← 返回 Skills 市场
completetech

Agentic Delivery Skill

作者 CompleteTech · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ pending
46
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install agentic-delivery-skill
功能描述
Create CompleteTech LLC delivery execution artifacts for approved agentic development engagements, including kickoff agendas, access checklists, project plan...
使用说明 (SKILL.md)

Agentic Delivery Skill

Purpose

Create delivery execution artifacts for CompleteTech LLC agentic development engagements after a proposal/SOW or contract is approved.

System Boundary

This skill owns execution after commercial approval: kickoff, project control, evaluation, launch preparation, handoff, and support artifacts. Use agentic-proposal-skill for unapproved commercial scope, agentic-contract-skill for legal agreement artifacts, agentic-security-review-skill for security or production-readiness review, agentic-invoice-skill for billing, agentic-customer-success-skill for relationship health and renewal, and agentic-case-study-skill only after outcomes are verified and approved for proof.

Core Workflow

  1. Identify the delivery need: kickoff, access, planning, status, decisions, risk/issue, change request, prototype review, evaluation, acceptance, launch, monitoring, support, handoff, closeout, or escalation.
  2. Gather verified facts: approved scope, workflow, owners, timeline, milestones, systems, approval gates, evaluation examples, risks, dependencies, support expectations, and acceptance criteria.
  3. Use references/use-case-decision-table.md to choose the right delivery artifact.
  4. Use references/delivery-positioning.md for CompleteTech LLC delivery framing and guardrails.
  5. Use references/delivery-catalog.md for the near-exhaustive delivery artifact library.
  6. Keep delivery practical and bounded. Do not fabricate client facts, approvals, test results, metrics, regulated-use assurances, legal claims, or production readiness.

Artifact Selection Guide

  • First meeting after signature: use kickoff-agenda.
  • Need client systems/docs/API access: use client-access-checklist.
  • Need execution structure: use project-plan.
  • Tracking milestone progress: use milestone-tracker.
  • Regular client update: use weekly-status-update.
  • Capturing decisions: use decision-log.
  • Capturing risks or active issues: use risk-and-issue-log.
  • Scope change request: use change-request-intake.
  • Blocking prerequisites: use dependency-tracker.
  • Communication cadence: use stakeholder-communication-plan.
  • Prototype review: use prototype-review-checklist.
  • Evaluation run: use evaluation-run-report.
  • Test summary: use test-results-summary.
  • Formal acceptance: use acceptance-review-packet.
  • Launch preparation: use launch-readiness-checklist.
  • Observability requirements: use monitoring-plan.
  • Post-handoff help: use support-plan.
  • Handoff preparation: use handoff-checklist.
  • Admin/operator documentation: use administrator-runbook.
  • Reviewer or user training: use user-reviewer-quickstart.
  • After launch: use post-launch-review.
  • Retrospective: use lessons-learned.
  • Project close: use closeout-summary.
  • Incoming support request: use support-ticket-intake.
  • Escalation path: use escalation-procedure.
  • Deployment-specific rollout: use deployment-runbook.
  • Acceptance defects: use defect-remediation-plan.
  • Client training session: use training-session-plan.

When several artifacts fit, choose the one closest to the operational event. Do not mark launch-ready, accepted, or complete unless the verified evidence supports it.

Quality Rules

  • Execute the approved scope; route new scope into change request intake.
  • Protect human approval gates for external communications, production changes, purchases, data export, and material business decisions.
  • Track decisions, risks, issues, dependencies, and acceptance evidence explicitly.
  • Verify evaluation examples before acceptance.
  • Document logs, monitoring, runbooks, quickstarts, support, and handoff.
  • Use TBD or open questions for unknowns.

Resource Guide

  • references/delivery-positioning.md: load for CompleteTech LLC delivery language and boundaries.
  • references/use-case-decision-table.md: load when choosing a delivery artifact.
  • references/delivery-lifecycle.md: load for flow from kickoff through support and closeout.
  • references/delivery-catalog.md: load for the near-exhaustive delivery template library.
  • references/template-index.json: machine-readable template metadata used by the renderer.
  • scripts/render_delivery.py: list delivery artifacts or render a draft with placeholders.

Renderer

python3 scripts/render_delivery.py --list
python3 scripts/render_delivery.py --stage status --list
python3 scripts/render_delivery.py --template kickoff-agenda --var client_name=Acme --var workflow="support triage"

Rendered artifacts are drafts. Replace placeholders with verified project facts before sending or storing them.

Rendering to a Branded PDF

Artifacts from this skill are delivered as branded CompleteTech LLC PDF documents, not raw Markdown. The renderer emits the PDF (and prints the Markdown) in one command, using the same reportlab branding engine as the contract skill:

pip install -r requirements.txt
python3 scripts/render_delivery.py --template launch-readiness-checklist \
  --out artifact.pdf --png artifact.png \
  --title "Launch Readiness Checklist" --doc-type "DELIVERY ARTIFACT" \
  --subtitle "Northwind Trading Co. — Support Email Triage Agent (Pilot)" --meta "DOCUMENT NO.=DEL-2026-0233" --meta "DATE=2026-06-12" \
  --var client_name="Client Name" --var workflow="support triage"
  • --no-pdf emits Markdown only (the original behavior); --no-cover drops the cover page.
  • Already drafted the Markdown yourself? Render it directly: python3 scripts/render_pdf.py --markdown artifact.md --out artifact.pdf --logo assets/logo.png --title "...".
  • The PDF supports a Markdown subset: #/##/### headings, paragraphs, - bullets, tables, > callouts, **bold**, and [PAGE_BREAK]. PDF requires reportlab; the optional --png preview requires pypdfium2 and pillow. See assets/examples/ for a rendered example.

Certificate Receipt Guidance

The skill remains usable without a classroom key. When certificate credit is needed, use scripts/request_receipt.py after the skill run. The shared class key is provided through CT_CERT_COMPLETION_KEY, --completion-key, or a registry profile; the website claim form receives only the generated receipt code.

Receipt requests include this skill ID: agentic-delivery-skill. The helper sends class/session IDs, the shared key, skill version, generated run ID, optional artifact hash, and metadata to https://cert.complete.tech/api/skill-runs. The student claims the certificate at https://cert.complete.tech/claim with the returned receipt.

Do not print, store, or commit real classroom completion keys.

如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install agentic-delivery-skill
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /agentic-delivery-skill 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
Fix installed package validation and packaged contract template
v1.0.0
Initial CompleteTech public ClawHub release
元数据
Slug agentic-delivery-skill
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Agentic Delivery Skill 是什么?

Create CompleteTech LLC delivery execution artifacts for approved agentic development engagements, including kickoff agendas, access checklists, project plan... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 46 次。

如何安装 Agentic Delivery Skill?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install agentic-delivery-skill」即可一键安装,无需额外配置。

Agentic Delivery Skill 是免费的吗?

是的,Agentic Delivery Skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Agentic Delivery Skill 支持哪些平台?

Agentic Delivery Skill 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Agentic Delivery Skill?

由 CompleteTech(@completetech)开发并维护,当前版本 v1.0.1。

💬 留言讨论