yaaif-create-file-workflow
Create a custom file workflow on YAA\F via the Cursor MCP bridge: an ambient workflow that runs when an uploaded file finishes extraction (file.ready /…
Skill by yaaif
Chalk Labs
Need help deploying yaaif-create-file-workflow?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/yaaif-yaaif-create-file-workflow
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: productivity, 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/yaaif-create-file-workflow
What's inside
- Skill name
yaaif-create-file-workflow- Description
- Create a custom file workflow on YAA\F via the Cursor MCP bridge: an ambient workflow that runs when an uploaded file finishes extraction (file.ready / file.failed / file.review_decided), reads the extracted text or tables, runs your own tool steps and replies to where the file came from (chat, Teams, Lark, email).
- License
- Apache-2.0
- Instructions
- 94 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Create a file extraction workflow on YAA\F
Extraction itself runs in the platform worker and is not pluggable per agent. What you attach
is a **post-extraction workflow**: the platform publishes a file event, an ambient trigger rule
(source `file`) matches it, and your workflow runs **as the uploader**.
```
Task Progress:
- [ ] 1. Auth + tenant
- [ ] 2. Clarify event, scope, processing and reply
- [ ] 3. Ensure the tools your steps call exist
- [ ] 4. Ambient agent
- [ ] 5. Preview with yaaif_file_workflow_template
- [ ] 6. Install with yaaif_file_workflow_create
- [ ] 7. Test with a real upload, check the file timeline
```
## Prerequisites
1. `yaaif-auth`
2. Ambient feature enabled on the deployment
3. For custom processing steps: the MCP tool is registered (`yaaif-create-mcp` / `yaaif_mcp_tools_list`)
If Admin UI **Open in Cursor** included `workflow_id`, stay in Cursor: load
`yaaif_ambient_workflow_get` and update that graph with `yaaif_ambient_workflow_update`. Do not create a duplicate.
## 1. Clarify
Ask only what is missing:
| Question | Maps to |
|---|---|
| Which events? (default ready + failed) | `events`: `file.ready`, `file.failed`, `file.review_decided` |
| All uploads, one chat agent, one file type? | `agent_id` **or** `filter_contains` (substring of the payload: agent id, MIME type, file name fragment, channel) |
| Need the extracted text / tables in the workflow? | `load_content`, `load_tables` |
| What custom processing? | `steps[]`: `{tool_name, input: {arg: binding}, output_key}` |
| What should the user be told? | `message_binding` (default `signal.payload.summary`; use your step's `context.*` result to send it) |
| Reply at all? | `reply` (default true) |
Payload fields for bindings (`signal.payload.*`): `file_id`, `name`, `mime_type`, `status`, `run_id`,
`data_class`, `quality_score`, `extracted_chars`, `review_status`, `summary`, `error`,
`origin.channel|session_id|user_id|agent_id`. No file content is in the payload: read it with
`file_load_context` / `file_tables` (steps `load_content` / `load_tables`).
## 2. Ambient agent
Reuse one (`yaaif_ambient_agent_list`) or create it (`yaaif_ambient_agent_create`, `mode: "active"`).
It only **owns** the workflow; replies go to the uploader, not to this agent.
## 3. Preview, then install
1. `yaaif_file_workflow_template` with the options: returns the workflow bodies without installing anything.
2. Show the user the steps and the rule(s); adjust.
3. `yaaif_file_workflow_create` with `ambient_agent_id` and the same options (`dry_run: true` first if unsure).
It creates one workflow + trigger rule per event.
Example (price lists from one agent, post to an ERP tool, tell the uploader the result):
```json
{
"ambient_agent_id": "<ambient agent id>",
"name": "Price list intake",
"events": ["file.ready", "file.failed"],
"agent_id": "<chat agent id>",
"load_tables": true,
"steps": [{
"tool_name": "erp_post_price_changes",
"input": { "file_id": "signal.payload.file_id", "tables": "context.file_tables" },
"output_key": "context.erp_result"
}],
"message_binding": "context.erp_result"
}
```
Need branching, approval or a skill step? Install with this tool first, then extend the graph with
`yaaif_ambient_workflow_update` (see `yaaif-create-ambient` for step types: `switch` on
`signal.payload.data_class` or `quality_score`, `approval`, `skill`, `send_email`, …).
## 4. Test
1. Upload a matching file in chat (or Teams/Lark/email).
2. `yaaif_ambient_runs_list` → `yaaif_ambient_run_get` for the run started by `file.ready`.
3. Admin UI → Files → the file's **Processing timeline** shows every stage and the `deliver:<channel>` reply.
## Rules to remember
- Rules are **per tenant**; scope with `agent_id` / `filter_contains`. Rules with source `any` or `*` never receive file events.
