
3. **Structured state (json-state)** — "I need counters, config, structured data"
- JSON-based state with efficient jq updates
- Good for: tracking metrics, configuration, action logs
4. **Multi-session workspace (workspace)** — "I need organized projects and sessions"
- Project folders with session tracking and archiving
- Good for: long-running work, multiple parallel projects
### Step 3: Copy Memory Skills
Memory templates are stored in this plugin at:
```
agent-dev/memory-templates/
file-index/ # setup-index/, refresh-index/, search-files/
brain/ # setup-brain/, create-note/, search-brain/, find-connections/
json-state/ # setup-memory/, load-memory/, update-memory/, memory-jq/
workspace/ # setup-projects/, create-project/, create-session/, archive-project/
```
Copy the selected memory type's skills into the agent:
```bash
# Get the plugin directory (where this skill lives)
PLUGIN_DIR="$(dirname "$(dirname "$(dirname "${0}")")")"
TEMPLATES_DIR="$PLUGIN_DIR/memory-templates"
# Copy skills to agent
cp -r "$TEMPLATES_DIR/[selected-type]/"* "$AGENT_DIR/.claude/skills/"
```
### Step 4: Update Agent CLAUDE.md
Add a section documenting the new memory capabilities:
```markdown
## Memory: [Type Name]
This agent has [type] memory installed. Available skills:
- `/[skill-1]` — description
- `/[skill-2]` — description
...
Run `/[setup-skill]` to initialize.
```
### Step 5: Confirm and Guide
Output:
```markdown
## Memory Added
Installed **[type]** memory to `[agent-name]`.
### New Skills
- `/[skill-1]` — description
- `/[skill-2]` — description
### Next Step
Run `/[setup-skill]` to initialize the memory system.
```
## Notes
- Skills are COPIED, not linked — agent becomes self-contained
- Multiple memory types can be installed in the same agent
- If skills already exist (duplicate names), warn and ask before overwriting
- The setup skill initializes the memory system (creates directories, indexes, etc.)From Abilityai/trinity-skills, Apache-2.0.
More from Abilityai/trinity-skills
- 0.570score
file-indexer
Abilityai
Generate a comprehensive file system index with directory tree, file sizes, and modification dates.
SkillAFreshness: AClaude Code +9 - 0.570score
explain-visually
Ability.ai
Explain a complex topic back to you with visuals - the right diagram for each facet (flowchart, timeline, sequence, schema/ER, state machine, chart…
SkillAFreshness: AClaude Code - 0.570score
animated-explainer
Ability.ai
Build an animated, data-driven explainer film for a real system — a canvas film that renders live from the product's own data and cannot drift, not an…
SkillAFreshness: AClaude Code - 0.567score
gemini-critic
Ability.ai
Ask Gemini's most powerful model for an independent second opinion - critique code with fresh eyes, evaluate an article, challenge a plan.
SkillAFreshness: AClaude Code +9 - 0.566score
agent-fleet-analysis
Ability.ai
Scan one or more directories of agents in ANY paradigm — Claude Code, n8n workflow exports, framework apps (LangChain/CrewAI/AutoGen), or freeform-coded…
SkillAFreshness: AClaude Code +9 - 0.565score
document-extractor
Abilityai
Extracts key information from documents (PDFs, images, text files) in a folder and creates structured markdown summaries with the same filename but .md…
SkillAFreshness: AClaude Code +9 - 0.565score
add-pipeline
Ability.ai
Scaffold a Trinity-compatible long-running pipeline inside any agent — creates projects/<slug>/{project.md, pipeline.yaml, instances/}, copies…
SkillAFreshness: AClaude Code - 0.561score
create-playbook
Ability.ai
Create a new skill or playbook.
SkillAFreshness: AClaude Code +9 - 0.561score
close
Ability.ai
Close the current issue without a git commit — adds summary comment and marks done.
SkillAFreshness: AClaude Code +9 - 0.561score
create-explanatory-image
Ruby
Generate explanatory diagrams and infographics that visually communicate concepts.
SkillAFreshness: AClaude Code +9 - 0.561score
autoplan
Ability.ai
Analyze a skill issue before implementing — reads the affected SKILL.md, identifies what changes are needed and any risks
SkillAFreshness: AClaude Code +9 - 0.561score
add-git-sync
Ability.ai
Add git-as-state hooks to an agent — auto-commits on Stop, rebases on SessionStart, snapshots on PreCompact.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 1
- Last commit (this folder)
- Oct 10, 2026 (20 days ago)
- Last release
- Oct 21, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.1.1
- License
- Apache-2.0
- Repository
- github.com/Abilityai/trinity-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Ability.ai
- 0.570score
animated-explainer
Ability.ai
Build an animated, data-driven explainer film for a real system — a canvas film that renders live from the product's own data and cannot drift, not an…
SkillAFreshness: AClaude Code - 0.570score
explain-visually
Ability.ai
Explain a complex topic back to you with visuals - the right diagram for each facet (flowchart, timeline, sequence, schema/ER, state machine, chart…
SkillAFreshness: AClaude Code - 0.567score
gemini-critic
Ability.ai
Ask Gemini's most powerful model for an independent second opinion - critique code with fresh eyes, evaluate an article, challenge a plan.
SkillAFreshness: AClaude Code +9 - 0.566score
agent-fleet-analysis
Ability.ai
Scan one or more directories of agents in ANY paradigm — Claude Code, n8n workflow exports, framework apps (LangChain/CrewAI/AutoGen), or freeform-coded…
SkillAFreshness: AClaude Code +9 - 0.565score
add-pipeline
Ability.ai
Scaffold a Trinity-compatible long-running pipeline inside any agent — creates projects/<slug>/{project.md, pipeline.yaml, instances/}, copies…
SkillAFreshness: AClaude Code - 0.561score
close
Ability.ai
Close the current issue without a git commit — adds summary comment and marks done.
SkillAFreshness: AClaude Code +9
Cite this page
add-memory skill. Agent Mart. https://agentmart.dev/skills/abilityai-add-memory (last updated 2026-10-24)