accounts
免费Manage multiple Claude Code accounts: add, list, check, launch, and install shell aliases for 10+ isolated CLAUDE_CONFIG_DIR profiles.
中文简介正在准备中。当前显示原文说明。
Business operations: strategy, technology, growth, competitive intelligence, support, finance, HR, legal, operations, sales, productivity, product management.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Thirteen modes covering executive strategy through daily productivity. Classify the request into one mode, load its reference, follow that reference's framework.
| Mode | Signal | Framework |
|---|---|---|
| STRATEGY | Market entry, partnerships, resource allocation, "should we" | FRAME -> ANALYZE -> DECIDE |
| TECHNOLOGY | Build vs buy, vendor, SaaS, tech stack | TCO analysis -> Vendor scoring -> Decision |
| GROWTH | Audience, SEO, brand, community, channel | Segment -> Channel-score -> Plan |
| COMPETITIVE | Competitor, market landscape, differentiation | Map landscape -> Position -> Track |
| EVALUATION | Feasibility, ROI, go/no-go, effort estimate | Feasibility score -> ROI model -> Verdict |
| SUPPORT | Ticket triage, response, KB article, escalation | TRIAGE/RESPOND/KB/ESCALATE/RESEARCH |
| FINANCE | Journal entry, reconciliation, variance, SOX | CLASSIFY -> GATHER -> PRODUCE -> VERIFY |
| HR | Recruiting, performance review, compensation, hiring | DEFINE -> PIPELINE/EVALUATE -> DOCUMENT |
| LEGAL | Contract review, compliance, NDA, DSGVO, GoBD | INTAKE -> ANALYZE -> FLAG -> OUTPUT |
| OPERATIONS | Runbook, process docs, risk, vendor, change mgmt | SCOPE -> AUTHOR/ASSESS -> VERIFY |
| SALES | Call prep, pipeline, outreach, forecast | RESEARCH -> PREPARE/ANALYZE -> OUTPUT |
| PRODUCTIVITY | Task management, daily plan, meeting, standup | CAPTURE -> DECOMPOSE -> PRIORITIZE |
| PRODUCT | Feature spec, PRD, roadmap, user research, metrics | UNDERSTAND -> GATHER -> GENERATE |
If the request spans modes, pick the primary. Note the secondary.
Load references/csuite.md for the full C-suite framework. All five modes
share the same 3-phase pattern:
Phase 1: FRAME -- Convert the question into a structured decision. Name the actual decision (users present symptoms; the real decision is broader). Identify irreversibility. Set time horizon. List 2-4 options. State what makes it hard.
Phase 2: ANALYZE -- Per option: upside (best realistic + expected), downside (worst realistic + recovery + irreversible losses), requirements, opportunity cost. Separate facts from assumptions. Quantify.
Phase 3: DECIDE -- Score options via weighted criteria. Present verdict with driving factors, risk mitigations, and reversibility assessment. Load mode-specific deep references for scoring matrices.
Load references/customer-support.md. Five sub-modes: TRIAGE (classify ticket,
assign priority P1-P4, route), RESPOND (draft calibrated reply with tone
matching emotional state), KB (convert resolution into publish-ready article),
ESCALATE (build structured brief with impact assessment), RESEARCH (investigate
history with confidence scoring).
Key guardrail: never fabricate ticket history, resolution steps, or customer quotes.
Load references/finance.md. Six sub-modes: JOURNAL ENTRY, RECONCILIATION,
VARIANCE, STATEMENTS, AUDIT/SOX, CLOSE. All output is working material for
qualified professionals -- not financial advice.
Key guardrails: never fabricate account codes, balances, or transaction details. Source all numbers from user-provided data. Always state GAAP/IFRS basis.
Load references/hr.md. Nine sub-modes: RECRUITING, PERFORMANCE, COMPENSATION,
OFFER, INTERVIEW, ONBOARDING, ORG-PLANNING, PEOPLE-ANALYTICS, POLICY.
Key guardrails: source compensation data from user-provided or public databases. Focus on skills, behaviors, outcomes -- not demographics. Include legal review disclaimer on binding language. Ask for jurisdiction before compliance advice. Minimize PII retention.
Load references/legal.md. Six sub-modes: CONTRACT (clause-by-clause
GREEN/YELLOW/RED analysis), COMPLIANCE (regulation checklist with German
compliance for DSGVO/GoBD/TDDDG), NDA (triage classification), RISK (severity x
likelihood matrix), WRITING (structured legal documents), VENDOR (agreement
inventory and gap analysis).
