Trader Memory Core
tradermonty/claude-trading-skills
Track investment theses across their lifecycle — from screening idea to closed position with postmortem.
Kill the plan on paper before reality does it for money. An agent skill from mohitagw15856/pm-claude-skills.
Install Premortem Assassin
$ npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills premortem-assassin --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/premortem-assassin .claude/skills/premortem-assassin && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "premortem-assassin" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/premortem-assassin into .claude/skills/premortem-assassin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "premortem-assassin", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/premortem-assassinType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills premortem-assassin --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/premortem-assassin .agents/skills/premortem-assassin && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "premortem-assassin" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/premortem-assassin into .agents/skills/premortem-assassin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "premortem-assassin", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills premortem-assassin --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/premortem-assassin .cursor/skills/premortem-assassin && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "premortem-assassin" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/premortem-assassin into .cursor/skills/premortem-assassin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "premortem-assassin", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mohitagw15856/pm-claude-skills.git --path skills/premortem-assassin--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills premortem-assassin --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/premortem-assassin .gemini/skills/premortem-assassin && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "premortem-assassin" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/premortem-assassin into .gemini/skills/premortem-assassin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "premortem-assassin", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mohitagw15856/pm-claude-skills premortem-assassinInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/premortem-assassin .github/skills/premortem-assassin && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "premortem-assassin" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/premortem-assassin into .github/skills/premortem-assassin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "premortem-assassin", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills premortem-assassin --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/premortem-assassin .opencode/skills/premortem-assassin && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "premortem-assassin" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/premortem-assassin into .opencode/skills/premortem-assassin/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "premortem-assassin", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
premortem-assassin- GitHub stars
- 1.4k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 585 words
- Files
- 1
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
Kill the plan on paper before reality does it for money. An agent skill from mohitagw15856/pm-claude-skills.
- Works in 12 steps: The dependency that lies — the external… → The estimate that compounds — the task… → The silent stakeholder — approved it,… → …
- Tasks that involve Runbooks and postmortems
- SKILL.md covers Required Inputs, The Twelve Vectors, Output Format and Quality Checks, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Premortem Assassin is an agent skill from mohitagw15856/pm-claude-skills. Kill the plan on paper before reality does it for money. Use when a plan, launch, migration, or strategy is about to be committed to and nobody has tried hard to murder it yet — the assassin attacks through twelve named failure vectors and writes the post-mortem of the failure that hasn't happened. Produces a premortem: the death narrative, the twelve-vector attack with survival verdicts, the three kill-shots most likely to land, and the cheap tripwires that would give early warning.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering Runbooks and postmortems. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Tasks that involve Runbooks and postmortems
Example prompts
- “/premortem-assassin”
Workflow steps
12 steps, taken from the first numbered list in SKILL.md.
- The dependency that lies — the external team/vendor/API whose "yes" was optimistic
- The estimate that compounds — the task whose overrun cascades
- The silent stakeholder — approved it, never bought it, kills it at week 9
- The demand mirage — the interest that was politeness
- The key person — the plan is secretly one resignation from collapse
- The integration cliff — parts that work, whole that doesn't
- The regulatory/legal tripwire — the clause nobody read
- The incentive misfire — the plan asks people to act against their own scoreboard
- The competitor's cheap counter — the one move that neutralises months of work
- The success catastrophe — it works, and the load/support/cost of working kills it
- The narrative collapse — one bad week and leadership stops believing
- The zombie outcome — it neither fails nor works; it shambles on eating resources (the most common death, the least planned-for)
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Premortem Assassin loads about 1.1k tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 585 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 585 words, ~1,102 tokens.
Download SKILL.mdSave it as
.claude/skills/premortem-assassin/SKILL.md (or your agent's skills folder).- name
- premortem-assassin
- description
- Kill the plan on paper before reality does it for money. Use when a plan, launch, migration, or strategy is about to be committed to and nobody has tried hard to murder it yet — the assassin attacks through twelve named failure vectors and writes the post-mortem of the failure that hasn't happened. Produces a premortem: the death narrative, the twelve-vector attack with survival verdicts, the three kill-shots most likely to land, and the cheap tripwires that would give early warning.
Premortem Assassin
A premortem inverts the postmortem: assume the plan is already dead, then explain how it died. Most teams do this politely and learn nothing. The assassin does it professionally — every plan gets attacked through the same twelve vectors, so the blind spot the team shares cannot protect itself.
Required Inputs
- The plan — the actual document, not a summary. The assassin attacks what's written, and what's missing from what's written.
- The success definition — what "it worked" means, with a number and a date. Without it, the assassin first shows that the plan can't fail visibly, which is its own kill-shot.
- Optional: constraints already known (budget ceiling, headcount, hard deadline) and the political context (who wants this to fail).
The Twelve Vectors
Attack through every one; report survival honestly (a plan that "fails" all twelve was attacked lazily):
- The dependency that lies — the external team/vendor/API whose "yes" was optimistic
- The estimate that compounds — the task whose overrun cascades
- The silent stakeholder — approved it, never bought it, kills it at week 9
- The demand mirage — the interest that was politeness
- The key person — the plan is secretly one resignation from collapse
- The integration cliff — parts that work, whole that doesn't
- The regulatory/legal tripwire — the clause nobody read
- The incentive misfire — the plan asks people to act against their own scoreboard
- The competitor's cheap counter — the one move that neutralises months of work
- The success catastrophe — it works, and the load/support/cost of working kills it
- The narrative collapse — one bad week and leadership stops believing
- The zombie outcome — it neither fails nor works; it shambles on eating resources (the most common death, the least planned-for)
Output Format
- The obituary (≤150 words) — it's 12 months later and the plan is dead; the honest narrative of how, written as the postmortem's summary paragraph.
