reasoning-semiformally

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.

Jump to install

Repository: oaustegard/claude-skills
Last source activity: July 25, 2026 at 21:21
Detected SKILL.md language: English
Stars: 147
Forks: 5

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/oaustegard/claude-skills --skill reasoning-semiformally

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

4 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

hallucinating-labels

Assign items to a CLOSED label vocabulary that is too large to put in a prompt — product taxonomies, category hierarchies, tag vocabularies, routing tables, ICD/SIC-style code lists. A cheap model writes the label it thinks the vocabulary would use, and an embedder snaps that writing onto the nearest legal value, so the schema is never transmitted and the output is always in-vocabulary. Use for "classify these into our taxonomy", "tag these against the existing tag list", "map these queries to categories", "the enum is too big to send", or a Literal/enum that hits a provider cap. NOT for a vocabulary that fits in a prompt — structured output measured 0.701 acc@1 there against this pattern's 0.564. NOT for open-ended labelling with no fixed vocabulary, and not for ranked retrieval over documents (bm25).

2026-09-01

declauding

Removes LLM prose tics from drafts — staged reveals, "it's not X, it's Y", significance tags, abstraction agency, coy headers, fragment cadence, the flatter slop patterns (copula avoidance, participle tails, forced triads, chatbot residue), the flat-certainty patterns the pass itself produces (bare adverbs, juridical vocabulary, verification compounds, privative coinages), and the confiding-essayist patterns (announced honesty, stranded auxiliaries, retroactive significance, totalizing claims, obituary headlines) — and returns plain human technical prose. Use when text needs editing for register, when someone says "de-claude", "de-slop", "humanize this", "this reads like AI", "make this sound human", "remove the tics/claudisms", or asks for a voice/register pass on a post, README, report, PR description or essay. Also use before publishing any draft Claude wrote. Verifies the rewrite kept every claim. Produces either clean prose or an annotated HTML diff showing every edit with its original and reason.

2026-08-30

atprotoing

Read Bluesky/ATProto without depending on Bluesky's AppView — interactions on a user's posts, thread replies, any repo's records, network-wide backlinks across every lexicon, an account's handle and PDS history, which collections are active network-wide, and layer-by-layer outage diagnosis. Use when bsky.app or the AppView is down or slow, when a Bluesky read returns timeouts or 5xx, when asked who liked/replied/quoted/reposted something, when pulling live Bluesky context cheaply, when reading records straight from a PDS, when asked who references a record or account anywhere on the network, whether an account has changed handle or migrated servers, or which lexicons and non-Bluesky apps are active on atproto. Complements browsing-bluesky, which routes everything through the AppView and fails when it does.

2026-08-30

View all from this repository

name	reasoning-semiformally
description	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.
metadata	{"version":"0.3.0"}

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 or similar): Read haiku.md in this skill directory. It contains full procedural templates with worked examples.

If you are Sonnet-class or above (Sonnet 4.6, Opus): Read sonnet.md in this skill directory. It contains compact verification checkpoints.

Composing Tasks

For complex tasks, apply templates sequentially:

Fault localization to find the bug
Patch verification to validate a proposed fix
Patch equivalence to compare alternative fixes

Each output feeds the next as premises.

reasoning-semiformally

Source facts

Install options

Review the source files

More from this repository

More from this repository

Semi-Formal Code Reasoning

Skip Conditions

Model-Specific Instructions

Composing Tasks

Semi-Formal Code Reasoning

Skip Conditions

Model-Specific Instructions

Composing Tasks