Skip to content
Agentmart
Submit a tool

yaaif-kg-skill-plan

Propose an ordered skill-authoring plan grounded in the Context Store knowledge graph and hand chosen steps to skill authoring.

Skill by yaaif

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying yaaif-kg-skill-plan?

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.

Book a call

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-kg-skill-plan

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.

We use your email only for this newsletter. Privacy

About

Propose an ordered skill-authoring plan grounded in the Context Store knowledge graph and hand chosen steps to skill authoring. Use when the user asks which skills to build from the catalog or wants a plan from the Entity Graph. Not for applying graph enrichments (use yaaif-kg-enhance).

No 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-kg-skill-plan

What's inside

Skill name
yaaif-kg-skill-plan
Description
Propose an ordered skill-authoring plan grounded in the Context Store knowledge graph and hand chosen steps to skill authoring. Use when the user asks which skills to build from the catalog or wants a plan from the Entity Graph. Not for applying graph enrichments (use yaaif-kg-enhance).
License
Apache-2.0
Instructions
19 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Call every Context Store tool through `yaaif_local_tool_call` with `name` set to the tool and the tool's fields under `arguments`. Surface tool errors verbatim and never simulate a result. If a `context_kg_*` call fails because the tool is unavailable, stop and say Context Store tools are not mounted on agent-service.

## Goal

Produce a 2-8 step plan of new `SKILL.md` packs that fulfils the user's intent, each step grounded in existing catalog IDs. Never write `skill:` nodes into the graph and never call `context_kg_propose_enrichments` or `context_kg_apply_enrichments`.

Copy IDs from tool output (`object_type:`, `mcp_tool:`, `mcp_server:`, `dimension:`, `metric:`, optional `concept:`). Never invent IDs.

## Flow

1. If the intent is not in the request, ask one short question for it (and optional scope or seed node ID).
2. Scan with `context_kg_get_snapshot`, `context_kg_get_data_model`, `context_kg_get_mcp_metadata`, then `context_graph_search`, `context_graph_neighbors`, `context_graph_query` to find anchors that match the intent. Gaps with catalog tools or types but no skill become plan steps. If an existing skill already covers a gap, say so instead of proposing a duplicate.
3. Call `context_kg_propose_skill_plan` with `intent`, `summary`, and `steps[]`, each with `step_id`, `proposed_skill_id`, `title`, `summary`, `node_ids` (at least one existing ID), and optional `suggested_tools` and `rationale`. `proposed_skill_id` must be path-like under `tenant/` or `yaaif/` with lowercase hyphen or slash segments, unique in the plan, and never a bare name. If the tool rejects unknown `node_ids`, fix them from tool results.
4. Present the stored plan as a short table: step, proposed skill ID, summary, node IDs. Use `context_kg_get_skill_plan` to re-read it.
5. Ask which steps to draft or whether to revise. For a revision, re-run `context_kg_propose_skill_plan`. For a chosen step, use `context_kg_skill_plan_step_brief` to get its brief and continue with the `yaaif-create-skill` skill.

Keep replies short.

From yaaif/cursor-plugin, Apache-2.0.

More from yaaif/cursor-plugin

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 1, 2026 (29 days ago)
Last release
Sep 2, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from yaaif

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-kg-skill-plan 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying yaaif-kg-skill-plan?

CallGet help
Cite this page

yaaif-kg-skill-plan. Agent Mart. https://agentmart.dev/skills/yaaif-yaaif-kg-skill-plan (last updated 2026-10-24)