The primary interface for managing knowledge and structured data within a Synap pod.
Install
mkdir -p .claude/skills/synap && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14414" && unzip -o skill.zip -d .claude/skills/synap && rm skill.zipInstalls to .claude/skills/synap
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use this skill whenever the user wants to capture, remember, find, or structure information in their Synap data pod. Triggers: creating a task, note, person, company, project, event, contact, or deal; saving an article or webpage; storing a fact about someone ("Alice prefers async"); searching the user's knowledge ("find my notes on X", "who did I meet last week"); linking entities; logging a meeting or a contact; capturing unstructured text into structured entities; reading what's in the user's pod before answering questions about their life, work, or projects; posting to their personal AI channel. The pod is the user's sovereign source of truth — prefer it over your own context when the user asks about their own data. Do NOT use this skill for extending the schema (use synap-schema) or building dashboards and views (use synap-ui).Key capabilities
- →Capture unstructured text into structured entities
- →Retrieve information from the user's data pod
- →Link entities within a knowledge graph
- →Log meetings or contacts
- →Read existing data before answering questions
- →Post to personal AI channels
How it works
The skill interacts with a Synap Data Pod to capture, retrieve, and structure information. It prioritizes recalling existing knowledge before creating new entries and treats 'proposed' responses as successful-in-review.
Inputs & outputs
When to use synap
- →Capture new task in pod
- →Search notes on project
- →Link entities in knowledge graph
About this skill
Synap — core data operations
You are connected to a Synap Data Pod at {SYNAP_POD_URL}. All requests use Authorization: Bearer {SYNAP_HUB_API_KEY}.
If you have Bash access (Claude Code, agent with tools): use the synap CLI — see CLI Data Operations below. Auth is automatic, --json gives clean output, no manual header management.
If you only have HTTP access: use the REST endpoints documented below. Your userId is in {SYNAP_USER_ID} (set by synap connect). If it's missing, call GET /api/hub/users/me → .id once.
Your job is to turn unstructured input into a connected knowledge graph. Isolated entities are anti-value. Every entity you create should link to at least one other entity.
Reflexes — what holds on every door
Canonical source — the MCP
instructionsfield is derived from this file and composed with live grounding under ONE 2 KB budget (pinned byinstructions-budget.test.ts). Most important first. Depth belongs in a skill, never here.
The user's Synap pod: source of truth for their life, work and people. Tool names below are stems; your door may prefix them (synap_ask, pod__ask).
- Recall first. Before answering about the user's world or creating,
ask(no duplicates). - Capture after. A durable fact, decision, person, task:
capture; about the user:remember_fact. No private scratchpad. - Orient once.
orient: pending review (raise first), open sessions, kinds, actions. - Work in a session.
start_sessionor resume (playbooktemplateId); project method = TRACK:list_tracks, elsestart_track; stepsstart_stage_session;advance_trackonly with the user; 2-5criteria; advancecurrentStage; person-only:owner:'human'outputs +blockedReason, thenwait_for_answerif listed; post progress, questions and results in its room (post_messagetosession.channelId); your own chat may repeat them;evaluate_sessionbeforecomplete_session. - Never guess a project. Pin what the user names:
set_workspace_focus/set_project_focus. Unset is safe. proposedis success, queued for review. Keep going; never retry.- Discover before inventing.
list_profiles/list_capabilitiesbefore defining a kind, role, space. Extend first (facet, overlay, parent); never a twin.
Depth via load_skill: system/synap/concepts, focus-sessions, from-intent (new area), escalation-ladder, writes, catalog.
Concepts — one word per idea
The ONE glossary; other skills point here. Word = what the user sees; internal = tools and tables.
| Word | Internal | Answers | Test · e.g. · not |
|---|---|---|---|
| Space | workspace | which domain: kinds + tools? | owns kinds, never done · CRM · not a project or method; findable, not emphasised |
| Project | project | what am I committed to, with whom? | ends with the commitment; spans spaces · a launch · not a task, method, or the owner's company |
| Track | project_tracks | how does one outcome move over time? | step progress inside ONE project · business model · owns no space: each step names its domain |
| Step | stage | which stretch of the track? | holds work over many sittings · repeating work = open-ended step + a Rule starting work into it |
| Work | focus_session | what am I doing this sitting? | one goal · no noun: "Start work" |
| Template | playbook | how do I reuse it? | kind DERIVED, never declared: scope session = work template, project = track template; also space and rule templates |
| Pack | suite | which templates come together? | a bundle; depends on space templates, never creates a space |
| Rule | automation | what runs by itself, when? | standing · "every Monday…" · not Approvals |
| Approvals | governance rules | which AI writes wait for me? | decides review vs auto, does no work |
| Tools | capability, skill, tool | what can it act with? | one word; the detail shows the kind |
| To review | proposal | what awaits my approval? | proposed is success |
| Role | role profile + facet | which hat does it wear? | one role per name, pod-wide; spaces add properties by overlay; its entities show in all · client · never a twin |
Doors: start_track, start_stage_session, start_session, create_rule, attach_facet.
