manage-schemas

Create, view, edit, delete, and validate note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Use when user says "create schema", "show schemas", "edit schema", "delete schema", "validate config", "what schemas exist", "add a note to schema", "remove note from schema", or "configure gates".

177 stars

Best use case

manage-schemas is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Create, view, edit, delete, and validate note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Use when user says "create schema", "show schemas", "edit schema", "delete schema", "validate config", "what schemas exist", "add a note to schema", "remove note from schema", or "configure gates".

Teams using manage-schemas should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/manage-schemas/SKILL.md --create-dirs "https://raw.githubusercontent.com/jpicklyk/task-orchestrator/main/claude-plugins/task-orchestrator/skills/manage-schemas/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/manage-schemas/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How manage-schemas Compares

Feature / Agentmanage-schemasStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Create, view, edit, delete, and validate note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Use when user says "create schema", "show schemas", "edit schema", "delete schema", "validate config", "what schemas exist", "add a note to schema", "remove note from schema", or "configure gates".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Manage Schemas — Note Schema Lifecycle

Create, view, edit, delete, and validate note schemas in `.taskorchestrator/config.yaml`. Schemas define which notes agents must fill at each workflow phase before advancing items.

---

## Step 1 — Determine Intent

Classify from `$ARGUMENTS` and conversation context before making any tool calls.

| Signal words | Action |
|---|---|
| "create", "build", "new", "add schema", "define", "set up" | CREATE |
| "show", "view", "list", "what schemas", "display" | VIEW |
| "edit", "modify", "change", "update", "add note to", "remove note from" | EDIT |
| "delete", "remove schema", "drop" | DELETE |
| "validate", "check", "verify", "lint" | VALIDATE |

If `$ARGUMENTS` contains both an action and a schema name (e.g., "view bug-fix"), extract both. If intent cannot be determined, ask via `AskUserQuestion` with options: Create, View / Validate, Edit, Delete.

> Validate is grouped with View — both are read-only operations on the config file.

---

## Step 2 — Config Bootstrap

Check if `.taskorchestrator/config.yaml` exists by reading it.

**If the file does not exist:**
- For **VIEW** or **VALIDATE**: report "No schemas configured — `.taskorchestrator/config.yaml` does not exist." and stop.
- For **CREATE**, **EDIT**, or **DELETE**: create the `.taskorchestrator/` directory if missing, then create `config.yaml` with an empty `work_item_schemas:` key:
  ```yaml
  work_item_schemas:
  ```

**If the file exists:** Read and parse it. Proceed to Step 3.

---

## Step 3 — Route to Operation

### CREATE — Build a New Schema

Interactive Q&A flow that gathers schema requirements, generates YAML, merges into config, and optionally creates a companion lifecycle skill.

For detailed workflow, see `references/create-workflow.md` in this skill folder.

### VIEW — Display Existing Schemas

Read `.taskorchestrator/config.yaml` and display schemas in a summary table:

```
◆ Note Schemas — .taskorchestrator/config.yaml

| Schema Type | Lifecycle | Queue Notes | Work Notes | Review Notes | Total |
|---|---|---|---|---|---|
| feature-implementation | auto | 1 (1 req) | 2 (2 req) | 1 (1 req) | 4 |
| bug-fix | auto | 1 (1 req) | 2 (2 req) | 1 (1 req) | 4 |
```

If the user specified a schema name, show that schema's full detail: each note with key, role, required, description, guidance, and skill (if set). Also show the schema's lifecycle mode and default_traits (if any).

If the config has a `traits:` section, show a separate traits summary table:

```
◆ Traits

| Trait | Notes | Skills |
|---|---|---|
| needs-security-review | security-assessment (review, req) | security-review |
| needs-migration-review | migration-assessment (queue, req) | migration-review |
```

If the config has an `auditing:` section, display the auditing status including verifier type when present:

```
◆ Auditing: enabled, verifier: noop
```

Or with a JWKS verifier and its source:

```
◆ Auditing: enabled, verifier: jwks (uri: https://provider.example/.well-known/jwks.json)
```

Or `◆ Auditing: disabled` (or omit if the section is absent). When `verifier` is absent, default to `verifier: noop`.

### EDIT — Modify an Existing Schema

Read current config, display the target schema, ask what to change (add note, remove note, toggle required, change description/guidance/skill, change lifecycle mode, add/remove default_traits, rename key), apply changes, write back.

When adding or editing a note, offer the `skill` field: "Should this note have a skill framework? If so, provide the skill name (e.g., `review-quality`). The skill will be invoked before the agent fills the note."

If the target schema is not found in config.yaml, inform the user and offer to CREATE instead.

For detailed workflow, see `references/edit-workflow.md` in this skill folder.

### DELETE — Remove a Schema

Read current config, confirm the schema name, warn about orphaned notes on existing items, remove the key, write back.

If the target schema is not found in config.yaml, inform the user and offer to CREATE instead.

For detailed workflow, see `references/delete-workflow.md` in this skill folder.

### VALIDATE — Check Config Integrity

Run structural and semantic checks on the config file and report issues with fix suggestions.

For detailed workflow, see `references/validate-workflow.md` in this skill folder.

---

## Step 4 — Report

**For write operations (CREATE, EDIT, DELETE):**
- Show what changed in the config file
- Remind: **MCP reconnect required** (`/mcp`) for schema changes to take effect — the server caches schemas on first access

**For VIEW and VALIDATE:** The output from Step 3 is the deliverable — no additional report needed.

---

## Troubleshooting

**`expectedNotes` is empty after creating an item with the schema tag**
- Cause: MCP server hasn't loaded the updated config file
- Solution: Run `/mcp` in Claude Code to reconnect the server, then retry

**Schema not applied — item has no schema**
- Cause: The item's `type` field doesn't match any key in `work_item_schemas`, and its tags don't match any `note_schemas` key (legacy fallback)
- Resolution order: `type` field → direct lookup in `work_item_schemas`; if no type or no match, first tag match in `note_schemas`; if no match, falls back to `default` schema if one exists
- Solution: Verify the item's type and tags with `query_items(operation="get", id="<uuid>")`. Set `type` to a key that exists in `work_item_schemas` for reliable schema selection.

