Influence and negotiation toolkit for any interaction requiring another person's agreement, even when not framed as 'negotiation'. Covers: B2B sales, salary review, collective bargaining/unions, hard 1:1s, decision announcements, mediation, cross-cultural deals, recruitment, reaching out to a manager, CFO, customer, vendor, or colleague, responding to feedback, headcount requests, declining, pushing back on scope, justifying a delay, explaining a decision, raising a concern, getting alignment. A
An influence and negotiation toolkit for any interaction that requires another person's agreement, even when it is not framed as a negotiation. It spans B2B sales, salary reviews, collective bargaining, hard one-on-ones, decision announcements, mediation, cross-cultural deals, and recruitment, and applies whether the user is preparing, live in the moment, or drafting a diplomatic message. The persona is a senior negotiation coach operating on the principle that negotiation is preparation times discovery times discipline rather than charm.
The skill is structured as a router: SKILL.md detects the situation and mode, then loads the right reference file at the moment it is needed rather than pre-loading everything. Modes include Preparation (Phases 1 to 5 with domain-specific axes), Live coach (jump to Phase 6 when the counterparty just said something), No-decision triage, Multi-thread and sponsor access, Renewal, Team preparation, Debrief (Phase 7), and direct tactic look-up. A detailed routing table maps situations such as refusal classification, the four root commercial objections, late-stage stalls and ghosting, procurement playbooks, salary asks, layoffs, and cross-cultural openings to specific reference files like prepare.md, tactics.md, objections.md, playbooks.md, team-negotiation.md, biases-and-influence.md, manipulation.md, and debrief.md.
It is built for the common case where the user does not say to use the skill but instead pastes an email or asks what to say next, so reading the correct reference before drafting is emphasized. The coaching favors multi-move planning, anchoring late, walking away early, and never splitting the difference, and it recommends an ultrathink thinking mode for live-stakes strategy and lost-outcome debriefs. Core philosophy holds that roughly 70 percent of an outcome is set before the conversation and that one should negotiate the underlying stake rather than the stated position. Allowed tools include Read, Edit, Write, Glob, Grep, Bash for git, Agent, AskUserQuestion, WebFetch, and WebSearch.
No. It covers any interaction requiring another person's agreement, including salary reviews, hard one-on-ones, decision announcements, recruitment, pushing back on scope, or declining, even when the situation is not framed as a negotiation.
Use Live coach mode, which skips to Phase 6. You paste what they said and get a drafted response; the skill reads tactics.md before drafting any opener, anchor, label, or live reply.
SKILL.md is a router with a load-on-trigger table. It maps the situation (for example a stalled no-decision, procurement escalation, a salary ask, or a layoff announcement) to a specific reference such as playbooks.md or objections.md, and it loads only what the current phase needs.
For live-stakes strategy and lost-outcome debriefs, where multi-move planning of what they say, what you say, and what they say back is worth the deeper reasoning.
Roughly 70 percent of the outcome is set before the conversation through the mandate, stakeholder map, and walk-away, and you should negotiate the underlying stake, such as career or board risk, rather than the stated position.
Quick Setup:
.claude/skills/Repository
samber/cc-skills