القائمة
Start an OpenClaw coding session from DevCD's local Action Packet before asking the developer to recap.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | devcd-continuity |
| description | Start an OpenClaw coding session from DevCD's local Action Packet before asking the developer to recap. |
| metadata | {"openclaw":{"requires":{"bins":["devcd"]}}} |
The YAML frontmatter keys name and description are the discovery signal loaded automatically.
The remaining SKILL.md body is the complete skill guidance and is loaded on demand.
Use this when an OpenClaw agent is starting or resuming coding work in a repository where DevCD is configured as an MCP server named devcd.
Your job is to create the Turn-0 continuity moment: start from local context, not from a user recap.
Before asking the developer to explain the task, read:
devcd://context/action-packetdevcd://context/policy-summaryIf the Action Packet is ready, begin your first reply with:
do_not_repeat warnings;Then ask only for confirmation or correction. Do not ask the developer to re-summarize work that DevCD already provided.
If ready_for_agent is false or the Action Packet has no goal:
devcd://context/continuity-packet for broader context.Do not invent missing context.
Use compact language. The moment should feel like continuity, not a report.
I picked up DevCD context.
Goal: <current goal>
Next: <next action>
Blocked by: <blocker or none visible>
I will not repeat: <do_not_repeat item or none visible>
Policy note: <withheld summary or none visible>
Proceeding with <next action>. Confirm or redirect.
If the user confirms, continue work normally and keep policy boundaries intact.
Capture continuity metadata on key execution triggers during work.
Close a session with a compact handoff before switching agents.
Recovery path when continuity packet readiness or tooling is limited.
Mandatory first move for local DevCD continuity before asking for recap.
Use when a change affects architecture, slice boundaries, API contracts, policy rules, or memory schemas. Creates or updates Architecture Decision Records (ADRs) before implementation. Keywords: ADR, decision record, proposed, architecture boundary, policy change, API contract, slice design.
Use when an agent ignores instructions, loses context, misuses tools, produces weak handoffs, behaves unreliably across multiple steps, or needs observability and operational guardrails. Covers instruction loading checks, handoff discipline, context compaction, multi-agent coordination, failure-mode analysis, and verification gates for agent-driven work.