Work a method on a project: list_tracks → none? list_playbooks (scope project = track template) → start_track; each step start_stage_session; never advance_track without the user. Detail: from-intent.
Existing work can be filed into a step with update_session trackId/trackStage (proposed; the session keeps its space).
Escalation ladder — discover → invent under proposal → crystallize after proof
The always-on brief lives in reflexes.md, which points here. This file is the full HOW when you need more than the corner-of-your-head reminder.
No private scratchpad. Everything you learn goes into the shared graph, not a hidden note. Capture a proven tool-fact into knowledge immediately; PROMOTE it into a curated skill only once it's proven reusable — a skill is a versioned artifact (one capability, when-to-use + do/don't), never an append-anything log.
Why it exists
Agents fail in two ways: (1) dead-end ("I can't do that") when the substrate could express the need after discovery or a proposed meta change, and (2) silent invent (minting workspaces/profiles/views without checking what already exists). The ladder is the habit that prevents both. Soft teaching only — no hard tool filtering by tier.
Levels
L0 — Reflexes (always)
Recall before non-trivial work (synap_ask / search). Capture durable learning after. Treat "proposed" as success-in-review, not an error. Orient once per session.
L1 — OPERATE on data
Default mode: work with what already exists.
- Capture free text, create/update entities, link, attach known facets
- Start/update sessions when the work is a unit with a deliverable
- Prefer existing profiles, views, capabilities, playbooks over inventing structure
L2 — DISCOVER before invent
When the tool list or current schema doesn't express the need — search before minting:
list_profiles/list_views/list_capabilities({query})in the active lensesmarket.search({query, kind?})overcapability|template|automation|cell- Load the relevant skill (
load_skill/ discover_tools) if the HOW is unclear. User stated a new area of work →system/synap/from-intent(conductor). Schema extend vs invent →system/synap-schema/extend-first. Missing domain workspace →system/agent-os/skill.
Only if L2 returns empty for the real need do you climb to L3.
L3 — MUTATE the meta-model (proposal-gated)
Extend the substrate so the need becomes expressible. Always governed — expect "proposed".
| Need | Prefer | Tool sketch |
|---|---|---|
| Hat on a kind the role doesn't list yet | Widen applicableKinds | define_role same slug + extra kinds (merge). Hats attach to any kind, not only person/company |
| Role/hat missing | Existing role attach | define_role only after list_profiles empty for that role |
| Field missing | Existing property | define_kind with the existing kind's slug + the new field in properties[] (slug-idempotent) |
| Kind missing | Closest parent kind | define_kind (extend, don't fork). Pod-wide by default — pass entityScope:'workspace' only for an app-specific kind |
| View missing | Existing view | list_views first, then create_view (recovery or proactive) |
| Domain missing | Template | market.search(kind:template) → install/propose before freehand create_workspace |
| Capability missing | Marketplace | market.install (always proposes for agents) |
Template-before-workspace (hard rule in teaching): new operational domains start as marketplace templates when one fits. Freehand workspace creation is last
Content truncated.
When not to use it
- →When extending the schema
- →When building dashboards and views
- →When inventing workspaces from capture
Prerequisites
Limitations
- →Do NOT use this skill for extending the schema
- →Do NOT use this skill for building dashboards and views
- →Capture placement routes to EXISTING lenses only , never invent a workspace from capture
How it compares
This skill provides a structured way to manage personal data as a 'sovereign source of truth,' differing from relying on the agent's own context or training data for user-specific information.
Compared to similar skills
synap side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| synap (this skill) | 0 | 3mo | Review | Intermediate |
| agent-memory-mcp | 8 | 8mo | Review | Intermediate |
| braindump | 7 | 7mo | No flags | Beginner |
| context-management | 1 | 10mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
agent-memory-mcp
davila7
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
braindump
huytieu
Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction
context-management
No-Trade-No-Life
在多轮对话和多 Agent 协作场景下，帮助模型管理指令、项目状态和长上下文。通过外部文档与会话笔记实现可控的“记忆”、指令冲突检测和高质量交接。适用于任务跨多次调用、跨 Agent、需要稳定行为规范时使用。
hindsight-cloud
vectorize-io
Store team knowledge, project conventions, and learnings from tasks. Use to remember what works and recall context before new tasks. Connects to Hindsight Cloud. (user)
ask
Lambenthan
对 wiki 提问，综合检索相关页面后回答，好的回答可 crystallize 回 wiki
knowledge-ops
ThanhTrunggDEV
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.