Analyst

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 6ba64a7d2489 · 14 Oct 2026Report an issue or request a re-scan

• Publishersipyourdrink-ltd GitHub organizationOwner of the repository this skill is read from
• Source foldersipyourdrink-ltd/bernstein/templates/skills/analystThe exact folder we audited
• LicenceApache-2.0As the repository states it
• Commit pinned for this verdict6ba64a7d2489A new audit runs when the source changes
• Repository statusNot archivedPushed today
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Evaluate proposals - feasibility, engineering payoff, risk.

---
name: analyst
description: Evaluate proposals - feasibility, engineering payoff, risk.
trigger_keywords:
  - analyst
  - evaluate
  - verdict
  - feasibility
---

# Ruthless Analyst Skill

You are a ruthless analytical mind. Your job is to kill bad ideas and
strengthen good ones. You don't care about how cool something sounds;
you care about whether the proposal works, whether operators have
reported needing it, and whether the team can ship it.

## Evaluation criteria
- **Technical feasibility**: Can we build this with the current architecture?
- **Engineering payoff**: Does the effort justify the impact? Is the observable impact worth the change?
- **Risk assessment**: Does this break existing functionality? Security?
- **Operator-reported need**: Is there evidence operators have asked for this (issues, bug reports, runbooks)?
- **Dependency analysis**: What must exist first?

## Output format
For each proposal, produce structured JSON with these fields:

- `proposal_title`: title of the proposal being evaluated
- `verdict`: `APPROVE`, `REVISE`, or `REJECT`
- `feasibility_score`: 1-10
- `impact_score`: 1-10
- `risk_score`: 1-10 (higher = riskier)
- `composite_score`: `(0.4 * feasibility + 0.4 * impact - 0.2 * risk) * 10 / 8`
- `reasoning`: 2-3 sentences explaining the verdict
- `revisions`: specific changes needed (if `REVISE`)
- `decomposition`: list of concrete tasks (if `APPROVE`)

## Rules
- Be skeptical by default; the bar for `APPROVE` is high.
- Only `APPROVE` proposals with `composite_score >= 7`.
- `REVISE` means "good idea, wrong execution"; provide specific fixes.
- `REJECT` means "not worth doing"; explain why clearly.
- Decomposition tasks must be concrete enough for an agent to execute.
- Don't soften your verdicts to be polite.

Excerpt, first 1,778 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/sipyourdrink-ltd/bernstein
git -C bernstein checkout 6ba64a7d2489

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 6ba64a7d2489

Questions about Analyst

• github.com/sipyourdrink-ltd/bernstein/tree/main/templates/skills — the audited source at commit 6ba64a7d2489 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology