Skip to content
Get packs

Decision Post-Mortem

Scores a past business decision against its pre-set success criteria and original dissent

Source Download skill
Repository
alirezarezvani/claude-skills
Stars
29,149
Licence
MIT
Files
1 file

What it does

Once installed, the agent can review a business decision after it has played out. It compares actual results against the success and kill criteria written before the decision, revisits concerns that were raised but overruled, and checks the original assumptions. It then produces a structured retrospective record with a WIN, PARTIAL, LOSS or MIXED verdict and suggested follow-up actions. It is designed as one step in a larger chain of executive-style planning commands.

Great for

  • Leaders or teams who already track decisions with written success metrics and want a disciplined review at the 90-day mark
  • Founders or managers who want to check whether dissenting views in past decisions turned out to be right
  • People studying how to run honest retrospectives on strategic choices

Skip it if

  • Anyone without a prior decision record, since the skill depends on criteria written before the decision; without them it can only offer after-the-fact judgement (the skill itself warns against retro-fitted criteria)
  • Situations needing verified financial or legal conclusions, because the scoring relies entirely on metrics the user supplies and the skill does not check their accuracy

Try asking

  • “Run a post-mortem on last quarter's pricing change against its pre-committed success metrics”
  • “Review the decision to enter a new market now that its 90-day checkpoint has arrived”
  • “Revisit the dissent from our boardroom memo on the hiring freeze and score whether those concerns materialised”
Step-by-step guide: how to use Decision Post-MortemInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    post-mortem.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip post-mortem.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip post-mortem.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Make sure the decision record was created with explicit success and kill criteria, otherwise the scoring will be weak
  • Supply concrete actual figures and thresholds so the Met? and Triggered? columns can be filled accurately
  • Review the agent's verdict yourself, since it depends on the data you provide and the scoring is only as reliable as those inputs

What's inside

  • SKILL.md

Redistributed unmodified from alirezarezvani/claude-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.