Skip to content
Agent Orchestration
Skill

/status-progression

Navigates 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

BOOST
From plugin
task-orchestrator
20929 skills4 agents2 commands
Install
$ npx -y skills add jpicklyk/task-orchestrator --skill status-progression --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/status-progression

Context preview

The summary Claude sees to decide when to auto-load this skill.

Navigates 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

SKILL.md

status-progression.SKILL.md
name: status-progression
description: "Navigates 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."
argument-hint: "[optional: item UUID or title to look up]"

Status Progression — Current (v3)

Guides role transitions for a WorkItem: identify the item, check gate status, fill missing notes, and advance. Handles all triggers including block, resume, and cancel.

---

Step 1: Identify the Item

Resolve `$ARGUMENTS` to a UUID via `query_items` search (`operation="search"`, `query=$ARGUMENTS`, `limit=5`); if ambiguous, present matches via `AskUserQuestion`. If `$ARGUMENTS` is empty, ask for a UUID or title fragment.

---

Step 2: Check Current State

Once you have the item ID, call:

get_context(itemId="<item-uuid>")

Parse the response and display a status card. Use this format:

◉ "Implement authentication module"
  Role:     work
  Gate:     ⊘ blocked — 2 required notes missing
  Missing:  implementation-notes (work, required)
            session-tracking (work, required)
  Guidance: "Describe what was implemented, which files changed, and why
             the approach was chosen..."
◉ "Design API schema"
  Role:     queue
  Gate:     ✓ open — all required notes filled (or no schema)
  Next:     advance_item(trigger="start") → work

**Fields to surface from `get_context` response:**

| Response Field | What to Show | |---|---| | `item.role` | Current role label | | `gateStatus.canAdvance` | ✓ open or ⊘ blocked | | `gateStatus.missing` | List each missing note key + role | | `guidanceKey` | Key of first unfilled required note with guidance; resolve its text via `query_items(operation="schema", itemId="<uuid>")` to show as "Guidance:" | | `noteSchema` | List all schema notes with `exists` status |

If the item has no schema (no tags matching a schema key), `noteSchema` will be empty and the gate is always open.

---

Step 3: Fill Missing Notes (if Gated)

If `gateStatus.canAdvance = false`, the item cannot advance until required notes are filled.

For each missing note, check whether its content can be inferred from the conversation context. If yes, fill it directly. If not, ask the user what to capture.

Use `guidanceKey` to prompt the user — resolve its guidance text via `query_items(operation="schema", itemId=...)`. Only one `guidanceKey` is returned — for the first unfilled required note. See schema entries list for all unfilled notes.

Fill notes with:

manage_notes(
  operation="upsert",
  notes=[
    { itemId: "<uuid>", key: "implementation-notes", role: "work", body: "<content>" },
    { itemId: "<uuid>", key: "session-tracking", role: "work", body: "<content>" }
  ]
)

After filling, re-check gate status:

get_context(itemId="<uuid>")

Confirm `gateStatus.canAdvance = true` before proceeding to Step 4. If notes are still missing after the upsert, show the updated status card and repeat for any remaining gaps.

---

Step 4: Advance the Item

With the gate open, call `advance_item` with the appropriate trigger (trigger semantics are documented in the `advance_item` tool description):

advance_item(transitions=[{ itemId: "<uuid>", trigger: "start" }])

Parse the response and report the transition result:

✓ Advanced: queue → work
  ↳ Cascade: "Feature: Auth System" also moved queue → work
  ↳ Unblocked: "Write integration tests" (was waiting on this item)
  ↳ Next phase notes:
      implementation-notes (work, required)
      session-tracking (work, required)

**Fields to check in the advance response:**

| Response Field | What to Report | |---|---| | `newRole` | The core transition (`previousRole` is omitted from success results) | | `cascadeEvents` | Parent or ancestor items that auto-transitioned | | `unblockedItems` | Sibling items that are now actionable | | `expectedNotes` | Notes for the next phase — show as "Next phase notes:" |

If `cascadeEvents` is empty, omit the cascade line. If `unblockedItems` is empty, omit the unblocked line. If `expectedNotes` is empty or absent (no schema), omit the next phase notes line.

---

Troubleshooting

**Problem: `advance_item` fails with "required notes not filled"**

Cause: The current phase has required notes that have not been upserted yet. Gate enforcement runs before the transition executes.

Solution: The gate-failure error already lists the missing note keys. Fill each one with `manage_notes(operation="upsert")`, then retry `advance_item`. Call `get_context` only if you need broader item state.

---

**Problem: Item cannot advance — it is blocked by a dependency**

Cause: Another item has a `BLOCKS` edge pointing to this item, and that blocking item has not yet reached terminal role.

Solution: Find the blocker:

query_dependencies(operation="get", itemId="<uuid>", direction="incoming", includeItemInfo=true)

Identify the blocking item (role will be non-terminal). Advance the blocking item to terminal first. When it completes, the current item appears in `unblockedItems`.

---

**Problem: Item is in BLOCKED role and `start` fails**

Cause: The item is in the BLOCKED role (was explicitly blocked with `trigger: "block"`). The `start` trigger is not valid from BLOCKED — it is only valid from QUEUE, WORK, or REVIEW.

Solution: Use `trigger: "resume"` to return the item to its previous role:

advance_item(transitions=[{ itemId: "<uuid>", trigger: "resume" }])

After resuming, check `get_context` and then advance normally with `start` if the gate is open.

---

**Problem: Want to skip the review phase and go directly to terminal**

Cause: The item is in WORK role and has a review-phase schema, but verification is already done or not applicable.

Solution: Use `trigger

Read more
Ships withtask-orchestrator

Server-enforced workflow discipline for AI agents. Prompt-based frameworks hope the LLM follows instructions. This one blocks the call if it doesn't.

Get the whole plugin

Other skills on task-orchestrator.