diagnose-stall
Diagnose why agent orchestration stopped producing progress — silent stalls in /loop, dispatch-agents, or execute-plan. Use when work appears hung, no output for several minutes, or a subagent never returned.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 292
- Forks
- 23
01 前言 Front Matter
- name
- diagnose-stall
- model
- haiku
- description
- Diagnose why agent orchestration stopped producing progress — silent stalls in /loop, dispatch-agents, or execute-plan. Use when work appears hung, no output for several minutes, or a subagent never returned.
03 SKILL.md 正文
Diagnose Stall
HARD GATE — Do NOT restart work blindly. Run this diagnostic first when orchestration goes quiet without an explicit terminal state.
Explicit handler for silent stalls in long-running agent workflows (/loop, dispatch-agents, execute-plan, build-epic resume mode).
Stall signals
| Signal | Likely cause |
|---|---|
| No stdout for >5 min on a monitored loop tick | Sleep/watcher misconfigured or prompt never re-armed |
| Subagent dispatched but no completion message | Agent hung, blocked on approval, or scope too large |
dispatch-agents cycle 3 reached with gaps |
Circuit exhausted — needs human escalation |
| Verify command running >15 min | Missing timeout or waiting on external service |
handoff.next_skill unchanged across turns |
Prior skill never wrote handoff |
Process
- Read state —
specs/state.yaml:handoff.next_skill,active_flow,metrics.story_start, open decisions. - Check locks —
bash scripts/check-stale-locks.shif present; readspecs/agent-locks.yaml. - Inspect terminals — list background shells; note PIDs, last output timestamp, exit codes.
- Classify stall type:
- waiting_approval — tool blocked on user consent
- blocked_dependency — prior task incomplete or red gate
- agent_exhausted — max iterations/cycles reached
- misconfigured_loop — duplicate sentinel, wrong regex, or sleeper not re-armed
- external_io — network, CI, or deploy wait without timeout
- unknown — escalate with evidence bundle
- Recommend recovery — one action only (resume, kill PID, re-dispatch with smaller brief, escalate to user).
- Write report —
specs/verifications/STALL-<timestamp>.mdwith classification, evidence, and recommended next skill.
Integration
| Caller | When to invoke |
|---|---|
/loop (Cursor) |
After two consecutive ticks with no observable progress |
dispatch-agents |
When a wave exceeds expected duration with zero returns |
execute-plan |
When a step checkpoint is overdue |
| User | "Why did this stop?" / "Nothing is happening" |
Verify
→ verify: test -f specs/state.yaml
Handoff
Gate: READY → next: survey-context (if state unclear) or resume prior skill from state.yaml
Writes: specs/verifications/STALL-*.md
04 同仓库更多 Skills
skill-verify-fail-open-fixture
Negative-path fixture for run-skill-verify.sh — must never PASS.
negative-path
暂无简介
write-document
Write, organize, and sync high-integrity technical documents using the BMAD methodology. Ensures every document is Bold, Minimal, Actionable, and Durable. Use when creating architectural docs, technical guides, or organizing the specs/ directory.
wire-observability
Add structured JSON logging, observability commands, and idempotent setup scripts to a project. Use when a project needs production-readiness instrumentation, when user wants structured logging, or as a production-readiness gate at any phase of development.
wire-ci
CI pipeline setup with bundled, forge-neutral templates and local validation. Detects the forge from the git remote, generates workflows for supported forges, and skips honestly for the rest. The CI equivalent of wire-observability.
visual-dashboard
Start a browser-based dashboard that visualizes architecture, implementation plans, and project status. Persists artifacts in .bigpowers/dashboard/. Reads specs/state.yaml, release-plan.yaml, epics, and planning-status via HTTP API or opencode panel.