**Duplicate schema key in config file**
- Cause: YAML allows duplicate keys but only the last one is used
- Solution: Check for duplicate entries under `work_item_schemas:` (or `note_schemas:`) and merge them

**Changes not taking effect after editing config**
- Cause: The server caches schemas on first access — changes are not hot-reloaded
- Solution: Run `/mcp` to reconnect the MCP server subprocess

---

## Examples

**Example 1: View all schemas**

User says: "What schemas do I have?"
1. Read `.taskorchestrator/config.yaml`
2. Display summary table with note counts per phase
3. Offer to show detail for any specific schema

**Example 2: Add a required note to an existing schema**

User says: "Add a test-plan note to the bug-fix schema"
1. Read config, find `bug-fix` schema
2. Ask: which phase (queue/work/review), required?, description, guidance
3. Append the new note entry, write config back
4. Remind: `/mcp` reconnect needed

**Example 3: Validate config after manual editing**

User says: "I edited the config by hand — check it"
1. Read and parse config
2. Run validation checks (syntax, structure, field rules, duplicates)
3. Report issues or confirm "Config is valid — N schemas, M total notes"

Related Skills

dependency-manager

177
from jpicklyk/task-orchestrator

Visualize, create, and diagnose dependencies between MCP work items. Use when a user says "what blocks this", "add a dependency", "show dependency graph", "why can't this start", "link these items", "unblock this", "remove dependency", or "show blockers".

work-summary

177
from jpicklyk/task-orchestrator

Generate a hierarchical project dashboard showing all work items organized by container, with IDs, tags, status, and priority visible. Always use this skill for any request about project status, work summaries, or item overviews — never construct dashboards manually with raw MCP calls. Trigger on any of these phrases or intent: "project status", "what's active", "show me the dashboard", "work summary", "summary", "what should I work on", "project health", "what's blocked", "where did I leave off", "show items", "what's in the backlog", "overview", or any request to see or review the current state of work items. This includes session-start context gathering — if you need to understand current project state, use this skill.

status-progression

177
from jpicklyk/task-orchestrator

Navigate role transitions for MCP work items using advance_item. Shows current role, gate status, required notes, and the correct trigger to use. Use when a user says "advance this item", "move to work", "start this task", "complete this item", "what's the next status", "why can't I advance", "unblock this", "cancel this item", or "check gate status".

schema-workflow

177
from jpicklyk/task-orchestrator

Guide an MCP work item through its schema-defined lifecycle — filling required notes using guidancePointer and advancing through gate-enforced phases. Internal skill triggered by hooks and output styles during orchestration workflows. Use when an item has schema tags and needs to progress through queue, work, review, or terminal phases with note gates.

quick-start

177
from jpicklyk/task-orchestrator

Interactive onboarding for the MCP Task Orchestrator. Detects empty or populated workspaces and walks through how plan mode, persistent tracking, and the MCP work together. Use when a user says "get started", "how do I use this", "quick start", "first time setup", "onboard me", "what can this MCP do", or "help me learn task orchestrator".

pre-plan-workflow

177
from jpicklyk/task-orchestrator

Internal workflow for plan mode — checks MCP for existing work, note schemas, and gate requirements to set the definition floor before planning begins. Triggered automatically when entering plan mode for any non-trivial implementation task.

post-plan-workflow

177
from jpicklyk/task-orchestrator

Internal workflow for post-plan materialization — creates MCP items from the approved plan and dispatches implementation. Triggered automatically after plan approval when MCP tracking is active.

create-item

177
from jpicklyk/task-orchestrator

Create an MCP work item from conversation context. Scans existing containers to anchor the item in the right place (Bugs, Features, Tech Debt, Observations, etc.), infers type and priority, creates single items or work trees, and pre-fills required notes. Use this whenever the conversation surfaces a bug, feature idea, tech debt item, or observation worth tracking persistently. Also use when user says "track this", "log this bug", "create a task for", or "add this to the backlog".

batch-complete

177
from jpicklyk/task-orchestrator

Complete or cancel multiple items at once — close out features, clean up old work, archive completed workstreams. Use when a user says "close out this feature", "complete everything under X", "cancel this workstream", "clean up old items", "bulk complete", "finish this feature", or "archive completed work".

spec-quality

177
from jpicklyk/task-orchestrator

Specification quality framework for planning. Defines the minimum bar for what a plan must address — alternatives, non-goals, blast radius, risk flags, and test strategy. Referenced by schema guidance fields during queue-phase note filling. Read this skill whenever filling requirements or design notes for any MCP work item.

session-retrospective

177
from jpicklyk/task-orchestrator

Analyze the current implementation run — evaluate schema effectiveness, delegation alignment, note quality, plan-to-execution fit. Captures cross-session trends and proposes improvements when patterns repeat. Use after implementation runs, or when user says 'retrospective', 'session review', 'what did we learn', 'analyze this run', 'how did that go', 'evaluate our process', 'wrap up', 'end of session review'. Also use when the output style's retrospective nudge fires after complete_tree.

review-quality

177
from jpicklyk/task-orchestrator

Review quality framework for the work-to-review transition gate. Guides verification of plan alignment, test quality, and code simplification before marking implementation complete. Referenced by schema guidance fields during review-phase note filling. Read this skill when filling review-checklist notes or when asked to review completed implementation work.