memo-stress-tester
Use when evaluating business documents for structural integrity and persuasive logic.
Best use case
memo-stress-tester is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when evaluating business documents for structural integrity and persuasive logic.
Teams using memo-stress-tester should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/memo-stress-tester/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How memo-stress-tester Compares
| Feature / Agent | memo-stress-tester | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when evaluating business documents for structural integrity and persuasive logic.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
## Overview Memo stress-testing is the rigorous evaluation of a business document's "readiness" for executive decision-making. It identifies logical gaps, unproven assertions, and "half-baked" ideas. By applying the Amazon narrative standard, Minto's pyramid logic, and the doctrine of Completed Staff Work, it ensures that a document is a self-contained tool for strategic action rather than a draft for the boss to finish. ## Guiding Principles ### Principle 1: Completed Staff Work (Source: Web, Completed Staff Work Doctrine) Study, write, restudy, and rewrite until you have evolved a single proposed action. The "Chief" should only need to approve or disapprove. If the superior has to do more research or thinking, the staff work is incomplete. ### Principle 2: The Self-Contained Narrative (Source: Bryar, Working Backwards) A memo must stand on its own without a supporting presentation. It should be a narrative that forces better thinking and allows for deep, silent reading. If the document relies on "hallway context" or a presenter's explanation, it fails the stress test. ### Principle 3: MECE Validation (Source: Minto, The Pyramid Principle) Every group of supporting points must be **Mutually Exclusive** (no overlaps) and **Collectively Exhaustive** (no gaps). If points in a list overlap, the logic is "fuzzy." If a key driver is missing, the document is fragile. ### Principle 4: Contribution over Effort (Source: Drucker, The Effective Executive) The memo must focus on the *results* and *contribution* to the organization, not the effort centers (costs/internal processes). An effective memo identifies what needs to be *done* to move the needle on the outside environment. ### Principle 5: The "Answer First" Order (Source: Minto, The Pyramid Principle) Never build a "logical crescendo" where the recommendation is at the end. State the conclusion first, then support it. Executives are paid to make decisions; don't make them wait for page 6 to see what they are deciding. ## When to Use This Skill - Before submitting a proposal to senior leadership. - Reviewing a peer's PRD or strategic brief. - Auditing a document after a meeting resulted in "no decision" or "more research needed." - Compressing a long report into a "one-pager." ## When NOT to Use This Skill - Brainstorming/Ideation phases where logic is still fluid. - Informal updates or status reports that don't require a decision. ## Core Process ### Step 1: The "Completed Staff Work" Audit (Source: Web) Ask: "If I presented this to the CEO today, could they say 'Yes' or 'No' and be done with it?" - If the answer is "We need to look into X," the memo fails. - Identify every "To-Do" that the memo implicitly leaves for the reader. ### Step 2: The SCQ Logic Check (Source: Minto, The Pyramid Principle) Validate the structural arc: 1. **Situation:** Is the context universally agreed upon? 2. **Complication:** Is the "trigger" for the document clear? 3. **Question:** Does the document answer the *actual* question raised by the complication? ### Step 3: The MECE Stress Test (Source: Minto, The Pyramid Principle) Look at every bulleted list or set of supporting points: - **Overlap check:** Is Point A actually a subset of Point B? - **Gap check:** Is there a "missing middle" that invalidates the conclusion? - **Consistency check:** Are all points in the group of the same "kind"? ### Step 4: The Amazon "Narrative" Pass (Source: Bryar, Working Backwards) Replace "PowerPoint logic" (fragments/lists) with narrative prose. - Does the document follow a causal sequence? - Are the metrics "input-based" (controllable) rather than just "output-based" (revenue/growth)? - Does it anticipate and answer the 5-10 most likely "Frequently Asked Questions"? ### Step 5: The Drucker "Contribution" Filter (Source: Drucker, The Effective Executive) Review the "Ask": - Does it focus on the organization's performance in the *outside* environment? - Does it explicitly state the trade-offs (what we will *not* do)? ## Frameworks & Models ### Amazon 6-Pager Structure (Source: Bryar, Working Backwards) 1. **Introduction:** Purpose and scope. 