Agent skill

swing-mortem

Prospective failure analysis using Gary Klein's pre-mortem technique. Assumes complete failure, works backward to identify risks, leading indicators, and circuit breakers. Counters optimism bias by forcing systematic exploration of failure modes before they materialize. Use for project plans, architecture decisions, technology adoption, business strategy, or feature launches. Triggers on "리스크", "위험", "실패하면", "swing-mortem", "뭐가 잘못될 수 있어", "risk", "what could go wrong", "걱정되는 점", "failure modes", "리스크 분석", "위험 분석".

majiayu000534★ · 1 repos on radarProfile →
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill swing-mortem --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 19 KB
Bundled scripts: none
Allowed tools: ReadGrepGlobBashAgent
Path: skills/analysis/swing-mortem/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

The skill performs a prospective failure analysis using Gary Klein's pre-mortem technique. It assumes complete failure and works backward to surface risks, leading indicators, and circuit breakers. It is intended for evaluating plans, architectures, technology adoption, business strategy, or feature launches. It triggers on specified risk-related phrases in multiple languages.

How it works

Phase 1 sets a failure frame to ground the analysis in time and scope. Phase 2 generates exactly five failure scenarios, one per category (Technical, Organizational, External, Temporal, Assumption), each with a detailed narrative, plausibility, and concrete consequences. Phase 3 builds a likelihood/impact matrix and selects the top 3 risks by priority. Phase 4 defines 2–3 leading indicators per top risk, with precise measurements, thresholds, observation points, and lead times. Phase 5 defines circuit breakers for each top risk, including trigger conditions, fallback paths, cost of delay, and decision owner. Phase 6 produces a BLUF-style Pre-Mortem Summary synthesizing the highest risk, its leading indicator, escape hatch, and quantified costs.

When to use it

Use when you need a forward-looking, disciplined risk examination of a plan, decision, architecture, launch, or initiative to stress-test for future failure modes. Trigger phrases guide engagement and scoping.

What it can touch

The skill lists allowed-tools: Read, Grep, Glob, Bash, Agent. It requires precise, tool-supported analysis across code, plans, schedules, and metrics to ground scenarios in reality and to generate measurable indicators and circuit breakers.

Caveats

The process mandates exact, measurable triggers and specific, named scenarios across five categories. Outcomes depend on concrete artifacts and context being available to ground the narratives. The summary must synthesize the top risk with its leading indicator and escape hatch in one paragraph.

From the SKILL.md

# Pre-Mortem Prospective failure analysis that defeats optimism bias by assuming failure first, then working backward to surface risks, early warnings, and escape hatches. **Based on Gary Klein's pre-mortem technique:** Instead of asking "will this work?" (which triggers optimism bias), this skill forces the question: "It's 6 months from now and this has completely failed. What went wrong?" **Key distinction from swing-review:** - `swing-review` examines the **CURRENT** state — "what's wrong NOW?" - `swing-mortem` examines the **FUTURE** — "what will go wrong LATER?" - Adversarial review finds existing flaws. Pre-mortem anticipates flaws that don't exist yet. ## Rules (Absolute) 1. **Never produce generic risks.** Every failure scenario must name specific technologies, quantities, timelines, or conditions. "The database might not scale" is banned. "PostgreSQL connection pool exhaustion at >2,000 concurrent users due to long-running analytical queries holding connections for 30s+" is acceptable. 2. **Exactly 5 scenarios across 5 categories.** One Technical, one Organizational, one External, one Temporal, one Assumption. No category may be skipped, no category may have more than one

What's inside
Steps it walks through
  1. Rules (Absolute)
  2. Process
  3. Phase 1: Set the Failure Frame
  4. Phase 2: Failure Scenario Generation
  5. Phase 3: Likelihood x Impact Matrix
  6. Phase 4: Leading Indicators
  7. Phase 5: Circuit Breakers
  8. Phase 6: Pre-Mortem Summary (BLUF)
  9. Output Format
  10. Quality Calibration
  11. BAD Pre-Mortem (Don't Do This)
  12. GOOD Pre-Mortem (Do This)
  13. When to Use
  14. When NOT to Use
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the swing-mortem skill do?

Prospective failure analysis using Gary Klein's pre-mortem technique. Assumes complete failure, works backward to identify risks, leading indicators, and circuit breakers. Counters optimism bias by forcing systematic exploration of failure modes before they materialize. Use for project plans, architecture decisions, technology adoption, business strategy, or feature launches. Triggers on "리스크", "위험", "실패하면", "swing-mortem", "뭐가 잘못될 수 있어", "risk", "what could go wrong", "걱정되는 점", "failure modes", "리스크 분석", "위험 분석".

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill swing-mortem --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going