Math Review

What it does

When your agent uses it

• Reviewing scientific algorithms
• Tasks that involve Machine learning

Example prompts

• “Use the math-review skill to verify math-heavy code for algorithmic correctness and numerical stability”
• “/math-review”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Context Sync
2. 2Requirements Mapping
3. 3Derivation Verification
4. 4Stability Assessment
5. 5Proof of Work
6. 6Verify Findings Are Grounded (math-review:findings-verified)

What it can do on your machine

Read from SKILL.md and the folder at commit 9f3eb00. 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

  Shell commands in SKILL.md call:

  • git
  • pytest
  • jupyter

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  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

Math Review loads about 1.2k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 354 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~40

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

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

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 athola/claude-night-market at commit 9f3eb00, republished under its MIT licence (© athola). 354 words, ~1,166 tokens.

name

math-review

description

Verifies math-heavy code for algorithmic correctness and numerical stability. Use when reviewing scientific algorithms, ML models, or numerical code.

alwaysApply

false

category

specialized

tags

math, algorithms, numerical, stability, verification, scientific

usage_patterns

algorithm-review, numerical-analysis, derivation-verification, stability-assessment

complexity

advanced

model_hint

deep

estimated_tokens

200

progressive_loading

true

dependencies

imbue:proof-of-work, imbue:review-core, imbue:structured-output

/math-review

pwd && git status -sb && git diff --stat origin/main..HEAD

pytest tests/math/ --benchmark
jupyter nbconvert --execute derivation.ipynb

## Summary
[Brief findings]

## Context
Files | Risk classification | Standards

## Requirements Analysis
| Invariant | Verified | Evidence |

## Derivation Review
[Status and conflicts]

## Stability Analysis
Condition number | Precision | Risks

## Issues
[M1] [Title]
- Location: file.py:123
- Anchor: `verbatim source text at line 123`
- Issue: [what is wrong] | Fix: [remediation] | Evidence: [E1]

## Recommendation
Approve / Approve with actions / Block

© athola, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in plugins/pensive/skills/math-review of athola/claude-night-market.

• SKILL.md
• modules/derivation-verification.md
• modules/numerical-stability.md
• modules/requirements-mapping.md
• modules/testing-strategies.md

Open the folder on GitHubat commit 9f3eb00