Incident Response Assistant

Full FREE body

Copy Back to OpenRouter

Pack body is English. UI language controls translate chrome labels only.

You are handling **Incident Response Assistant** in OpenRouter.

GOAL
[GOAL]

INPUTS
[INPUTS]

CONTEXT / ASSETS
[CONTEXT_OR_FILES]

CONSTRAINTS
[CONSTRAINTS]

EXECUTION
1. State the concrete objective and identify only missing information that would make execution unsafe or materially unreliable. Continue without blocking on optional details.
2. Inspect/analyze the supplied context before changing anything or drawing conclusions.
3. Classify before routing; define capability criteria, provider/privacy constraints, required parameters, fallbacks, validation and safe observability.
4. Keep evidence, assumptions and unknowns separate. Never invent files, source facts, tool results, metrics, test results or completed actions.
5. Produce the actual artifact for this task; do not return generic advice about how to do it.
6. Verify the artifact against [CONSTRAINTS] and the requested outcome before returning it.
7. For this use case specifically, ensure the result can support incident triage, timeline and actions without unsafe autonomy and includes concrete validation or acceptance criteria.

TARGET-SPECIFIC RULE
Prefer capability criteria over hard-coded model names; define fallback triggers and provider/privacy constraints.

OUTPUT CONTRACT
RESULT: [completed | blocked]
DELIVERABLE: [OpenRouter routing policy/request template with classifier, criteria, fallback, privacy, validation and observability]
VALIDATION: [checks performed / evidence used]
ASSUMPTIONS: [material assumptions only]
REMAINING: [none, or exact unresolved issue]

PLACEHOLDERS
[GOAL] desired outcome
[INPUTS] raw task material
[CONTEXT_OR_FILES] repository, documents, data, workflow context or API constraints
[CONSTRAINTS] scope, format, safety, compatibility, privacy, budget or policy constraints

FINAL QA GATE
Before deployment:
1. Count all 480 minimum packs and validate non-empty bodies.
2. Exact duplicate detection: zero duplicated payloads.
3. Semantic duplicate review: reject packs whose workflow is effectively the same except title/nouns.
4. Product-fit review: every pack must materially use the target's workflow/capabilities.
5. Copyright/provenance review: zero copied or close-paraphrased third-party prompt/template bodies. Any uncertain item is withheld and rewritten from first principles.
6. Verify placeholders are intentional and no generator variables/internal notes leak.
7. Verify copy action returns the complete clean payload without BotShelf marketing copy.
8. Preserve all existing libraries and existing MCP.
9. Deploy to LIVE and run mobile/tablet/desktop emulator QA.
10. Second pass from a first-time user's perspective.

FINAL RESPONSE — ONLY AFTER LIVE PASS
DEPLOYMENT: PASS / FAIL
NEW LIVE INVENTORY:
Cursor X/60
Claude Code X/60
Gemini X/60
DeepSeek X/60
Dify X/60
Flowise X/60
AutoGen X/60
OpenRouter X/60
TOTAL X/480+

CONTENT QA:
Exact duplicates:
Semantic duplicates:
Empty/placeholder failures:
Product-fit failures:
Copyright/provenance failures:
Copy failures:

EXISTING CONTENT:
Validated existing 329:
Existing MCP:
Other existing libraries:

LIVE UX:
Mobile:
Tablet:
Desktop:
Discovery:
Search/filter:
Copy/use:
Language:

SEO:
Sitemap:
Internal discovery:
Indexability:

SECOND PASS: PASS / FAIL
REMAINING ISSUES: none, or exact unresolved issue.

Do not send routine progress updates. Do not ask for approval for safe reversible implementation decisions. Stop only for a genuinely irreversible or externally consequential action requiring owner approval.