agentleFS
Gingiris-1031Gingiris-1031/gingiris-skills/skills/gr-opc-service-validation/SKILL.md

gr-opc-service-validation

Skill89 starsChanged 32 days agoMITView on GitHub

Use this skill to validate an expertise-based solo service with a bounded showcase or paid pilot, client-fit checks, pricing evidence, delivery capacity and repeat-demand signals. 适用于 OPC 服务验证、服务产品化、试单复盘和接单容量判断;输出可执行试单卡及继续/修改/停止决定。

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use known context, ask only the missing decision-critical question, then produce a usable draft.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

OPC Service Validation / OPC 服务验证

Scope / 范围

Validate one professional service against real buyer behavior and sustainable delivery. This is the focused experiment stage; gingiris-solopreneur-coach covers broader direction-finding and coaching. Neither is required to install the other. Do not rename the user's business into consulting if they chose a product; test the relevant assumption or explain that another workflow fits better.

本 Skill 聚焦一个专业服务的真实需求与可持续交付验证;已有 gingiris-solopreneur-coach 负责更广的方向探索与陪跑。两者可独立使用。不把用户选择的产品业务强改为咨询,也不要求辞职、注册公司或先免费劳动。

Use known context, ask only the missing decision-critical question, then produce a usable draft. Follow the user's language; bilingual references are available, but do not duplicate every answer unless requested.

使用已有背景,只补影响决定的关键信息,然后产出草稿。跟随用户语言;不默认每次双语输出。

Workflow / 流程

  1. Evidence of ability / 能力证据:列出实际完成的任务、本人贡献、可展示产物、结果口径和可使用权限。区分平台资源与个人能力。能力标签或过往职位本身不证明可交付。List completed work, personal contribution, artifacts and permission to show it; distinguish personal ability from platform advantages.
  2. One bounded offer / 一个有边界的服务:指定买方、任务、交付物、排除项、所需客户输入、时间与验收。避免“什么都能帮”。Name the buyer, task, deliverable, exclusions, required input, timeline and acceptance criteria.
  3. Fit before work / 先筛适配:确认问题优先级、决策者、预算/付款意愿、执行配合与数据可得性。顾问、创始人与内部执行者分别承担什么?Qualify urgency, decision authority, willingness to pay, access and execution ownership; avoid solving an unowned problem.
  4. Bounded showcase or paid pilot / 有上限的样例或付费试单:读取 试单模板。声明教学样例、真实项目和已验收案例的区别;免费/折价仅是可选实验,写工时/支出上限,不承诺收入。Read the pilot worksheet; label demonstrations versus accepted client work. Free work is optional, capped and never required.
  5. Pricing and capacity / 定价与容量:比较同范围报价、交付成本、返工与沟通负担、客户接受度和个人可持续程度。写清币种、税费/费用口径、付款节点和范围变更方式;具体法律条款需另按需求核验。Compare like-for-like scope and full effort, not a celebrity consultant's rate. Define scope changes and payment milestones.
  6. Accept, settle, review / 验收、回款、复盘:交付完成、客户验收、实际到账、复购/转介绍分开记录。读取 复盘与容量表,给继续/修改/暂停结论及改变结论的证据。Delivery, acceptance, payment and repeat demand are separate observations.

Decision discipline / 判断纪律

Warm feedback is not payment evidence. One successful delivery does not prove PMF or recurring revenue. Track the next similar request, scope stability, repeat purchase and marginal effort. A narrow service with healthy capacity can be a valid destination; hiring or platform-building is optional.

称赞不是付款;一单成功不等于 PMF、订阅收入或可复制商业模式。观察相似需求、范围稳定性、复购与新增交付成本。保持小规模也是有效选择,团队化与平台化并非必经终点。

A useful finish is a filled pilot card, one next action, an observation window and a stopping condition. Lack of evidence is a reason to reduce uncertainty, not invent conversion rates. Income targets and workload limits are personal inputs, not universal thresholds.

完成标准是可填写并执行的试单卡、下一步动作、观察窗口与停止条件。收入目标与工时上限来自个人条件,不套用“赚5000即可辞职”等阈值。联系客户、签约、收款、公开案例均按用户实际授权执行。

Provenance / 来源

Adapted from Gingiris's service-productization guides and October–November 2026 workshop/OPC retrospective material. Published package contains general methods and labeled synthetic worksheets, not private transcripts, named client metrics or a promise to reproduce the author's income.

基于 Gingiris 服务产品化指南及 2026 年 10–11 月 workshop/OPC 复盘提炼。仅分发通用方法与明确标注的教学样例,不附私人逐字稿、客户数据,不承诺复现作者收入。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.