yaaif-create-skill
Author or maintain a YAA\F SKILL.md pack and load it into the tenant catalog via the yaaif Cursor MCP bridge.
Skill by yaaif
Chalk Labs
Need help deploying yaaif-create-skill?
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-skill
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: design, 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-skill
What's inside
- Skill name
yaaif-create-skill- Description
- Author or maintain a YAA\F SKILL.md pack and load it into the tenant catalog via the yaaif Cursor MCP bridge. Use when Admin UI Open in Cursor / Create in Cursor selected a skill_id, or when creating a new skill. Prefers platform local skill lifecycle tools when available.
- License
- Apache-2.0
- Instructions
- 89 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- frontmatter.md · references/
SKILL.md (first lines)
# Create and load a YAA\F skill
```
Task Progress:
- [ ] 1. Auth + tenant
- [ ] 2. Capture intent + discover tools
- [ ] 3. Search existing / guided draft
- [ ] 4. Edit + validate module (local tools)
- [ ] 5. Enable + map agents (REST)
- [ ] 6. Refresh / runtime reload
```
## Prerequisites
Run `yaaif-auth` first. Optionally `yaaif_doctor` (confirm `local_tools`).
If the prompt includes `skill_id` from Admin UI, stay in Cursor — do not open
Admin UI URLs. Load that skill and maintain it; do not create a second skill
with the same id.
## Maintain a selected skill
When `skill_id` is present:
1. `yaaif_skill_get` / `yaaif_skill_file_tree` / `yaaif_skill_read_file`
2. Edit with `yaaif_skill_update_module_files` / `yaaif_skill_edit_section` /
`yaaif_skill_develop`
3. `yaaif_skill_tools_check` then `yaaif_skill_validate_module`
4. `yaaif_skill_map_agents_merge` if mapping changed
5. `yaaif_skill_refresh` then `yaaif_skill_runtime_reload`
6. If this skill is bound to a Scenario (`spec_id` in the prompt or a known
slot), keep editing through the skill tools. Do not finish with
`yaaif_agent_spec_sync_from_objects`; live skill-file edits become drift
until someone explicitly adopts them.
## Authoring
Read [references/frontmatter.md](references/frontmatter.md). Prefer lean chat skills unless SAP GUI / ambient / always-active is required.
- `id` is the path relative to the tenant skills root (e.g. `domain/my-skill`)
- Final path segment must equal frontmatter `name`
- Use **real** tool names from local tools or MCP catalog only
- Chat→ambient skills must include `list_ambient_workflows` and `trigger_ambient_workflow`
### Preferred path (platform local tools)
1. Discover: `yaaif_local_tools_list` (`family: skill`) and/or `yaaif-platform-tools`
2. Search: `yaaif_local_tool_call` → `skill_search` / `skill_search_workspace`
3. Draft: `yaaif_skill_guided_draft` (or `skill_create_guided_draft`)
4. Edit: `yaaif_skill_update_module_files` / `yaaif_skill_edit_section` / `yaaif_skill_develop`
5. **Check tools:** `yaaif_skill_tools_check` with the draft markdown (or `tools[]`) — must pass
6. Link tools: `yaaif_skill_mcp_tool_catalog` + `skill_tool_link_manager`
7. Validate: `yaaif_skill_validate_module` (strict) — prefer over `yaaif_skill_validate`
8. Map: `yaaif_skill_map_agents_merge`
9. `yaaif_skill_refresh` then `yaaif_skill_runtime_reload`
10. If creating under a Scenario, pass `spec_id` + `slot_key` on
`yaaif_skill_create`. Binding is enough; do not call
`yaaif_agent_spec_sync_from_objects` as a default finish step.
### Fallback (REST only)
When local tools are unavailable (doctor `local_tools` failed):
1. `yaaif_skill_create` with `id`, `description`, `instruction`, `tools` / `allowed_tools`, `enabled: true`
2. Companions via `yaaif_skill_write_file`
3. Prefer `yaaif_skill_map_agents_merge`
4. `yaaif_skill_validate` (optional)
5. `yaaif_skill_refresh` then `yaaif_skill_runtime_reload`
## MCP subset handoff
When the prompt includes `mcp_server_id` (optional `tools[]` / `prompts[]` / `resources[]` / `skill_id`):
1. Refresh the server if the names are missing (`yaaif_mcp_server_refresh` or catalog list).
2. Look up existing generated skills for this server. Reuse `skill_id` when present.
3. Draft a proposed pack: id, name, description, selected capabilities, and frontmatter (`allowed-tools`, `mcp-servers`; optional `allowed-prompts`, `allowed-resources`, and `allowed-tools: [server-slug:*]` wildcards). Use only listed or catalog names. Do not invent tool, prompt, or resource names.
4. Present the plan and **wait for explicit confirmation**. Do not call `skill_generate_from_mcp_server`, `yaaif_skill_create`, or enable/map until the operator confirms.
5. After confirmation, upsert with `skill_generate_from_mcp_server` (local tool) or `POST /api/mcp-tools/servers/:id/generate-skill`. Do **not** use `skill_create_guided_draft` for this path.
6. The upsert writes a **disabled, unmapped** pack (`metadata.source: mcp_generated`). Do not enable or map unless the operator asks.
7. After the upsert: `yaaif_skill_tools_check` then validate. Enable + `yaaif_skill_map_agents_merge` only after review.
## File-aware skills
Call `yaaif_dev_session_ensure`, then exercise `yaaif_files_list` / `yaaif_load_artifacts` / `yaaif_file_load_context` while drafting. Put `files_list` / `load_artifacts` / `file_load_context` (and `file_share_link` if needed) in frontmatter. Files may be referenced by durable `file_id` or ADK artifact name (+ optional `version`).
## Hand-off
Report skill id, validation result, enabled flag, mapped agent ids, and whether local lifecycle tools were used.From yaaif/cursor-plugin, Apache-2.0.
More from yaaif/cursor-plugin
- 0.565score
yaaif-create-file-workflow
yaaif
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 /…
SkillAFreshness: AClaude Code +9 - 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 - 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 - 0.526score
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-scenario
yaaif
Create or maintain a YAA\F Scenario (Agent Spec): segments, architecture slots, bindings, workflow_design, coverage, and bidirectional catalog sync.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 8, 2026 (1 month 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-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 - 0.565score
yaaif-docs
yaaif
Answer questions about how the current YAAIF version works.
SkillAFreshness: AClaude Code +9 - 0.565score
yaaif-create-file-workflow
yaaif
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 /…
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
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-skill 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-skill. Agent Mart. https://agentmart.dev/skills/yaaif-yaaif-create-skill (last updated 2026-10-24)