Resolve Failures
Failure resolution executor. ALWAYS invoke this skill when instructed to fix test failures in a worktree. Do not read test output or edit code directly — use this skill first to load the failure resolution workflow.
Install
npx skills add TalonT-Org/AutoSkillit --skill resolve-failuresgit clone --depth 1 https://github.com/TalonT-Org/AutoSkillit.git /tmp/AutoSkillit
mkdir -p ~/.claude/skills
cp -r /tmp/AutoSkillit/src/autoskillit/skills_extended/resolve-failures ~/.claude/skills/resolve-failuresPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Resolve Failures Skill
Fix test failures in a worktree implemented by `/autoskillit:implement-worktree-no-merge`, leaving the worktree green and unmerged for the orchestrator's merge gate.
## When to Use
- MCP orchestrator calls this via `run_skill` after `ci_watch` reports a CI failure
- MCP orchestrator calls this via `run_skill` after `test_check` returns FAIL
- MCP orchestrator calls this via `run_skill` when `merge_worktree` returns `dirty_tree`
- Takes three required positional arguments: `{worktree_path} {plan_path} {base_branch}`
- Optional trailing args (passed by recipe): `{ci_conclusion} {ci_failed_jobs} {diagnosis_path}`
- Remediates test failures only — the orchestrator is responsible for calling `merge_worktree` after verify passes.
- Emits a typed `verdict` output token so the recipe can route correctly (never silently re-pushes).
## Critical Constraints
**NEVER:**
- Merge if ANY test fails
- Merge via `merge_worktree` or any other mechanism
- Call `merge_worktree` MCP tool
- Make changes unrelated to fixing test failures
- Exceed 3 fix-and-retest iterations
- Delete the worktree if tests still fail after max attempts
- Modify the plan file
- Create files outside `{{AUTOSKILLIT_TEMP}}/resolve-failures/` directory
- Report `fixes_applied=0` when CI has identified a specific failing test
**ALWAYS:**
- Read the plan first to understand implementation intent
- Commit each fix iteration separately with descriptive messagesDetails
- Skill name
resolve-failures- Repository
- TalonT-Org/AutoSkillit
- Path
src/autoskillit/skills_extended/resolve-failures/SKILL.md- License
- MIT
- Repo updated
- 8 November 2026
FAQ
What does the Resolve Failures skill do?
Failure resolution executor. ALWAYS invoke this skill when instructed to fix test failures in a worktree. Do not read test output or edit code directly — use this skill first to load the failure resolution workflow.
How do I install the Resolve Failures skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add TalonT-Org/AutoSkillit --skill resolve-failures. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Resolve Failures popular?
It lives in TalonT-Org/AutoSkillit, which has 5 GitHub stars and 1 forks.
Related skills
Analyze Prs
5TalonT-Org/AutoSkillit
Analyze all open PRs targeting a base branch — determine merge order, identify file overlaps, and tag each PR as simple or needs_check for complexity. Use at the start of a PR consolidation workflow.
Arch Lens C4 Container
5TalonT-Org/AutoSkillit
Create C4 Container architecture diagram showing static structure, building blocks, and technology choices. Anatomical lens answering "How is it built?
Arch Lens Concurrency
5TalonT-Org/AutoSkillit
Create Concurrency architecture diagram showing parallel execution patterns, thread pools, synchronization, and barriers. Physiological lens answering "How does parallelism work?
Review Promotion
5TalonT-Org/AutoSkillit
Reviewer-facing deep analysis of an integration-to-main promotion. Performs domain risk scoring, breaking change audit, regression risk assessment, test coverage delta, and cross-domain dependency analysis. Use when you want a reviewer's guide before approving a promotion PR.
Exp Lens Severity Testing
5TalonT-Org/AutoSkillit
Analyze severity of experimental tests — adversarial cases, negative controls, falsification tests, easy-pass detection, and confirmatory theater. Falsificationist lens answering "Would this design have caught the error?
Validate Audit
5TalonT-Org/AutoSkillit
Validate audit findings from audit-arch, audit-tests, or audit-cohesion against actual code, git history, and design intent using 9–10 parallel subagents. Removes contested findings, documents exceptions, adjusts severities. Use when user says "validate audit", "validate findings", "validate report", or "check audit results".
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.