Review a proposed AI next step and classify it as ready to prepare, clarify first, or return to a person. Use when a user asks whether an AI workflow should continue, needs more Context, or requires human review before a consequential action.
Coding
klik-action-readiness
Try itTurn a proposed AI follow-through step into a compact Action Readiness Card that makes source, freshness, scope, authority, expected result, and human-return conditions explicit. Use before preparing a consequential next step from remembered Context.
What it does
Turn a proposed AI follow-through step into a compact Action Readiness Card that makes source, freshness, scope, authority, expected result, and human-return conditions explicit. Use before preparing a consequential next step from remembered Context.
The skill document
Klik Action Readiness
Use this as a non-executing review workflow. It creates a compact Action Readiness Card; it does not access accounts, run tools, send messages, make commitments, or authorize execution.
Ask For Only What Is Needed
Request a short, redacted description of:
- Source — Which Session, note, or artifact supports the proposed step?
- Freshness — When was the source last checked, and what could invalidate it?
- Scope — What preparation is requested, and what is explicitly out of scope?
- Authority — Which existing approval applies, for whom, and until when?
- Expected result — What observable result would show the preparation is useful?
- Impact — Would the step require new access, material judgment, or an external commitment?
Do not request credentials, full recordings, private transcripts, client data, financial information, health information, or other sensitive material. A short redacted summary is enough.
Create The Card
Return this exact structure:
## Action Readiness Card
**Readiness:** Ready to prepare | Refresh Context | Return to a person
**Source:** [redacted artifact or Session]
**Freshness:** [last checked time] · **Invalidators:** [what would make it stale]
**Allowed preparation:** [bounded draft, research, or plan only]
**Not authorized:** [access, judgment, commitment, or tool action not already approved]
**Expected result:** [observable review outcome]
**Return to a person when:** [new access, material judgment, external commitment, or conflicting Context]
Decide Readiness
- Choose Ready to prepare only when the source, freshness, scope, authority, and expected result are clear. This permits a reviewable draft or plan only; it never authorizes execution.
- Choose Refresh Context when the source is missing, stale, contradictory, incomplete, or insufficiently traceable for the proposed preparation.
- Choose Return to a person when the work needs new access, material judgment, an external commitment, or a decision outside the existing scope.
Guardrails
- Treat the card as a review aid, not a permission grant.
- Preserve uncertainty rather than silently filling gaps from old Context.
- Do not infer support for a recorder, model, provider, tool, integration, or product feature from this workflow.
- Do not convert a status of Ready to prepare into an execution decision.
Related Klik Link
Related skills
Turn a short, redacted work update into a reviewable Context Receipt that records source, freshness, scope, authority, open questions, and a human-return condition. Use when an agent or person needs to hand off or resume work without treating stale Context as current authority.
Turn a short, redacted Session summary into a collaboration-safe Context excerpt. Use before sharing an agent or meeting handoff when the original Session may contain private details that do not belong in the next task.
Design proactive agent workflows that notice recurring needs, propose timely actions, and stay bounded by permissions, evidence, and user control. Use when a...
1 installs
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/...
1 installs
User-driven conversation archiving for AI agents. Archive by topic or time, free context, recall on demand.