Agent skill

pre-plan-workflow

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.

Stars 177
Forks 18

Install this agent skill to your Project

npx add-skill https://github.com/jpicklyk/task-orchestrator/tree/main/claude-plugins/task-orchestrator/skills/pre-plan-workflow

SKILL.md

Pre-Plan Workflow — Definition Floor

When entering plan mode, use the MCP to set the definition floor before writing your plan.

The definition floor is the baseline of existing work, documentation requirements, and gate constraints that the plan must account for.

If MCP is unreachable: Proceed with planning based on conversation context. Note in the plan that MCP state could not be verified — existing work may overlap. Re-check after MCP reconnects.

Step 1: Check Existing MCP State

Call the health check to see what's already tracked:

get_context()

If active or stalled items exist:

  • Identify items related to the current request — avoid planning work that duplicates what's already tracked
  • For each relevant active item, call get_context(itemId=...) to inspect:
    • Note schema — which notes are expected for this item's tags
    • Gate status — which required notes are filled vs. missing, and whether the item can advance
    • Guidance pointer — authoring guidance for the first unfilled required note

If no items exist (clean slate):

  • The definition floor is simply "no existing MCP state to account for"
  • Proceed with planning, but still check Step 2 for schema awareness

Step 2: Discover Note Schema Requirements

Read .taskorchestrator/config.yaml in the project root (this is a file read, not an MCP call):

  • If the file exists, list the discovered schemas and their required notes per phase
  • Schemas are defined under work_item_schemas: (preferred) or note_schemas: (legacy)
  • Each schema key (e.g., feature-implementation, bug-fix) is a type identifier — set it as the item's type field to activate gate enforcement. Tags can be used for additional categorization but are no longer the primary schema activator.
  • Required queue-phase notes define what documentation must exist before work starts
  • Required work-phase notes define what must be captured during implementation
  • Use guidancePointer values from get_context(itemId=...) on existing items to understand how to author each note

If no config file exists, the project has no note schemas — items will be schema-free with no gate enforcement. Proceed with planning normally.

Use schemas to inform the plan: When a schema applies, each planned task should:

  • Note which schema type will be applied at materialization (e.g., type: "feature-implementation")
  • Account for required notes — plan sections should naturally produce content that maps to required note keys
  • Respect dependency ordering — which tasks block others (these become BLOCKS edges)

Step 3: Plan with MCP Awareness

Structure the plan knowing it will be materialized into MCP items after approval:

  • Each planned task should map to one work item with clear boundaries — a single unit of work a subagent can own
  • Account for dependency ordering — which tasks block others (these become BLOCKS edges)
  • Consider the hierarchy — a root container item with child task items is the standard pattern

Continue with Plan Mode

The prerequisite is complete. Now proceed with plan mode's normal workflow — explore the codebase, understand existing patterns, and design your implementation approach. Use the definition floor from Steps 1-3 to inform your plan.

Once the plan is approved, the post-plan hook will guide you through materialization and implementation dispatch. Do not materialize before approval.

Expand your agent's capabilities with these related and highly-rated skills.

jpicklyk/task-orchestrator

implement

End-to-end workflow for taking MCP work items from backlog to merged PR. Handles git branching, schema-driven planning, implementation, independent review, and PR creation. Composes spec-quality, review-quality, and schema-workflow skills into a single pipeline. Use when a user says "implement this", "work on this item", "fix these bugs", "pick up the next task", "create a PR for this", "go through the backlog", or references specific MCP item IDs for implementation.

177 18
Explore
jpicklyk/task-orchestrator

review-quality

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.

177 18
Explore
jpicklyk/task-orchestrator

feature-implementation

Guide the full lifecycle of a feature-implementation tagged MCP item (the feature container) — from queue through review

177 18
Explore
jpicklyk/task-orchestrator

spec-quality

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.

177 18
Explore
jpicklyk/task-orchestrator

session-retrospective

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.

177 18
Explore
jpicklyk/task-orchestrator

prepare-release

End-to-end release automation — reads commits since last tag, infers semver bump, drafts changelog, creates release PR, merges it, waits for CI green, tags, and monitors the Docker build to completion.

177 18
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results