Skip to content
Skills Library
AI & agents · Automation

workspace-knowledge-sync

/workspace-knowledge-sync

Syncs knowledge to the agentic-harness knowledge base and AGENTS.md learned facts. Use when the assistant discovers new patterns, learns user preferences, workspace facts, or identifies information worth preserving for future sessions. Integrates with platform-engineer (formerly tech-assistant) for automatic trigger points.

Licence
MIT
Last repository change
25.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Syncs knowledge to the agentic-harness knowledge base and AGENTS.md learned facts. Use when the assistant discovers new patterns, learns user preferences, workspace facts, or identifies information worth preserving for future sessions. Integrates with platform-engineer (formerly tech-assistant) for automatic trigger points.

Original author description

Syncs knowledge to the agentic-harness knowledge base and AGENTS.md learned facts. Use when the assistant discovers new patterns, learns user preferences, workspace facts, or identifies information worth preserving for future sessions. Integrates with platform-engineer (formerly tech-assistant) for automatic trigger points.

How it works

  1. Purpose
  2. Trigger Points (Automatic)
  3. How It Works
  4. Knowledge Structure
  5. Learned Facts — Criteria and Guardrails
  6. Manual Usage
  7. Integration with platform-engineer (formerly tech-assistant)
  8. Best Practices
  9. Examples
  10. Configuration
Original SKILL.md headings · 211 lines, 942 words
SKILL.md preview
---
name: workspace-knowledge-sync
description: Syncs knowledge to the agentic-harness knowledge base and AGENTS.md learned facts.
  Use when the assistant discovers new patterns, learns user preferences, workspace facts,
  or identifies information worth preserving for future sessions. Integrates with platform-engineer
  (formerly tech-assistant) for automatic trigger points.
origin:
  type: first-party
metadata:
  inspired_by:
    - repository: cursor/plugins
      path: continual-learning/skills/continual-learning
      ref: 60c641e4fad674784b30abcf9f8915dea39df38d
      note: Durable learned facts (user preferences / workspace facts), plain-bullet AGENTS.md
        sections, deduplication and 12-bullet cap; adapted without hooks/transcript mining to explicit sync
---

# Workspace Knowledge Sync

Automatically syncs valuable discoveries, patterns, and decisions to the agentic-harness knowledge base and durable `AGENTS.md` learned facts.

---

## Purpose

The orchestrator session accumulates knowledge through work. This skill ensures that valuable discoveries don't get lost and are available for future sessions — both in the workspace knowledge base (`knowledge/`) and as durable learned facts in `AGENTS.md`.

Inspired by `cursor/plugins` `continual-learning` (without hooks — no transcript mining or `stop` hook).

---

## Trigger Points (Automatic)

The platform-engineer (archived `tech-assistant` — now inline `references/WORKSTATION_OPS.md`) will invoke this skill automatically when:

| Situation | What to Sync | Target |
|-----------|--------------|--------|
| Discovery of new skill/tool | Skill name, purpose, usage pattern | `knowledge/skills/discovered.md` |
| New process pattern | Process steps, roles, tools | `knowledge/processes/general.md` |
| Key decision made | Decision, rationale, outcome | `knowledge/learnings/general.md` |
| Pending follow-up | Task description, context | `knowledge/todos/pending.md` |
| User teaches something | Information, preference | Relevant knowledge file |
| Recurring user preference / correction | Plain bullet, durable preference | `AGENTS.md` → `## Learned User Preferences` |
| Stable workspace fact | Plain bullet, durable fact | `AGENTS.md` → `## Learned Workspace Facts` |

---

## How It Works

### Knowledge base (`agent-toolkit memory`)

The skill uses the stable `agent-toolkit memory` API with `--from-skill` for origin tracking (harness alias: `assistant-memory` / `bin/assistant-memory`):

```bash
# Search before adding
agent-toolkit memory search "<query>"

# Add a learning (with origin tracking)
agent-toolkit memory add --type learning --from-skill knowledge-sync "Pattern: <description>"

# Add a skill (with tags)
agent-toolkit memory add --type skill --from-skill knowledge-sync --tags jira,workflow "New skill: <name>"

# Add a pending todo
agent-toolkit memory add --type todo --from-skill knowledge-sync "<description>"
```

### Learned facts (AGENTS.md)

For durable, reusable facts that should survive across sessions, update `AGENTS.md` directly:

1. Read existing `AGENTS.md` first. If it does not exist, create it with only:
   - `## Learned User Preferences`
   - `## Learned Workspace Facts`
2. Pull out only durable, reusable items:
   - recurring user preferences or corrections
   - stable workspace facts
3. Update `AGENTS.md` carefully:
   - update matching bullets in place
   - add only net-new bullets
   - deduplicate semantically similar bullets
   - keep each learned section to at most 12 bullets
4. If the merge produces no `AGENTS.md` changes, leave `AGENTS.md` unchanged.

No hooks, no transcript index, no `followup_message` — the sync is explicit (manual or via platform-engineer trigger), not hook-driven.

