القائمة
Use when recording durable preferences, decisions, deferred options, workspace facts, open questions, or when the user chooses a lightweight path over a more robust option.
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
Use when the user proposes a need, request, feature, design/refactor, bug report, symptom, phenomenon, vague correction, or expected-vs-actual mismatch before implementation. This is the second-priority skill after using-just-demand, including when a conversation pivots from ordinary Q&A to a concrete request, bug, or correction.
Load this skill first for repo work so the correct just-demand routing rules are applied before other workflow skills.
Use when a formal work item is ready to execute, when dispatching just-demand-researcher, just-demand-coder, just-demand-tester, or just-demand-advisor subagents, or when building context for focused execution.
Use when the user proposes a new goal, feature, bugfix, design, refactor, research item, UI request, or any unclear work that may become a formal work item. Shapes work into task-ready intake after socratic-clarification has handled requests, bugs, pivots from ordinary Q&A, and other material uncertainty.
Use after implementation, after just-demand-tester output, when verification fails, when the user gives correction feedback, or before claiming a workflow task is done.
Use when a formal work item is ready to execute, when dispatching just-demand-researcher, just-demand-coder, just-demand-tester, or just-demand-advisor subagents, or when building context for focused execution.
| name | just-demand-memory |
| description | Use when recording durable preferences, decisions, deferred options, workspace facts, open questions, or when the user chooses a lightweight path over a more robust option. |
Persist durable knowledge without turning exploratory chat into permanent policy by accident.
When the user chooses a minimal or fast path, record the more robust option if it matters later:
## Deferred Option: <name>
Id: O001
Scope: workspace | task
Status: deferred
Chosen Instead: <chosen path>
Reason: <why not now>
Risk: <risk of deferring>
Source Task: <task-id or none>
Revisit When:
- <trigger>
When extracting durable knowledge from debugging or exploration, choose the right tier:
| Tier | Use when | Destination |
|---|---|---|
| Global reusable skill | Pattern applies across modules, projects, or repos; triggers capture-lessons conditions (>=3 attempts, architectural trap, reusable methodology) | .agents/skills/<pattern-name>/SKILL.md via capture-lessons |
| Workspace memory | Durable but project-local: this repo's conventions, scripts, architecture decisions, verified local facts | .just-demand/knowledge/memory.md |
| Task decisions | Task-only or one-off: not reusable beyond the current work item | Task decisions.md |
Do not promote a lesson to global skill tier unless it is clearly pattern-based and portable. When in doubt, keep it workspace-local.
When a task is about to leave the active set (archived or cleaned up), extract durable knowledge first:
decisions.md to workspace memory if they apply beyond the task.capture-lessons if they meet the global skill threshold.