Continue work

Skill zdnemz/claude-team/.claude/skills/continue-work

Autonomous Multi-Agent System

Install

npx -y skills add zdnemz/claude-team --skill continue-work

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Autonomous execution loop — pick the next ready tasks from the plan, dispatch specialist agents with the right model, verify results, record progress, commit. Use when state phase is PLANNED or EXECUTING.

SKILL.md

2.7 KB, as published. Nobody here has run it

Continue Work

If phase is PLANNED: state_set {phase:"EXECUTING", detail:"<current epic>"}. Then loop:

1 — Load

progress_status → if a handoff note exists (memory_get context/handoff), apply it then memory_delete context/handoff. Read docs/plans/legend.md; pick the current epic (first not-done whose dependencies are done); read its epic file. For architecture/spec context, query the knowledge graph (/graphify) instead of re-reading whole spec files.

2 — Pick

Ready tasks = status todo with all depends done. Prefer finishing an in-flight story over opening a new one. Up to 3 tasks may run as parallel subagents ONLY if they touch disjoint files; otherwise sequential.

3 — Dispatch

For each task, spawn its role agent with its model (both named in the task line):

Named agent type available → use it.
Not yet registered this session → spawn general-purpose with the body of .claude/agents/<role>.md prepended to the prompt + the task's model param.

The dispatch prompt MUST contain: task id + title, the story's acceptance criteria, deliverable, verify step, paths of relevant specs, and: "Report files changed + verification command + output."

4 — Verify (you, not them)

Run the task's verify step yourself. Story complete → spawn qa-engineer for a story-level check against its acceptance criteria. Fail → one retry with the failure context. Fail again → escalate model one tier (registry escalation rule). Still failing → mark task blocked, memory_save blockers/<task-id> (symptom, attempts, what's needed), move on if other tasks are workable.

5 — Record (never skip, every task)

Tick the task checkbox in the epic file (todo→done, or mark blocked).
progress_log {status:"done", task:"T-…", role:"…", note:"…"}.
Decisions made along the way → memory_save decisions/<slug>.
Git repo exists → commit per completed task: T-NNMMKK: <title>.

6 — Continue or stop

Keep looping while ready tasks remain and context is healthy. Stop and summarize when:

A story/epic milestone lands → report, ask user whether to continue.
A blocker needs the user → surface it plainly. state_set BLOCKED only if NOTHING else is workable.
Context nearly exhausted → memory_save context/handoff (in-flight work, exact next step), progress_log, tell the user: type start in a fresh session to resume.
Last epic done → state_set {phase:"DONE"}, final report.