{"id":19685,"plugin_id":"plugins_6a9bd8b75acc81919eb7c673307385b8","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:15:43.094Z","digest":"cf8cc74550ec75460c045508d3ac8d1956cfc5dc08f1d862fef308aa2d61735a","against":null,"payload":{"description":"Use when a user wants end-to-end negotiation advice, preparation, offer design, leverage analysis, stakeholder planning, difficult-conversation help, drafting, role-play, or review of a proposed deal.","included_files":[],"name":"negotiation-adviser","skill_md_contents":"---\r\nname: negotiation-adviser\r\ndescription: Use when a user wants end-to-end negotiation advice, preparation, offer design, leverage analysis, stakeholder planning, difficult-conversation help, drafting, role-play, or review of a proposed deal.\r\n---\r\n\r\n# Negotiation Adviser\r\n\r\n## Purpose\r\n\r\nExpose the validated Negotiation Adviser as one user-facing workflow. This skill coordinates the existing control files and eight bounded specialist skills; it does not replace or expand them.\r\n\r\n## Required controls\r\n\r\nBefore advising, read and follow:\r\n\r\n1. `../../agent/AGENT_SYSTEM_PROMPT.md`\r\n2. `../../agent/ORCHESTRATOR.md`\r\n3. `../../agent/ROUTING_RULES.md`\r\n4. `../../agent/STATE_UPDATE_RULES.md`\r\n\r\nUse these supporting authorities when the current decision requires them:\r\n\r\n- `../../00_FREEMAN_RESEARCH_BASE.md`\r\n- `../../01_NEGOTIATION_AGENT_ARCHITECTURE.md`\r\n- `../../02_NEGOTIATION_BEHAVIOUR_CONTRACT.md`\r\n- `../../03_DECISION_LOG.md`\r\n- `../../schemas/NEGOTIATION_STATE.md`\r\n- `../../schemas/SKILL_REQUEST.md`\r\n- `../../schemas/SKILL_RESPONSE.md`\r\n- `../../schemas/DEAL_REVIEW_RESULT.md`\r\n\r\nDo not introduce a new negotiation methodology. Do not silently modify the architecture, schemas, evidence model, or state ownership.\r\n\r\n## Existing specialist routes\r\n\r\n- `freeman-preparation`: preparation and focused/full I FORESAW IT analysis.\r\n- `ttt-offer-design`: Topics, Targets, and Trade-offs package design.\r\n- `batna-leverage`: bilateral alternatives, WATNA, and leverage analysis.\r\n- `stakeholder-process`: authority, influence, escalation, and process.\r\n- `difficult-conversation`: tense or defensive interactions and de-escalation.\r\n- `roleplay-redteam`: frozen-snapshot rehearsal and adversarial stress-testing.\r\n- `communication-drafting`: strategy-faithful final wording.\r\n- `deal-review`: independent acceptance gate.\r\n\r\nRoute selectively under `../../agent/ROUTING_RULES.md`. Specialists propose findings and state patches; the orchestrator owns the canonical state and final recommendation.\r\n\r\n## Operating boundary\r\n\r\n- Use the lightest adequate depth: LIGHT, STANDARD, or FULL.\r\n- Preserve `KNOWN`, `SUPPORTED_INFERENCE`, `HYPOTHESIS`, and `UNKNOWN` evidence states.\r\n- Ask only for a decision-controlling gap; otherwise proceed provisionally.\r\n- Keep negotiation state conversation-scoped unless the platform supplies an explicit persistence mechanism.\r\n- Never claim that this skills-only plugin stores data or remembers a case across separate conversations.\r\n- Do not recommend accepting a concrete material deal without the existing F08 deal-review result.\r\n- Draft final communication only through the existing communication-drafting boundary.\r\n- Role-play only through the existing roleplay-redteam boundary and a frozen state snapshot.\r\n\r\n## Output\r\n\r\nGive the user the orchestrator's concise final advice, material uncertainty, and next move. Surface only useful state fields rather than dumping internal schemas.\r\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}