2. **Goals/Inputs:** What we are trying to achieve and the controllable inputs. 3. **Tenets:** The guiding principles for the decision. 4. **State of the Business:** Data and current context. 5. **Lessons Learned:** What we've discovered so far. 6. **Strategic Recommendation:** The "Completed Staff Work" action. ### The "Dissent" Rule (Source: Drucker, The Effective Executive) A memo is stress-tested when it includes the strongest possible counter-argument. If the document shows "total consensus" without acknowledging the risks or alternatives, the decision is likely to be a "resulting" error. ## Cross-Skill Invocations REQUIRED SUB-SKILL: **non-fiction-precision** — to ensure the prose is clear enough to be tested. RECOMMENDED SUB-SKILL: **assumption-audit** — to validate the data behind the logic. ## Common Mistakes 1. **The "Wait for It" Recommendation:** Burying the lead at the end of the document. (Source: Minto) 2. **The "Check-In" Memo:** Asking the boss "What do you think?" instead of "I recommend X because Y." (Source: Web, Completed Staff Work) 3. **Indiscriminate Detail:** Including a thousand details that *don't* add up to one impression. (Source: McPhee/Drucker) ## Diagnostic Checklist - [ ] Is there a specific, actionable recommendation? - [ ] Does the memo answer "Why now?" and "Why us?" - [ ] Are all supporting points MECE (Mutually Exclusive, Collectively Exhaustive)? - [ ] Is the document self-contained (no presentation required)? - [ ] Has the strongest counter-argument been addressed? ## Sources - Minto, Barbara. *The Pyramid Principle*. Ch. 1-3 (Logic and Structure). - Drucker, Peter. *The Effective Executive*. Ch. 3 (Contribution), Ch. 7 (Effective Decisions). - Bryar, Colin. *Working Backwards*. Ch. 5 (Narratives/6-Pagers). - Wikipedia. "Completed Staff Work".
Related Skills
qa-tester
QA Tester Agent. 테스트 작성, 실행, 검증을 담당합니다. 테스트, 검증, 단위테스트, 통합테스트, E2E 관련 요청 시 사용됩니다.
playwright-e2e-tester
Expert in end-to-end testing with Playwright, the modern cross-browser testing framework. Specializes in test generation, page object patterns, visual regression testing, and CI/CD integration. Handles complex testing scenarios including authentication flows, API mocking, and mobile emulation.
openclaw-memory
Production-grade memory management for OpenClaw. Search, compress, encrypt, authenticate, rate limit, and audit OpenClaw memory (MEMORY.md, AGENTS.md, memory/) with enterprise-grade security.
memory-leak-audit
Audit code for memory leaks and disposable issues. Use when reviewing event listeners, DOM handlers, lifecycle callbacks, or fixing leak reports. Covers addDisposableListener, Event.once, MutableDisposable, DisposableStore, and onWillDispose patterns.
core-tester
Comprehensive testing and quality assurance specialist for ensuring code quality through testing strategies
agent-penetration-tester
Expert penetration tester specializing in ethical hacking, vulnerability assessment, and security testing. Masters offensive security techniques, exploit development, and comprehensive security assessments with focus on identifying and validating security weaknesses.
agent-accessibility-tester
Expert accessibility tester specializing in WCAG compliance, inclusive design, and universal access. Masters screen reader compatibility, keyboard navigation, and assistive technology integration with focus on creating barrier-free digital experiences.
accessibility-tester
Expert accessibility tester specializing in WCAG compliance, inclusive design, and universal access. Masters screen reader compatibility, keyboard navigation, and assistive technology integration with focus on creating barrier-free digital experiences.
acceptance-tester
Execute systematic acceptance testing to verify implementations against acceptance criteria. Use this skill when tasks mention "驗收測試", "acceptance testing", "驗收", "validate implementation", or when Gherkin scenarios need to be executed.
u0538-engineering-memory-consolidation-pipeline
Operate the "Engineering Memory Consolidation Pipeline" capability in production for workflows. Use when mission execution explicitly requires this capability and outcomes must be reproducible, policy-gated, and handoff-ready.
activating-memories
Loads project-specific memories at session start and triggers onboarding for new projects. Use when starting a new coding session or when the user says "activate" or asks about project context.
vps-memory
Access Flo's long-term memory on the VPS (OpenClaw). ALWAYS use when the user says "memory", "memories", "remember", "souviens-toi", "rappelle-toi", "save memory", "search memory", "VPS memory", "OpenClaw", or mentions saving/searching past sessions or knowledge.