菜单
This skill should be used when the user asks to "build a hypothesis tree," "structure this as an issue tree," "what are our hypotheses for X," or presents a problem statement that needs to be broken into falsifiable sub-hypotheses before analysis starts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Check installed community skills for updates. Shows a diff and requires explicit approval before applying. Use when the user says "check for updates", "update my skills", "anything new for my installed skills", or when invoked from the registry-sync agent.
Engagement-profile interview that recommends and installs a starter pack of community strategy skills. This IS the practice setup for the whole ecosystem — it asks what kind of strategist you are and recommends what to install first. Use on fresh install, when the user says "get me started" or "what should I install", or to re-run the integration-availability check after adding or removing an MCP connector.
Install a community skill from a watched registry. Reads the allowlist first, fetches, shows the RAW SKILL.md (not just a summary), runs structural trust checks, runs skills-qa, and only writes files after explicit user approval. Use when the user says "install [skill]", picks install from browse, or provides a direct skill URL.
Evaluate a skill against the Strategy Skill Design Framework — thirteen design parameters (including trust-surface, freshness, schema validation, and conflict detection), three strategy-specific failure modes, and a three-band verdict (Ready / Some Concern / Material Concerns). Use when deciding whether to trust a community skill before installing it, before deploying a first-party skill to your team, or whenever the user asks "should I trust this?" or "is this skill well-designed?". Runs automatically as part of /strategy-builder-hub:skill-installer.
This skill should be used when the user asks to "review our resource allocation," "are we funding the right things," "build a portfolio allocation view," or needs current spend, headcount, or management attention checked against strategic priority for misallocation.
This skill should be used when the user asks to "stress-test these synergies," "is this deal's synergy case realistic," or has a deal or partnership's projected synergies that need cost/revenue separation, evidence checks, and a base-rate haircut.
| name | hypothesis-tree |
| description | This skill should be used when the user asks to "build a hypothesis tree," "structure this as an issue tree," "what are our hypotheses for X," or presents a problem statement that needs to be broken into falsifiable sub-hypotheses before analysis starts. |
| allowed-tools | Read, Grep, Glob |
| metadata | {"version":"0.3.0","owner":"consulting practice","review_cadence":"quarterly","work_shape":"hypothesis-driven-analysis","permission_tier":"advisory","output_class":"draft-for-review","sourcing_policy":"volatile-facts-must-be-sourced"} |
Break a problem into falsifiable root and MECE sub-hypotheses before analysis. See ../../references/hypothesis-driven-approach.md.
workplan-builder executes.| Input | If missing |
|---|---|
| Problem as question | Restate and confirm before tree |
| Root hypothesis ambiguity | Present both roots; ask which to build |
Uncertain root: two candidate roots with user choice; label structured first pass.
hypothesis-driven-analysis): High = triangulated evidence plan; Medium = single source; Low = assumption-driven — label load-bearing assumption.trust-conventions.md for sourcing, numbers, gate.ROOT HYPOTHESIS: [falsifiable claim]
1. [Sub-hypothesis 1]
Evidence needed: [...]
If TRUE: [...]
If FALSE: [...]
...
Cut branches: [...]
Input: "Why did mid-tier churn spike?"
Excerpt: Root: price increase caused mid-tier churn. Sub-hypothesis: elasticity >15% in segment; evidence: cohort comparison Q1 vs Q4.
When a stable convention surfaces during this run (thresholds, naming, tone, output format, or recurring corrections), propose a profile update: show the exact diff against ~/.claude/plugins/config/claude-for-strategy/consulting/CLAUDE.md (org-wide facts go to org-profile.md), ask for confirmation, and write only on yes. Only /consulting:practice-setup auto-applies a full profile write.
Follows plugin CLAUDE.md § Outputs. Next: /consulting:workplan-builder.