---

## Knowledge Structure

```
knowledge/
├── skills/
│   └── discovered.md      # New skills found during work
├── processes/
│   ├── jira.md
│   ├── confluence.md
│   └── general.md        # Generic process patterns
├── learnings/
│   └── general.md        # Key decisions and insights
└── todos/
    └── pending.md        # Follow-up items

AGENTS.md (workspace root)
├── ## Learned User Preferences   # max 12 plain bullets
└── ## Learned Workspace Facts    # max 12 plain bullets
```

---

## Learned Facts — Criteria and Guardrails

Inspired by `continual-learning` `agents-memory-updater` (adapted without transcript mining):

**Include only:**
- Recurring user preferences or corrections (e.g., "Always use feature branches", "Prefer pnpm over npm")
- Stable workspace facts (e.g., "Primary DB is Postgres 16 on host X", "Deploy via Vercel")

**Exclude:**
- Secrets, private data, tokens, credentials
- One-off instructions or transient details
- Evidence/confidence tags, process instructions, rationale blocks, or metadata

**Format:**
- Plain bullet points only (`- ...`)
- Keep only these sections: `## Learned User Preferences`, `## Learned Workspace Facts`
- No tables, no tags, no frontmatter in these sections

**Limits:**
- At most 12 bullets per section; deduplicate semantically similar bullets
- Update in place when a bullet already exists with similar meaning

---

## Manual Usage

You can also trigger this skill manually:

```
User: "Save that pattern for later"

Assistant: → Use knowledge-sync to preserve the pattern

User: "Remember I prefer pnpm and conventional commits"

Assistant: → Append to knowledge/learnings/general.md and AGENTS.md ## Learned User Preferences
```

---

## Integration with platform-engineer (formerly tech-assistant)

The platform-engineer (archived `tech-assistant` → `references/WORKSTATION_OPS.md`) checks for these automatic sync opportunities:

1. **After task creation/update** → Sync initiative info
2. **After discovering space/list IDs** → Sync to knowledge base (per `knowledge-sync`).
3. **After learning user preferences** → Sync to learnings + `AGENTS.md` learned facts (if durable)
4. **When user mentions follow-up** → Add to pending
5. **After stable workspace facts emerge** → Sync to `AGENTS.md` `## Learned Workspace Facts`

---

## Best Practices

1. **Be selective** - Only sync valuable, reusable information
2. **Be specific** - Include context and usage examples
3. **Be concise** - One idea per entry, link to details
4. **Be current** - Update outdated information when found
5. **Be durable** - AGENTS.md facts must be reusable across sessions, not transient

---

## Examples

### Auto-sync discovery

```
Assistant discovers Initiative list IDs for all Technology spaces
→ Syncs to knowledge/processes/clickup/spaces/
```

### Auto-sync key decision

```
Assistant and user decide on naming convention
→ Syncs to knowledge/learnings/general.md
```

### Learned fact — user preference

```
User repeatedly corrects: "use pnpm, not npm"
→ Assistant adds to AGENTS.md:
  ## Learned User Preferences
  - Use pnpm for JS package management
```

### Learned fact — workspace fact

```
Workspace uses Postgres 16 with vector extension on host db.internal
→ Assistant adds to AGENTS.md:
  ## Learned Workspace Facts
  - Postgres 16 with pgvector on db.internal
```

### Manual sync request

```
User: "Remember that we always use feature branches"
→ Assistant syncs to knowledge/processes/general.md and AGENTS.md ## Learned User Preferences
```

---

## Configuration

The skill uses these environment variables:

| Variable | Default | Purpose |
|----------|---------|---------|
| `KNOWLEDGE_BASE_PATH` | `~/.ai-workspace/knowledge` | Knowledge base root |

---

Base directory: `~/.local/share/knowledge-sync` (installer path; `~/.local/share/agent-toolkit/` when using toolkit install)

Versions

The database has no other skills named workspace-knowledge-sync.

Identical content appears in 6 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version a93341ab35a2 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100journal-record
    Use when you've learned something worth remembering — a decision, design rationale, user behavior pattern, process learning, research finding, or style convention. Records it to the persistent team knowledge graph for future sessions.
  • 100memos-memory
    Use when the user shares durable facts worth persisting across sessions (preferences, project decisions, environment setup, corrections), asks to remember or recall something, or when a question may depend on prior sessions. Drives the local MemOS MCP server (memos_* tools, all…
  • 92agent-memory
    Persist and retrieve repository-specific knowledge using AGENTS.md files. Use when you want to save important information about a codebase (build commands, code style, workflows) for future sessions.
  • 100lavra-knowledge
    Capture solved problems as knowledge entries for fast recall. Use when a solution should be preserved for future sessions.
  • 86knowledge-capture
    Save durable preferences, decisions, project facts, commitments, and lessons cheaply with knowledge_remember, or short notes and page updates with attribution and readback. Use for explicit saves or agent-driven remembering when Knowledge is the selected memory provider.
  • 100knowledge-sync
    Use when the developer wants Opem's assistant to answer from documentation kept in their repository: Markdoc or Markdown documents, front matter, access tags for roles, syncDocuments from @opem/node, PUT /api/v1/manage/knowledge/documents, a GitHub Actions workflow that syncs on…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.