yaojingang/yao-open-skills is a public collection of reusable AI skills for research, decision-making, business analysis, learning, and document creation. It serves people who want repeatable, maintainable AI workflows instead of isolated prompts, and catalogued add-ons are published skills from this collection.
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 skills add yaojingang/yao-open-skills --skill yao-positioning-skillgit clone --depth 1 https://github.com/yaojingang/yao-open-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yaojingang/yao-open-skills/yao-positioning-skill)<a href="https://agentmods.dev/skills/yaojingang/yao-open-skills/yao-positioning-skill"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-open-skills/yao-positioning-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yaojingang/yao-open-skills/yao-positioning-skill"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-open-skills/yao-positioning-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00114 | $0.01282 |
| Opus 5 | $0.00057 | $0.00641 |
| Sonnet 5 | $0.00023 | $0.00256 |
| Haiku 4.5 | $0.00011 | $0.00128 |
Grade A, and why
yao-positioning-skill 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 12d ago.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
定位分析与报告
Owned Job
- 为个人、课程、产品、服务或品牌生成定位报告。
- 研究五类竞争参照。
- 比较 2 至 3 套方案并推荐或降级。
Workflow
- 按
references/intake-and-readiness-gate.md接受问答、附件或 URL，整理符合templates/intake-brief.schema.json的intake-brief.json，运行python3 scripts/validate-intake.py intake-brief.json。 - 仅当校验返回
intake_ready才开始检索；否则停止并使用返回的缺失项与示例，每轮追问 1 至 3 个问题。开始前回显对象、目的、范围、已收资料、自述项和待核验项。 - 选择
local、standard或deep研究模式。需要当前竞品、价格或市场事实时必须联网核验。 - 读取
references/theory-system.md。个人 IP 或课程任务再读references/course-marketing-method.md。 - 按
references/ai-workflow.md建立主张清单、竞争集合、研究计划和证据台账。 - 按
references/source-credibility-policy.md区分事实、自述、推断、假设和建议；来源必须通过权威性、主张适配、直接性、时效性、独立性和市场适配检查。 - 按
references/competitor-research-method.md研究竞争与心智位置。禁止把“未发现公开证据”写成“不存在”。 - 按
references/demand-and-differentiation-method.md分析需求、市场空位和 D6 优势，执行否决规则。 - 通过诊断与推荐门槛后生成 2 至 3 套定位方案并压力测试，只推荐一套；不通过时只输出初步观察和补证计划。
- 按
references/plain-language-positioning-method.md生成通俗的心智快照，再进入可视化报告。 - 先生成符合
templates/report-data.schema.json的 JSON，再运行python3 scripts/validate-report-data.py positioning-report-data.json。 - 校验通过后运行
python3 scripts/render-report.py positioning-report-data.json --out positioning-report。 - 运行
python3 scripts/review-report.py positioning-report，修复语义、图表、移动端、打印和跨格式回归；不得通过删证据或升级置信度消除警告。 - 按
references/report-contract.md核对 HTML、JSON、Markdown 的结论、指标和引用一致性。模板或图表变更再按references/report-review-method.md执行三视口与 A4 PDF 栅格化审校。
Downgrade Rules
- 研究就绪门槛未通过：只补信息，不检索竞品、不生成方案。
- 诊断门槛未通过：只输出初步观察和补证计划。
- 无法访问外部资料且用户未提供竞品：进入本地证据模式，输出补证清单。
- 没有用户需求证据：不得宣称市场空位。
- 没有可证明优势：输出能力建设建议，不制造差异化标签。
- 涉及第一、唯一、领先或效果承诺：要求独立证据和合规审查。
Output Contract
默认交付：
positioning-report.html：离线可视化决策报告。positioning-report-data.json：唯一结构化事实源。positioning-report.md：无脚本降级版与审计记录。
先用一页心智快照说清结论，再提供需求、竞争、优势、方案、行动、风险、证据和验证计划。个人 IP 或课程增加四层一致性，课程再增加行动路径、4P 与课程机制。缺失数据展示“证据不足”，不得伪造图表或总分。
交付前 review-report.py 必须通过。来源时效和证据警告可保留，但必须在报告和审校结果中可见；零警告交付使用 --strict。
Reference Map
- 理论：
references/theory-system.md、references/plain-language-positioning-method.md、references/course-marketing-method.md - 执行：
references/intake-and-readiness-gate.md、references/ai-workflow.md - 研究：
references/source-credibility-policy.md、references/competitor-research-method.md - 分析：
references/demand-and-differentiation-method.md - 交付：
references/report-contract.md、references/report-review-method.md、references/html-report-spec.md、references/metric-dictionary.md - 渲染资产：
assets/report-template.html、assets/echarts.min.js - 系统说明：
reports/positioning-skill-system-overview-2026-07-16/index.html - 分发净化：
scripts/sanitize-package.py（仅在重建 ZIP 后执行）
What ships with it
36 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.
- agents/interface.yaml 1019 B
- assets/echarts.min.js 1096 KB runs code
- assets/LICENSE-echarts.txt 12 KB
- assets/NOTICE-echarts.txt 376 B
- assets/report-template.html 94 KB
- LICENSE 1.0 KB
- manifest.json 888 B
- README.md 4.4 KB
- references/ai-workflow.md 6.3 KB
- references/competitor-research-method.md 4.7 KB
- references/course-marketing-method.md 4.9 KB
- references/demand-and-differentiation-method.md 3.9 KB
- references/html-report-spec.md 5.0 KB
- references/intake-and-readiness-gate.md 8.9 KB
- references/metric-dictionary.md 4.7 KB
- references/plain-language-positioning-method.md 4.5 KB
- references/report-contract.md 5.3 KB
- references/report-review-method.md 3.9 KB
- references/source-credibility-policy.md 6.6 KB
- references/theory-system.md 11 KB
- reports/positioning-skill-system-overview-2026-07-16/index.html 71 KB
- requirements.txt 91 B
- scripts/render-report.py 21 KB runs code
- scripts/report_model.py 45 KB runs code
- scripts/review-report.py 10 KB runs code
- scripts/sanitize-package.py 5.7 KB runs code
- scripts/schema_validator.py 5.9 KB runs code
- scripts/validate-intake.py 5.4 KB runs code
- scripts/validate-report-data.py 1.9 KB runs code
- security/permission_policy.json 1.3 KB
- security/permission_policy.md 1015 B
- templates/evidence-ledger.md 924 B
- templates/intake-brief.schema.json 2.2 KB
- templates/intake-questionnaire.md 1.6 KB
- templates/positioning-report.md 1.2 KB
- templates/report-data.schema.json 22 KB
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.
- 12d ago First seen · 64 lines · 114 tokens per session scan A 49f9c8be536a
yao-positioning-skill is a skill published in the GitHub repository yaojingang/yao-open-skills (1,311 stars, last pushed 14d ago), licensed MIT. It adds 114 tokens to every session and 1,282 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…