Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/silver2dream/ai-workflow-kit/create-issuesnpx skills add silver2dream/ai-workflow-kit --skill create-issuesgit clone --depth 1 https://github.com/silver2dream/ai-workflow-kitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00059 | $0.00750 |
| Opus 5 | $0.00030 | $0.00375 |
| Sonnet 5 | $0.00012 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
create-issues scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Issues Skill
Systematic workflow for creating well-structured GitHub issues from high-level requirements.
Overview
This skill transforms user requirements into a set of well-structured, dependency-aware GitHub issues. It follows a 5-phase workflow with a mandatory user approval gate before creating any issues.
When to Use
Use this skill when:
- User invokes
/create-issues - User describes a feature or requirement that needs multiple issues
- User wants to plan work breakdown systematically
- User needs help decomposing a complex requirement
Workflow
Phase 1: Codebase Analysis
Read phases/analyze.md
Scan the project to understand:
- Repository structure and languages
- Module organization and patterns
- Existing test coverage
- Configuration from workflow.yaml
Phase 2: Requirement Breakdown
Read phases/breakdown.md
Systematically decompose the requirement:
- Identify discrete tasks
- Detect dependencies between tasks
- Assign complexity scores (1-5)
- Assign priorities (P0/P1/P2)
- Group by execution phase
Phase 3: Issue Proposal Generation
Read phases/propose.md
Generate detailed proposals:
- Full issue content with all fields
- Scope with specific file paths
- Acceptance criteria
- Verification commands
- Dependency graph visualization
Phase 4: User Approval Gate
Read phases/approval.md
Present proposals and wait for confirmation:
- Display formatted proposals
- User responds: yes/no/edit
- Only proceed if user explicitly approves
Phase 5: Issue Creation
Read phases/create.md
Create issues via GitHub CLI:
- Execute
gh issue createfor each issue - Capture returned issue numbers
- Update dependency references
- Generate final report with links
Critical Rules
- NEVER create issues without user approval
- ALWAYS show full proposal details before asking for approval
- Respect dependency order - issues with dependencies must reference actual issue numbers
- Follow commit format -
[type] subject(no colon) - Include verification commands - Go projects use
go test ./...andgo build ./...
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 110 lines · 0 tokens per session scan A b33b6aca5c97
create-issues is a skill published in the GitHub repository silver2dream/ai-workflow-kit (2 stars, last pushed 29d ago), licensed Apache-2.0. It adds 59 tokens to every session and 750 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-interactive-slides
발표문·강의안·제품 시연을 스토리보드로 구조화하고 체험형 또는 시연형 HTML·CSS·JavaScript 슬라이드로 제작·검증한다. 내용에 맞는 인터랙션, 발표자 노트, 시연 cue, 리허설과 fallback이 필요할 때 사용한다. 일반 PPTX 편집이나 정적인 문서 작성에는 사용하지 않는다.
prompt-coach
사용자가 대상 작업을 실행하지 않고 재사용 가능한 최종 프롬프트 자체를 만들거나, 막연한 아이디어를 질문으로 구체화해 프롬프트만 함께 작성하려 할 때 사용한다. 요청의 충분성을 판단해 필요한 경우에만 핵심 질문을 하고 사용자의 의도·제약·권한을 보존한 프롬프트를 반환한다. Prompt Compiler 플러그인으로 일반 작업을 요청했거나 요청을 개선한 뒤 실제 수행·검증하는 것이 주목적이면 prompt-compiler를, 기존 프롬프트의 품질 평가·비교·회귀 진단이 주목적이면 prompt-evaluator를 사용한다.
prompt-evaluator
프롬프트, 에이전트 지침과 워크플로 명세를 의도 보존, 모호성, 권한 경계, 작업 분해, capability routing, 최신성, 검증 가능성과 instruction/data boundary 관점에서 진단하고 수정안·비교 결과·회귀 평가 케이스를 작성한다. 사용자가 기존 프롬프트의 리뷰, 평가, 문제 진단, 전후 비교, 회귀 테스트, red-team 점검을 요청하거나 Prompt Compiler의 동작 품질을 검증하려 할 때 사용한다. 실행하지 않고 새 최종 프롬프트를 함께 작성하는 것이 주목적이면 prompt-coach를, 요청을 먼저 보완한 뒤 실제…
implement-async-ui-state
기존 프론트엔드에서 요청·스트림·background job·batch 작업의 비동기 상태를 실제 코드로 구현하고 검증한다. 사용자가 upload·generate·export·save·agent·tool 실행 화면에 접수·진행·사용자 입력 대기·부분 성공·오류·취소·재시도·재연결을 구현하거나 중복 실행, optimistic rollback, stale·late response와 job identity 문제를 해결해 달라고 할 때 사용한다. Dialog·Combobox·Carousel의 키보드·포커스·제스처 계약이 주 결과면…
implement-ui-interaction
기존 프론트엔드에 키보드·포커스·터치·포인터·제스처가 정확한 widget 상호작용을 구현하고 검증한다. 사용자가 Dialog, Popover, Tooltip, Menu, Combobox, Carousel, drag·swipe·pinch 또는 floating positioning을 실제 코드로 만들어 달라고 할 때 사용한다. 요청·스트림·background job·batch의 중복 실행, 취소·재시도·부분 성공 같은 비동기 작업 수명주기가 주 결과면 implement-async-ui-state를, 시간 기반 모션 자체가 주 결과면…
build-data-visualization
데이터와 사용자 과업에 맞는 차트·시각화 표현을 정하고 Bklit UI, Recharts, Apache ECharts, Observable Plot, D3 또는 기존 도구로 실제 프론트엔드에 구현·검증한다. 사용자가 대시보드 차트, 분석 화면, 실시간·대용량 시각화, 지도·네트워크·사용자 정의 그래픽, Bklit UI 설치·활용이나 접근 가능한 데이터 표현을 요청할 때 사용한다. 원칙 설명·명세만 필요하면 uiux-advisor를, 기존 차트 감사만 필요하면 uiux-auditor를 사용한다.