fix
starsforks
How to install fix?
parcadei/continuous-claude-v3/fix
$npx -y skills add parcadei/Continuous-Claude-v3 --skill fixMeta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.
SKILL.md
| 1 | # Fix |
| 2 | |
| 3 | Workflow orchestrator for bug investigation and resolution. Chains specialized skills based on issue scope. |
| 4 | |
| 5 | ## Usage |
| 6 | |
| 7 | ``` |
| 8 | /fix <scope> [options] [description] |
| 9 | ``` |
| 10 | |
| 11 | ## Question Flow (No Arguments) |
| 12 | |
| 13 | If the user types just `/fix` with no or partial arguments, guide them through this question flow. Use AskUserQuestion for each phase. |
| 14 | |
| 15 | ### Phase 0: Workflow Selection |
| 16 | |
| 17 | ```yaml |
| 18 | question: "What would you like to fix?" |
| 19 | header: "Fix type" |
| 20 | options: |
| 21 | - label: "Help me choose (Recommended)" |
| 22 | description: "I'll ask questions to pick the right fix workflow" |
| 23 | - label: "Bug - something is broken" |
| 24 | description: "Chain: investigate → diagnose → implement → test → commit" |
| 25 | - label: "Hook - Claude Code hook issue" |
| 26 | description: "Chain: debug-hooks → hook-developer → implement → test" |
| 27 | - label: "Dependencies - import/package errors" |
| 28 | description: "Chain: preflight → research → plan → implement → qlty-check" |
| 29 | - label: "PR Comments - address reviewer feedback" |
| 30 | description: "Chain: github-search → research → plan → implement → commit" |
| 31 | ``` |
| 32 | |
| 33 | **Mapping:** |
| 34 | - "Help me choose" → Continue to Phase 1-4 questions |
| 35 | - "Bug" → Set scope=bug, skip to Phase 2 (issue details) |
| 36 | - "Hook" → Set scope=hook, skip to Phase 2 (issue details) |
| 37 | - "Dependencies" → Set scope=deps, skip to Phase 2 (issue details) |
| 38 | - "PR Comments" → Set scope=pr-comments, skip to Phase 2 (issue details) |
| 39 | |
| 40 | **If Answer is Unclear (via "Other"):** |
| 41 | ```yaml |
| 42 | question: "I want to understand what kind of fix you need. Did you mean..." |
| 43 | header: "Clarify" |
| 44 | options: |
| 45 | - label: "Help me choose" |
| 46 | description: "Not sure - guide me through questions" |
| 47 | - label: "Bug - something is broken" |
| 48 | description: "Code isn't working as expected" |
| 49 | - label: "Hook - Claude Code hook issue" |
| 50 | description: "Hooks not firing or producing wrong output" |
| 51 | - label: "Neither - let me explain differently" |
| 52 | description: "I'll describe my issue" |
| 53 | ``` |
| 54 | |
| 55 | ### Phase 1: Issue Type |
| 56 | |
| 57 | ```yaml |
| 58 | question: "What kind of issue are you dealing with?" |
| 59 | header: "Issue type" |
| 60 | options: |
| 61 | - label: "Something is broken/not working" |
| 62 | description: "Bug in the code" |
| 63 | - label: "Claude Code hook not firing" |
| 64 | description: "Hook-specific debugging" |
| 65 | - label: "Import/dependency errors" |
| 66 | description: "Package or module issues" |
| 67 | - label: "Need to address PR feedback" |
| 68 | description: "Reviewer comments to fix" |
| 69 | ``` |
| 70 | |
| 71 | **Mapping:** |
| 72 | - "Something broken" → bug scope |
| 73 | - "Hook not firing" → hook scope |
| 74 | - "Import errors" → deps scope |
| 75 | - "PR feedback" → pr-comments scope |
| 76 | |
| 77 | ### Phase 2: Issue Details |
| 78 | |
| 79 | ```yaml |
| 80 | question: "Can you describe the issue?" |
| 81 | header: "Details" |
| 82 | options: [] # Free text - user describes the problem |
| 83 | ``` |
| 84 | |
| 85 | Capture the error message, unexpected behavior, or PR link. |
