skills.rest
Hexalith
HexalithOFFICIAL
Explore all skills by this author →
WebsiteGitHub

bmad-loop-resolve

Resolves CRITICAL escalations in paused bmad-loop runs by updating frozen specs interactively.

Updated Mar 1, 2026
Search Tags:#workflow orchestration#interactive session#spec editing#bmad-loop#escalation resolution#story re-drive#intent gap
One-click install
npx skills add https://github.com/Hexalith/Hexalith.Parties --skill bmad-loop-resolve-hexalith
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-loop-resolve
Source: https://github.com/Hexalith/Hexalith.Parties/tree/main/.agents/skills/bmad-loop-resolve
Command: npx skills add https://github.com/Hexalith/Hexalith.Parties --skill bmad-loop-resolve-hexalith

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When an automated bmad-loop run pauses because a dev or review session hit a CRITICAL escalation — a contradiction or gap in the frozen spec it could not safely resolve alone — this Skill provides an interactive session to disambiguate the spec with a human and unblock the run. ## Core Features & Use Cases - Escalation triage: Reads the orchestrator-written context.json to present recorded escalations, the frozen spec, and the pause reason to the human with concrete resolution options. - Frozen spec correction: Amends the <frozen-after-approval> block and acceptance criteria so a fresh dev session has exactly one correct reading, then writes a resolution.json marker so the orchestrator can re-arm the story. - Worktree and sentinel handling: Correctly routes spec edits based on spec_reaches_the_redrive and redrive_base_ref, handles review-stage intent-gap patch restores, and resolves stories-mode sentinels and ambiguous story-file matches. - Use Case: A review session escalates because the spec is silent on empty-list behavior for a CLI command; you invoke this Skill, review the saved patch as evidence, agree with the human on the intended behavior, amend the spec, and record the resolution so the run resumes. ## Quick Start Invoke the skill with /bmad-loop-resolve <story-key> after a bmad-loop run pauses on a CRITICAL escalation, then read the resolve context file it points to.

Frequently Asked Questions about bmad-loop-resolve

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I resolve a paused bmad-loop run after a CRITICAL escalation?▼

Invoke /bmad-loop-resolve with the escalated story key, read the context.json at $BMAD_LOOP_RESOLVE_CONTEXT, present the escalation evidence and options to the human, amend the frozen spec with the agreed decision, and write the resolution.json marker so the orchestrator can re-arm the story.

What is the difference between bmad-loop-resolve and automated dev or review sessions?▼

This session is interactive: a human is present and the skill is expected to ask questions and present options. The automated dev/review sessions run with never-ask rules, while this session exists precisely to get a human decision on ambiguities automation could not resolve.

Why did my spec edit not reach the re-drive after resolving an escalation?▼

When spec_reaches_the_redrive is false, the edited spec lives in a discarded worktree. If redrive_base_ref names a branch, the correction must be committed on that branch; if it is HEAD, the edit must be re-applied uncommitted in the main checkout.

When should I include restore_patch in the resolution marker?▼

Include restore_patch only when a review-stage intent-gap escalation saved a patch, restore_supported is true, and the human confirms the attempted implementation was correct. Omit it when the attempted reading was wrong or when resolution commits overlap the patch's files.

Can bmad-loop-resolve implement the fix or commit code itself?▼

No. The skill only edits spec content and writes the resolution marker. It must not implement features, run tests, commit, change sprint-status.yaml, or set the spec status field; the orchestrator handles re-arming and re-dispatch deterministically.

What happens if an escalation cannot be resolved in the session?▼

If the human defers or the fix requires out-of-scope changes like a PRD or architecture update, do not write the resolution marker. Exiting without it leaves the story escalated and the run paused, which is the safe default.

Related Skills

Explore More Software Engineering Skills→
HexalithHexalith

bmad-loop-resolve

Resolves CRITICAL escalations in paused bmad-loop runs by updating frozen specs interactively.

Official
Advanced
unbakedcosmosunbakedcosmos

bmad-loop-resolve

Resolves CRITICAL escalations in paused bmad-loop runs by updating frozen specs interactively.

Community
Intermediate
OpenLitterMapOpenLitterMap
132

achievements-system

Evaluate uploads, streaks, and per-tag counts against seeded thresholds.

Official
Advanced
0xHoneyJar0xHoneyJar
5

model-usage

Summarize per-model AI costs from CodexBar CLI logs.

Official
Intermediate