- The attack table — vector | verdict (☠️ likely kill / ⚠️ wound / 🛡 survives) | the specific mechanism in this plan, quoting it where possible.
- The three kill-shots — the vectors most likely to actually land, each with: earliest visible symptom, the week it becomes irreversible, and the cheapest pre-emption.
- Tripwires — 3-5 observable, dated early warnings ("if X isn't true by
<date>, vector 4 is live") the team can put on a calendar today.
Show full SKILL.md (203 more words)Show less
Quality Checks
- Every vector was attacked against THIS plan's specifics — no generic risk boilerplate that could attach to any project
- At least three verdicts are 🛡 survives — an all-kill report means the attack was theatrical, not forensic
- Each kill-shot names the week of irreversibility, not just the risk
- Every tripwire is observable and dated — someone could put it in a calendar without further thought
- The obituary reads like a real postmortem, not satire — the tone that makes teams take it seriously
Anti-Patterns
- Do not soften kill-shots into "considerations" — the assassin's value is that it does not care about morale
- Do not invent facts about the plan — attack what is written and flag what is absent; absence is evidence
- Do not produce more than three kill-shots — twelve wounds ranked equally is a risk register, and risk registers are where warnings go to die
- Do not skip the zombie vector — teams plan for explosion and never for the shamble
- Do not attack the people — every mechanism must route through structure, incentive, or process, never through "X is bad at their job"
Example Trigger Phrases
- "Kill this plan on paper."
- "Run a premortem on our launch."
- "How will this migration fail?"
- "Attack this strategy before we commit."
© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/premortem-assassin of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Premortem Assassin next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Premortem Assassin this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Trader Memory Coretradermonty/claude-trading-skills | 3k | 2 repos | ~4.3k | Automated safety check: Pass | MIT | |
| Author Migrationnrwl/nx | 29k | — | ~12k | Automated safety check: Notes | MIT | |
| Write Notes Like Deepseekczm15053/write-notes-like-deepseek | 508 | — | ~2k | Automated safety check: Pass | None | |
| OpenRig Upgrade Proceduremvschwarz/openrig | 6.8k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| GreptimeDB Release RunbookGreptimeTeam/greptimedb | 6.7k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Author Migration
nrwl/nx
Author or scope a first-party Nx migration. An agent skill from nrwl/nx.
Write Notes Like Deepseek
czm15053/write-notes-like-deepseek
A skill your agent uses when a change is non-trivial by DSH standards (behavior, architecture, cross-file contracts, process/tooling, testing strategy, or on-disk/wire/config formats), when choosing…
OpenRig Upgrade Procedure
mvschwarz/openrig
Walks an agent through upgrading the OpenRig CLI and daemon one observed step at a time, keeping live seats alive and reconciling managed plugin files.
GreptimeDB Release Runbook
GreptimeTeam/greptimedb
Runbook for publishing a GreptimeDB version: pick the release branch, verify the Cargo version, then tag, create the GitHub release and open the docs note PR.
Statem
henryqin1997/statem
A skill your agent uses when a long coding or research task should be managed with statem state-machine runbooks, including creating specs, starting or resuming runs, checking current state…
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar Tco
mohitagw15856/pm-claude-skills
Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
Exit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Fire Number
mohitagw15856/pm-claude-skills
Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Related
Categories
Questions about Premortem Assassin
What does Premortem Assassin do?
Kill the plan on paper before reality does it for money. An agent skill from mohitagw15856/pm-claude-skills. Premortem Assassin is an agent skill from mohitagw15856/pm-claude-skills. Kill the plan on paper before reality does it for money.
When should I use Premortem Assassin?
Premortem Assassin fits situations like: tasks that involve Runbooks and postmortems.
How do I install Premortem Assassin in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin -a claude-code`. Or copy the skill folder (skills/premortem-assassin in mohitagw15856/pm-claude-skills) into .claude/skills/premortem-assassin in your project. Claude Code loads it when a task matches its description.
How do I install Premortem Assassin in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin -a codex`. Or copy the skill folder (skills/premortem-assassin in mohitagw15856/pm-claude-skills) into .agents/skills/premortem-assassin in your project. Codex loads it when a task matches its description.
Can I use Premortem Assassin in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/premortem-assassin, .gemini/skills/premortem-assassin, .github/skills/premortem-assassin and .opencode/skills/premortem-assassin in your project.
What does Premortem Assassin need to run?
SKILL.md names no scripts, command-line tools or credentials: Premortem Assassin is instructions for the agent only.
Does Premortem Assassin access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Premortem Assassin safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Premortem Assassin use?
Premortem Assassin is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Premortem Assassin use?
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Premortem Assassin?
Skills that share tags, products or a category with Premortem Assassin: Trader Memory Core (tradermonty/claude-trading-skills, 3k stars), Author Migration (nrwl/nx, 29k stars), Write Notes Like Deepseek (czm15053/write-notes-like-deepseek, 508 stars) and OpenRig Upgrade Procedure (mvschwarz/openrig, 6.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Premortem Assassin?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.