ai-toolkit-rules
Mandatory engineering, security, testing, git, performance, quality, and response rules.…
Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report.
$ npx -y skills add softspark/ai-toolkit --skill triage-issue --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/triage-issueContext preview
The summary Claude sees to decide when to auto-load this skill.
Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report.
name: triage-issue description: "Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report." user-invocable: true effort: high argument-hint: "[bug description or symptom]" agent: debugger context: fork allowed-tools: Read, Grep, Glob, Bash, Agent
$ARGUMENTS
Investigate a bug, find root cause, and create a GitHub issue with a TDD fix plan. Mostly hands-off.
/triage-issue [bug description or symptom]
1. **Captures** problem description (ONE question max) 2. **Explores** codebase deeply for root cause 3. **Identifies** fix approach 4. **Designs** TDD fix plan (RED→GREEN cycles) 5. **Creates** GitHub issue via `gh issue create`
Get brief description. If not provided, ask ONE question: "What's the problem you're seeing?"
Do NOT ask follow-up questions. Start investigating immediately.
Use Agent (subagent_type=Explore) to deeply investigate:
| Target | What to look for | |--------|-----------------| | Manifestation | Where the bug appears (entry points, UI, API) | | Code path | Trace the flow from trigger to symptom | | Root cause | Why it fails (not just the symptom) | | Related code | Similar patterns, adjacent modules, existing tests | | Recent changes | `git log` on relevant files | | Working patterns | Similar code elsewhere that works correctly |
Determine:
Ordered list of RED→GREEN cycles. Each cycle is one vertical slice:
Rules:
Use `gh issue create` with template below. Share URL immediately.
<issue-template>
What was found during investigation:
Do NOT include file paths, line numbers, or implementation details. Describe modules, behaviors, and contracts.
1. **RED**: Write test that [expected behavior] **GREEN**: [Minimal change to pass]
2. **RED**: Write test that [next behavior] **GREEN**: [Minimal change to pass]
**REFACTOR**: [Cleanup after all tests pass]
</issue-template>
AI coding toolkit with machine-enforced safety, 116 skills, 44 agents, lifecycle hooks, persona presets, opt-in plugin packs, and benchmark tooling.
Repo: softspark/ai-toolkit
Mandatory engineering, security, testing, git, performance, quality, and response rules.…
Searches past coding sessions for observations, decisions, context. Triggers: mem-search,…
Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. Triggers: a11y, accessibility, WCAG,…
Creates new specialized agents with frontmatter, tools, delegation. Triggers: new agent,…
Analyzes code quality, complexity, patterns across codebase. Triggers: quality report,…
API design: naming, versioning, pagination, idempotency, OpenAPI, error contracts and safe…