Case forensics

Skill dzhokhov/markdown-agent-vault/skills/case-forensics

Agent-ready Markdown vault methodology with AGENTS.md, templates, skills, logs, and file-safe workflows.

Install

npx -y skills add dzhokhov/markdown-agent-vault --skill case-forensics

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

SKILL.md

2.3 KB, as published. Nobody here has run it

Case Forensics

Navigation: Skill index

Overview

Convert the unstructured discussion into a reproducible instruction-level case.

Skill is responsible for the thread -> evidence map -> method extraction -> reproducibility report phase.

Workflow

1) Parse Timeline

Restore the chronology:

who acted,
What decisions were made,
What changes have been made,
That was the result.

2) Build Evidence Map

Mark each thesis:

EVIDENCE – Confirmed by message/artifact
ASSUMPTION – conclusion without direct proof
GAP - critically lacking data

3) Extract Method

Collect the method in consecutive steps:

entry
action
toolkits
quality control
completion

4) Quantify Outcome

Record:

before/after metrics
Type of effect (time/money/quality/risk)
failed

5) Reproducibility Score

Evaluate the reproducibility of the contract case-data-contract:

input_completeness
method_specificity
artifact_availability
metric_verifiability

6) Prepare Final Case

Give me:

case-case
How to Repeat in 120 Minutes
GAP block + questions to clarify from gap-interview-questions

Output

Return the sections:

Context and purpose
Baseline conditions
Method(s)
Materials/industry/tools
Outcome and metrics
That didn't work.
Replication in 120 minutes
Limits of portability
GAP and issues

Quality Gates

No steps without entry/exit.
Every numerical metric has a source in a thread.
Any hypothesis without confirmation is labeled ASSUMPTION.
There are obvious limitations to the applicability of the case.

Anti-Patterns

Do not give out a “success story” as a methodology.
Do not hide failures/limitations.
Do not replace GAP with guesswork.