| 86 | |
| 87 | ### Phase 3: Investigation Depth |
| 88 | |
| 89 | ```yaml |
| 90 | question: "How should I investigate?" |
| 91 | header: "Investigation" |
| 92 | options: |
| 93 | - label: "Diagnose and fix" |
| 94 | description: "Find the problem and implement a fix" |
| 95 | - label: "Diagnose only (dry run)" |
| 96 | description: "Just tell me what's wrong, don't change code" |
| 97 | - label: "Quick fix" |
| 98 | description: "I know the issue, just fix it fast" |
| 99 | ``` |
| 100 | |
| 101 | **Mapping:** |
| 102 | - "Diagnose only" → --dry-run |
| 103 | - "Quick fix" → skip investigation, go straight to spark agent |
| 104 | |
| 105 | ### Phase 4: Testing & Commit |
| 106 | |
| 107 | ```yaml |
| 108 | question: "After fixing, should I..." |
| 109 | header: "After fix" |
| 110 | multiSelect: true |
| 111 | options: |
| 112 | - label: "Write a regression test" |
| 113 | description: "Prevent this bug from recurring" |
| 114 | - label: "Commit the fix" |
| 115 | description: "Create a git commit" |
| 116 | - label: "Just fix, nothing else" |
| 117 | description: "I'll handle tests and git" |
| 118 | ``` |
| 119 | |
| 120 | **Mapping:** |
| 121 | - No "regression test" → --no-test |
| 122 | - No "commit" → --no-commit |
| 123 | |
| 124 | ### Summary Before Execution |
| 125 | |
| 126 | ``` |
| 127 | Based on your answers, I'll run: |
| 128 | |
| 129 | **Scope:** bug |
| 130 | **Issue:** "Login button not responding on Safari" |
| 131 | **Chain:** sleuth (investigate) → spark (fix) → arbiter (test) → commit |
| 132 | **Options:** (none) |
| 133 | |
| 134 | Proceed? [Yes / Adjust settings] |
| 135 | ``` |
| 136 | |
| 137 | ## Scopes |
| 138 | |
| 139 | | Scope | Chain | Description | |
| 140 | |-------|-------|-------------| |
| 141 | | `bug` | debug -> implement_task -> test-driven-development -> commit | General bug fix workflow | |
| 142 | | `hook` | debug-hooks -> hook-developer -> implement_task -> test hook | Hook-specific debugging | |
| 143 | | `deps` | dependency-preflight -> oracle -> plan-agent -> implement_plan -> qlty-check | Dependency issues | |
| 144 | | `pr-comments` | github-search -> research-codebase -> plan-agent -> implement_plan -> commit | Address PR feedback | |
| 145 | |
| 146 | ## Options |
| 147 | |
| 148 | | Option | Effect | |
| 149 | |--------|--------| |
| 150 | | `--no-test` | Skip regression test creation | |
| 151 | | `--dry-run` | Diagnose only, don't implement fix | |
| 152 | | `--no-commit` | Don't auto-commit the fix | |
| 153 | |
| 154 | ## Workflow |
| 155 | |
| 156 | ### Phase 1: Parse Arguments |
| 157 | |
| 158 | ```bash |
| 159 | # Parse scope and options |
| 160 | SCOPE="${1:-bug}" |
| 161 | NO_TEST=false |
| 162 | DRY_RUN=false |
| 163 | NO_COMMIT=false |
| 164 | |
| 165 | for arg in "$@"; do |
People who liked this also viewed
6 picksType
- azure-diagnosticsDebug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deploySkillsJul 2026
- systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesSkillsJul 2026
- safe-debugRigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training SkillsMay 2026
- explore-runRigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subseSkillsMay 2026
- minimal-run-and-auditRigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation SkillsMay 2026
- insforge-debugUse when diagnosing problems in an InsForge project — reactive failures (SDK error object, HTTP 4xx/5xx, gateway timeout 502/503/504, edge function failure or timeout, login/OAuth/auth errors, RLS denSkillsJul 2026
