Skill

feature-implement-complex

This skill should be used when feature complexity is complex (score 26-40) and the coordinator delegates architecture-heavy or multi-file implementation. Executes brainstorming, planning, and subagent-driven execution with opus and updates workflow and AI metrics.

Install

npx claudepluginhub siuninyue/siunin-plugins --plugin progress-tracker

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Execute high-complexity features with full design, planning, and implementation phases.

SKILL.md

Similar Skills

using-git-worktrees

Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.

superpowers

169.2k

subagent-driven-development

3 files

Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.

superpowers

169.2k

dispatching-parallel-agents

Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.

superpowers

169.2k

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitApr 26, 2026

Actions

View Source View Plugin View on GitHub View README

Purpose

Execute high-complexity features with full design, planning, and implementation phases.

Inputs

feature_id
feature_name
test_steps
complexity_score (26-40)

Outputs

Design exploration result
Implementation plan path
Execution completed status
Feature AI metrics with selected_model = opus

State Read/Write

Read:

docs/progress-tracker/state/progress.json
docs/progress-tracker/architecture/architecture.md (if present)

Write:

docs/progress-tracker/state/progress.json via progress_manager.py

Execution Context Requirements

CRITICAL: All plugins/progress-tracker/prog commands MUST be executed from the project root directory.

If not already in the project root, first run:

cd <project-root>

The prog tool uses relative paths and requires being in the correct project directory to resolve files correctly.

Steps

Validate complexity bucket is complex.
Display complex-mode banner and rationale.
Run unified preflight and follow decision before design/execution:

plugins/progress-tracker/prog git-auto-preflight --json

If decision=REQUIRE_WORKTREE, run:

Skill("using-git-worktrees", args="Set up isolated workspace for feature-<id>")

If decision=DELEGATE_GIT_AUTO, run:

Skill("progress-tracker:git-auto", args="Resolve workspace/git preflight blockers for feature-<id>")

If decision=ALLOW_IN_PLACE, continue in current workspace.

Run design phase:

Skill("brainstorming", args="<feature_name>: architecture and approach")

If docs/progress-tracker/architecture/architecture.md exists, include Execution Constraints (CONSTRAINT-*) in brainstorming context.

Update workflow to design complete:

plugins/progress-tracker/prog set-workflow-state \
  --phase "design_complete" \
  --next-action "planning"

Run planning phase:

Skill("writing-plans", args="<feature_name>: create implementation plan\nArchitecture constraints:\n- <CONSTRAINT-...>\nPlan path policy: must output under docs/plans/YYYY-MM-DD-<slug>.md (e.g. docs/plans/2026-03-03-feature-name.md)")

Update workflow to planning complete with plan path:

plugins/progress-tracker/prog set-workflow-state \
  --phase "planning_complete" \
  --plan-path "<returned_plan_path>" \
  --next-action "execution"

Run execution phase:

Skill("subagent-driven-development", args="plan:<returned_plan_path>")

Run final review + verification gates:

Skill("requesting-code-review", args="Review complex feature implementation: <feature_name>")
Skill("verification-before-completion", args="Verify complex feature evidence for <feature_name>")

Mark workflow as execution complete and save AI metrics:

plugins/progress-tracker/prog set-workflow-state \
  --phase "execution_complete" \
  --next-action "verify_and_complete"

plugins/progress-tracker/prog set-feature-ai-metrics <feature_id> \
  --complexity-score <score> \
  --selected-model opus \
  --workflow-path full_design_plan_execute

Ask user to run /prog done.

Compatibility rule:

Do not perform branch finalization here.
This skill prepares implementation for /prog done, which owns feature completion.

Plan Path Policy (Required)

set-workflow-state --plan-path must only store docs/plans/*.md. If returned path is invalid or missing, regenerate the plan before execution.

Failure Modes

If any phase fails, preserve the latest workflow state and return clear recovery guidance.
Do not mark feature complete here.

Commands

plugins/progress-tracker/prog set-workflow-state ...
plugins/progress-tracker/prog set-feature-ai-metrics ...

Examples

Auth system refactor (OAuth2 + JWT)
Multi-module integration
Core architecture redesign