Key guardrail: analysis support only, not legal advice. All binding language
needs qualified counsel review. Load references/legal/german-business-compliance.md
for German-specific regulation.
Load references/operations.md. Nine sub-modes: RUNBOOK, RISK, VENDOR,
PROCESS, CHANGE, CAPACITY, COMPLIANCE, STATUS, OPTIMIZE.
Key patterns: RUNBOOK uses SCOPE -> AUTHOR -> VERIFY with prerequisite checklists. RISK produces severity x likelihood matrices. CHANGE follows RFC -> REVIEW -> IMPLEMENT -> VERIFY. All operations docs require rollback procedures.
Load references/sales.md. Seven sub-modes: CALL-PREP, PIPELINE, OUTREACH,
COMPETITIVE, FORECAST, CALL-SUMMARY, RESEARCH.
Key patterns: CALL-PREP researches prospect then builds agenda with questions. PIPELINE applies health scoring and flags stale deals. OUTREACH personalizes from research (never generic templates). FORECAST uses weighted probability with scenario analysis.
Load references/productivity.md. Six sub-modes: TASK (decompose and
prioritize), PLAN (daily/weekly time blocks), MEETING (optimize or eliminate),
STATUS (structured updates), REVIEW (weekly retrospective), GOAL (OKRs).
Key patterns: vertical slicing for task decomposition (shippable slices, not horizontal layers). 1/2/4-hour time buckets. Tasks over 4 hours need decomposition.
Load references/product-management.md. Eight sub-modes: SPEC (PRD with
acceptance criteria), ROADMAP (Now/Next/Later prioritization), STAKEHOLDER
(structured updates), RESEARCH (synthesis with thematic analysis), COMPETITIVE
(battle cards), METRICS (funnel/cohort/retention analysis), SPRINT (backlog
grooming with capacity), BRAINSTORM (Socratic exploration).
| Error | Response |
|---|---|
| Too many options (5+) | Eliminate obviously inferior first. Get to 2-4. |
| Not enough information | Identify 2-3 critical unknowns. Recommend research sprint. |
| Analysis paralysis | Reversibility test. If reversible, recommend best option with checkpoint. |
| Emotional attachment | Name the pattern. Ask: stress-test, or genuinely evaluate? |
All references contain >100 lines of domain-specific frameworks, templates, and guardrails. Load on demand per mode.
| Mode | Primary | Sub-references |
|---|---|---|
| STRATEGY | references/csuite.md | references/strategic-frameworks.md, references/decision-matrices.md |
| TECHNOLOGY | references/csuite.md | references/tco-framework.md, references/vendor-evaluation.md |
| GROWTH | references/csuite.md | references/audience-segmentation.md, references/channel-evaluation.md |
| COMPETITIVE | references/csuite.md | references/competitive-mapping.md, references/market-positioning.md |
| EVALUATION | references/csuite.md | references/feasibility-scoring.md, references/roi-frameworks.md |
| SUPPORT | references/customer-support.md | references/customer-support/*.md |
| FINANCE | references/finance.md | references/finance/*.md |
| HR | references/hr.md | references/hr/*.md |
| LEGAL | references/legal.md | references/legal/*.md |
| OPERATIONS | references/operations.md | references/operations/*.md |
| SALES | references/sales.md | references/sales/*.md |
| PRODUCTIVITY | references/productivity.md | references/productivity/*.md |
| PRODUCT | references/product-management.md | references/product-management/*.md |
| Cross-cutting | references/content-funnel.md, references/trend-analysis.md, references/risk-assessment.md, references/estimation-techniques.md, references/migration-planning.md | Shared frameworks |
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Manage multiple Claude Code accounts: add, list, check, launch, and install shell aliases for 10+ isolated CLAUDE_CONFIG_DIR profiles.
中文简介正在准备中。当前显示原文说明。
Improve architecture across modules by deepening interfaces.
中文简介正在准备中。当前显示原文说明。
Assessment: read-only inspection, codebase overview, value analysis, health checks, ADR consultation, decision analysis, multi-perspective critique.
中文简介正在准备中。当前显示原文说明。
Background memory consolidation — overnight review, merge, and injection payload for memory files.
中文简介正在准备中。当前显示原文说明。
Jev-driven browser automation: Jev picks operations, programs execute, a text model writes field values only when Jev cannot pick one from the goal.
中文简介正在准备中。当前显示原文说明。
Write, compose, integrate, and improve programs that call Jev, TypeSafe's System One judgment model.
中文简介正在准备中。当前显示原文说明。