reasoning-semiformally SKILL.md skillA

reasoning-semiformally from oaustegard/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add oaustegard/claude-skills/reasoning-semiformally@v0.4.0

Pins v0.4.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
oaustegard/claude-skills
Path
plugins/code-intelligence/skills/reasoning-semiformally/SKILL.md
Versions recorded
4
Latest version
v0.4.0, committed Oct 7, 2026
First version recorded
Jul 7, 2026
Size
1,586 bytes
Repository stars
158
License
MIT

Apply semi-formal certificate reasoning to code analysis — patch verification, fault localization, patch equivalence. Use when reviewing patches, hunting bugs across scopes, comparing fixes, or when code reasoning requires tracing execution across files/modules. Triggers on code review, bug localization, patch comparison, name shadowing, scope analysis, regression checking.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Semi-Formal Code Reasoning

Structured certificate templates that force mandatory checkpoints before conclusions.

## Skip Conditions

Do NOT apply semi-formal reasoning when:
- The change is trivial: docs, formatting, version bumps, config changes
- The bug is locally obvious: typo, off-by-one in the same function, missing comma
- No execution paths cross scope boundaries
- The task is not code analysis (text editing, data extraction, summarization)

If any skip condition is met, proceed with standard reasoning.

## Model-Specific Instructions

**If you are Haiku-class (Haiku 4.5, Haiku 5.5):**
Read `haiku.md` in this skill directory. It contains full procedural templates with worked examples.

**If you are Sonnet-class or above (Sonnet 5, Sonnet 5.5, Opus, Fable):**
Read `sonnet.md` in this skill directory. It contains compact verification checkpoints.

## Composing Tasks

For complex tasks, apply templates sequentially:
1. **Fault localization** to find the bug
2. **Patch verification** to validate a proposed fix
3. **Patch equivalence** to compare alternative fixes

Each output feeds the next as premises.

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add oaustegard/claude-skills/reasoning-semiformally@sha256:fc7e89211c93798a

The line at the top of this page pins the label v0.4.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wy2gaxvkqyb5dmky.svg)](https://markdownregistry.com/a/art_wy2gaxvkqyb5dmky)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jul 7, 2026 and Oct 7, 2026, about one every 31 days.

versioncommittedcommitsizeaudit
v0.4.0 latest2026-10-07 87f7fec 1,586 BA view · diff
v0.3.12026-09-09 5e58100 1,567 BA view · diff
v0.3.02026-07-25 4b31e7d 1,569 BA view · diff
v0.3.02026-07-07 6154d36 1,557 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1586 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

oaustegard/claude-skills · 158 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wy2gaxvkqyb5dmky
GET https://markdownregistry.com/api/v1/resolve?ref=oaustegard/claude-skills/reasoning-semiformally
GET https://markdownregistry.com/api/v1/blob/fc7e89211c93798a1689113d6b9fa792ce985bcd603e10fd5eecc17356180011

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from oaustegard/claude-skills

AGENTS.md AGENTS.md file
oaustegard/claude-skills · AGENTS.md
git:20260529.cbbffef · audit A · 158 stars
CLAUDE.md CLAUDE.md file
oaustegard/claude-skills · CLAUDE.md
git:20260529.cbbffef · audit A · 158 stars
accessing-github-repos SKILL.md skill
oaustegard/claude-skills · accessing-github-repos/SKILL.md · GitHub repository access in containerized environments using REST API and credential detection. Use when git clone…
v2.0.0 · audit A · 158 stars
agent-routing SKILL.md skill
oaustegard/claude-skills · agent-routing/SKILL.md · Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe…
v2.8.0 · audit A · 158 stars
animating-with-code SKILL.md skill
oaustegard/claude-skills · animating-with-code/SKILL.md · Make a short animated film by writing the drawing code yourself: every frame a pure function of time, rendered…
v0.1.0 · audit A · 158 stars
api-credentials SKILL.md skill
oaustegard/claude-skills · api-credentials/SKILL.md · Securely manages API credentials for multiple providers (Anthropic Claude, Google Gemini, GitHub). Use when skills need…
v0.0.4 · audit A · 158 stars
asking-questions SKILL.md skill
oaustegard/claude-skills · asking-questions/SKILL.md · Guidance for asking clarifying questions when user requests are ambiguous, have multiple valid approaches, or require…
v1.0.7 · audit A · 158 stars
assessing-impact SKILL.md skill
oaustegard/claude-skills · assessing-impact/SKILL.md · Pre-change blast-radius report for a symbol or file. Walks tree-sitting references, augments with a plain-text scan…
v0.1.1 · audit A · 158 stars
atprotoing SKILL.md skill
oaustegard/claude-skills · atprotoing/SKILL.md · Read Bluesky/ATProto without depending on Bluesky's AppView — interactions on a user's posts, thread replies, any…
v0.3.0 · audit A · 158 stars
bm25 SKILL.md skill
oaustegard/claude-skills · bm25/SKILL.md · Ranked content search over a text corpus you point it at, using BM25 (via xhluca/bm25s). Corpus-agnostic: cloned repos…
v0.2.1 · audit A · 158 stars
browsing-bluesky SKILL.md skill
oaustegard/claude-skills · browsing-bluesky/SKILL.md · Browse Bluesky content via API and firehose - search posts, fetch user activity, sample trending topics, read feeds and…
v0.7.1 · audit A · 158 stars
building-github-index-v2 SKILL.md skill
oaustegard/claude-skills · building-github-index-v2/SKILL.md · DEPRECATED - Use building-github-index instead. Superseded per-file GitHub API implementation of progressive disclosure…
v2.0.2 · audit A · 158 stars

Every file in oaustegard/claude-skills

Other files named reasoning-semiformally

reasoning-semiformally SKILL.md skill
oaustegard/claude-skills · reasoning-semiformally/SKILL.md · Apply semi-formal certificate reasoning to code analysis — patch verification, fault localization, patch equivalence…
v0.4.0 · audit A · 158 stars

Browse by kind, by grade A, or by owner.