- The built-in automatic chat summary is independent: turn it off (Admin UI → File handling →
"Summarise new uploads automatically") if the workflow sends its own reply, or the user gets both.
- Email replies go to the original sender only, at most 3 per session per 10 minutes. Channels without a route are recorded as `skipped`.
- The workflow runs as the uploader: tools see only files that user can read.
- Reference: `agent-service/docs/file-workflows.md` and the pack `examples/workflow-packs/file-intake-workflow-pack/` in the YAAIF repository.From yaaif/cursor-plugin, Apache-2.0.
More from yaaif/cursor-plugin
- 0.565score
yaaif-kg-enhance
yaaif
Enhance the Context Store knowledge graph by discovering missing relationships between existing catalog nodes, proposing them for approval, and applying…
SkillAFreshness: AClaude Code +9 - 0.565score
yaaif-docs
yaaif
Answer questions about how the current YAAIF version works.
SkillAFreshness: AClaude Code +9 - 0.565score
yaaif-requirements
yaaif
Write a customer requirement analysis, functional specification, technical specification, and an estimate with timeline for a YAA\F Scenario, then store them…
SkillAFreshness: AClaude Code +9 - 0.561score
yaaif-governance
yaaif
Translate tenant business requirements into guardrail and harness settings, investigate policy-related failures, and apply explicitly confirmed governance…
SkillAFreshness: AClaude Code +9 - 0.559score
yaaif-kg-skill-plan
yaaif
Propose an ordered skill-authoring plan grounded in the Context Store knowledge graph and hand chosen steps to skill authoring.
SkillAFreshness: AClaude Code +9 - 0.529score
yaaif-plan-usecase
yaaif
Understand a business use case, propose a YAA\F architecture plan (chat skills, ambient workflows, desktop skills, agents, MCP tools, mappings), wait for…
SkillBFreshness: BClaude Code +9 - 0.529score
yaaif-create-skill
yaaif
Author or maintain a YAA\F SKILL.md pack and load it into the tenant catalog via the yaaif Cursor MCP bridge.
SkillBFreshness: BClaude Code +9 - 0.529score
yaaif-create-mcp
yaaif
Scaffold a YAA\F MCP server.
SkillBFreshness: BClaude Code +9 - 0.526score
yaaif-create-ambient
yaaif
Design and install YAA\F ambient workflows via the Cursor MCP bridge for customer/partner tenants (no monorepo required).
SkillBFreshness: BClaude Code +9 - 0.526score
yaaif-platform-tools
yaaif
Discover and correctly use YAA\F agent-service built-in local tools (skill lifecycle, files, ambient trigger, session/workflow state) when authoring skills or…
SkillBFreshness: BClaude Code +9 - 0.526score
yaaif-ops-support
yaaif
Operations support for LLM sessions, ambient workflow runs, and desktop executions: correlate IDs, analyze failures, pull telemetry, and optionally write a…
SkillBFreshness: BClaude Code +9 - 0.524score
yaaif-doctor
yaaif
Run YAA\F Cursor connectivity diagnostics (platform profile, OIDC, TLS/mTLS, auth/tenant, catalog ping, local tools API).
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 9, 2026 (21 days ago)
- Last release
- Sep 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/yaaif/cursor-plugin
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from yaaif
- 0.565score
yaaif-kg-enhance
yaaif
Enhance the Context Store knowledge graph by discovering missing relationships between existing catalog nodes, proposing them for approval, and applying…
SkillAFreshness: AClaude Code +9 - 0.565score
yaaif-docs
yaaif
Answer questions about how the current YAAIF version works.
SkillAFreshness: AClaude Code +9 - 0.565score
yaaif-requirements
yaaif
Write a customer requirement analysis, functional specification, technical specification, and an estimate with timeline for a YAA\F Scenario, then store them…
SkillAFreshness: AClaude Code +9 - 0.561score
yaaif-governance
yaaif
Translate tenant business requirements into guardrail and harness settings, investigate policy-related failures, and apply explicitly confirmed governance…
SkillAFreshness: AClaude Code +9 - 0.559score
yaaif-kg-skill-plan
yaaif
Propose an ordered skill-authoring plan grounded in the Context Store knowledge graph and hand chosen steps to skill authoring.
SkillAFreshness: AClaude Code +9 - 0.529score
yaaif-create-mcp
yaaif
Scaffold a YAA\F MCP server.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get yaaif-create-file-workflow running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
yaaif-create-file-workflow skill. Agent Mart. https://agentmart.dev/skills/yaaif-yaaif-create-file-workflow (last updated 2026-10-24)