Diagnose Stall

SkillAI & models

Lets your agent figure out why a multi-step task has stalled and stopped making progress.

Use Diagnose Stall in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Diagnose Stall and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Diagnose Stall skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Diagnose StallStart free
About this skill

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.

What this skill tells your AI

The instructions your AI receives, as published by danielvm-git/bigpowers in skills/diagnose-stall/SKILL.md and read by Ahel’s review.

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

SignalLikely cause
No stdout for >5 min on a monitored loop tickSleep/watcher misconfigured or prompt never re-armed
Subagent dispatched but no completion messageAgent hung, blocked on approval, or scope too large
dispatch-agents cycle 3 reached with gapsCircuit exhausted — needs human escalation
Verify command running >15 minMissing timeout or waiting on external service
handoff.next_skill unchanged across turnsPrior skill never wrote handoff

Process

  1. Read state — specs/state.yaml: handoff.next_skill, active_flow, metrics.story_start, open decisions.
  2. Check locks — bash scripts/check-stale-locks.sh if present; read specs/agent-locks.yaml.
  3. Inspect terminals — list background shells; note PIDs, last output timestamp, exit codes.
  4. 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
  5. Recommend recovery — one action only (resume, kill PID, re-dispatch with smaller brief, escalate to user).
  6. Write report — specs/verifications/STALL-<timestamp>.md with classification, evidence, and recommended next skill.

Integration

CallerWhen to invoke
/loop (Cursor)After two consecutive ticks with no observable progress
dispatch-agentsWhen a wave exceeds expected duration with zero returns
execute-planWhen 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

Signals

GitHub stars
248
Forks
19
Last commit
Sep 2026
Advanced
Item type
skill
Key
diagnose-stall
Source
github.com/danielvm-git/bigpowers