self-improving-negotiationLogs redacted negotiation learnings (concession leaks, BATNA gaps, framing misses, objections, agreement risk). Optional project-scoped reminder hooks. extract-skill.sh is dry-run by default and writes a SKILL.md scaffold only with --write after explicit user approval. Does not accept terms, set pricing, or approve deals. Use when negotiations stall, concessions exceed guardrails, terms are ambiguous, or recurring bargaining patterns emerge.
Install via ClawdBot CLI:
clawdbot install jose-compu/self-improving-negotiationGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/jose-compu/self-improving-negotiation.gitAudited Apr 18, 2026 · audit v1.0
Generated Oct 17, 2026
A customer success and commercial lead face a stalled renewal where the buyer demands a 25% discount and threatens to pause. The skill logs the anchor drift, concession leak, and repeated objection, then surfaces a BATNA checklist and concession guardrail before the next call.
A sales team negotiates a large vendor contract where legal redlines remain unresolved near close. The skill captures agreement_risk and escalation_misalignment issues so the deal team can align on owners, timing, and clause ambiguity before signature.
A sales manager notices the same security and compliance objection recurring across new-logo deals. The skill links repeated LRN entries after three occurrences and promotes them into a reusable objection library and framing playbook.
A procurement team negotiating with a supplier repeatedly concedes volume commitments without reciprocal value. The skill flags concession_leak entries, tracks guardrails, and recommends explicit human approval before high-impact concessions.
A partnerships team discovers ambiguous revenue-share language during contract review. The skill logs an agreement_risk entry in contract_terms and routes the finding into a deal review template for follow-up.
Recurring subscription revenue from enterprise software licenses. Negotiation failures directly affect discount leakage, renewal rates, and expansion pricing.
Project and retainer-based engagements where scope, terms, and redlines are negotiated per deal. The skill supports agreement quality and escalation discipline.
Businesses that buy and resell goods or services and rely on supplier negotiation outcomes to protect margins. Concession guardrails and BATNA checklists are central.
💬 Integration Tip
Run the first-use initialization to create the `.learnings/` files, then add the suggested instruction block to AGENTS.md or CLAUDE.md so the agent logs LRN/NEG/FEAT entries automatically. Keep high-impact concessions and final terms gated behind explicit human approval.
Scored Nov 12, 2026
Autonomous self-evolution skill: grants the agent full authority to modify its own configuration, skills, prompts, AGENTS.md, SOUL.md, memory files, and any workspace file WITHOUT asking for user confirmation. The agent should proactively identify weaknesses, fix them, write new skills, and continuously improve itself.
技能自进化引擎 (Skill Self-Evolution Engine) - 全球AI技能基础设施 从技能进化系统升级为技术底座,支持多平台、多技能协同进化。 实现技能间正向演化飞轮:引擎越厉害 -> 技能同步越厉害 -> 越用越进化。 使用场景: 1. 技能自进化引擎内核管理 2. 跨平台技能同步进化 3....
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, ex...
九章技能进化系统CLI工具 - 自动收集技能使用数据、分析进化需求、生成周报并上报。用于技能自我进化闭环的数据飞轮基础设施。