Agent skill · Design & Presentation

execute-task

Execute the next TaskMaster task using the implementation plan with CDD verification. Picks the next ready task, matches it to the plan step, implements via a dispatched subagent, verifies subtasks with evidence, marks the task done, and loops until every task is complete. Wraps the TaskMaster next -> in-progress -> done lifecycle with CDD GREEN / RED / BLUE verification and the plugin's triple-verification rule. Autonomous by design — no user prompts inside the loop.

anombyte93github.com/anombyte93GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add anombyte93/prd-taskmaster --skill execute-task --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 19 KB
Bundled scripts: none
Allowed tools: -Read-Write-Edit-Bash-Skill-Agent
Path: skills/execute-task/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 586
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Executes the next TaskMaster task using the implementation plan with CDD verification. Picks the next ready task, matches it to the plan step, implements via a dispatched subagent, verifies subtasks with evidence, marks the task done, and loops until every task is complete. It wraps the TaskMaster next -> in-progress -> done lifecycle with CDD GREEN / RED / BLUE verification and the plugin's triple-verification rule. Autonomous by design — no user prompts inside the loop.

How it works

  • Entry conditions ensure EXECUTE phase and presence of required files.
  • Per-iteration cycle handles: heartbeat, inbox reconciliation, next task selection via python3 script.py next-task, plan loading from plan sources, CDD card generation from subtasks, status transitions (in-progress, done, scaffold), and subagent dispatch with system-prompt augmentation and complexity-tiered routing.
  • Subagent outcomes (DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, BLOCKED) drive subsequent steps, including possible re-dispatch, expansion, or downgrade.
  • A triple verification gate sequence runs only after hard exit-code gate and reachability sweep, combining plugin evidence checks, doubt sweep, validate, and an external Opus pass.
  • Depending on reachability verdict, the task either marks done and updates pipeline and subtasks, or auto-downgrades to scaffold with logging and continued iteration.
  • Step 12 renders progress; Step 13 loops back to Step 1 until SHIP_CHECK_OK or a halt condition.

When to use it

Use when a task-execution mode is active (EXECUTE) and there is at least one ready task to process; the skill halts if gaps are found or dependencies are blocked, and surfaces issues via the recon ladder or inbox.

What it can touch

  • Access to backend operations via Python scripts:
    • python3 script.py next-task
    • python3 script.py set-status --id <N> --status in-progress
    • python3 script.py set-status --id <N> --status done
    • python3 script.py expand --id <N>
    • .atlas-ai/ship-check.py --dry-run
    • python3 script.py reachability-sweep --task <task_id> --start-commit <task_start_sha>
  • Files and paths including: .atlas-ai/cdd/task-<id>.json, .atlas-ai/state/pipeline.json, .taskmaster/tasks/tasks.json, and various plan sources under docs/superpowers/plans/ or .taskmaster/docs/plan.md.
  • Tools and plugins listed in frontmatter (Read, Write, Edit, Bash, Skill, Agent, ToolSearch, mcp__atlas-engine, mcp__plugin_prd_go, mcp__plugin_prd-taskmaster_go, mcp__plugin_atlas-go_go).

Caveats

  • Autonomous loop with no user prompts; gaps surface via recon ladder or inbox rather than prompts.
  • Requires existence of phase EXECUTE indicators, ready tasks, and plan/evidence artifacts to proceed.
  • The hard gate, reachability sweep, and triple verification must pass for a task to be marked done; otherwise the task may be scaffolded or blocked per protocol.
  • Blocking scenarios may trigger expansion or subtask downgrades rather than silent failure.
From the SKILL.md

# execute-task The execution loop. Three sources converge: - **Plan** (HOW) — `docs/superpowers/plans/*.md` produced by GENERATE - **TaskMaster** (WHAT) — `.taskmaster/tasks/tasks.json` with dependencies and complexity scores - **CDD** (PROOF) — acceptance cards per task, evidence-gated execute-task is the single skill that runs the full build from "tasks are ready" to SHIP_CHECK_OK. It is autonomous — no AskUserQuestion inside the loop. Any gap that would require user input is surfaced through the recon escalation ladder (step 11) or the inbox (steps 4 and 8), never via a modal prompt. ## Entry This skill is invoked either: 1. Directly by the user once HANDOFF has completed and a task-execution mode (A/B/C) has been dispatched, **or** 2. By the `prd-taskmaster` orchestrator when `current_phase` is `EXECUTE`. On entry, confirm that: - `.atlas-ai/state/pipeline.json` exists and records `phase: EXECUTE` - `.taskmaster/tasks/tasks.json` exists with at least one ready task - `.atlas-ai/customizations/system-prompt-template.md` is present (may be empty — absence is a setup bug, empty is fine) If any of the above are missing, report the gap and halt. Do NOT attempt to bootstrap the missi

What's inside
Steps it walks through
  1. Entry
  2. Cycle (per iteration)
  3. Termination
  4. Red flags
  5. Observability
  6. Composition
  7. Non-exits
Commands it runs
python3 script.py next-task
python3 script.py set-status --id <N> --status in-progress
python3 script.py reachability-sweep \
python3 script.py set-status --id <N> --status done
python3 script.py set-status --id <N> --status scaffold
More from prd-taskmaster
All skills →
execute-fleetPhase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and…Workflow & ProductivityatlasThe Atlas engine — turn any goal into a validated PRD and an executable, verified task graph.…Content & Marketingcustomise-workflowCustomise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the…Design & PresentationdiscoverPhase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to…Documentationexpand-tasksExpand all TaskMaster tasks with deep research before coding begins. Reads tasks.json, launches…Workflow & ProductivitygeneratePhase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template…Documentation
About this skill
What does the execute-task skill do?

Execute the next TaskMaster task using the implementation plan with CDD verification. Picks the next ready task, matches it to the plan step, implements via a dispatched subagent, verifies subtasks with evidence, marks the task done, and loops until every task is complete. Wraps the TaskMaster next -> in-progress -> done lifecycle with CDD GREEN / RED / BLUE verification and the plugin's triple-verification rule. Autonomous by design — no user prompts inside the loop.

How do I install it?

Run `npx skills add anombyte93/prd-taskmaster --skill execute-task --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From anombyte93/prd-taskmaster, a repository with 586 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.