Compares HEAD with the latest published version to analyze real changes, group by type, and recommend version bumps. Use before publishing a release to understand what actually changed.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Analyzes unpublished changes by comparing HEAD with the latest published version. Reads actual diffs instead of just copying commit messages.
# npm
npm view <package-name> version 2>/dev/null || echo "not published"
# PyPI
pip index versions <package-name> 2>/dev/null | head -1
# Or use git tags
git tag --sort=-v:refname | head -1
# Get actual diff (NOT just commit messages)
git diff v{published-version}..HEAD --stat
git diff v{published-version}..HEAD
For each commit, MUST:
## Unpublished Changes (v{published} -> HEAD)
### Features
| Scope | What Changed |
|-------|--------------|
| auth | Added OAuth2 support with Google and GitHub providers |
### Fixes
| Scope | What Changed |
|-------|--------------|
| api | Fixed race condition in concurrent request handling |
### Refactoring
| Scope | What Changed |
|-------|--------------|
| core | Extracted retry logic from 3 services into shared module |
### Breaking Changes
- Removed deprecated `v1/login` endpoint
### Files Changed
42 files changed, 1205 insertions(+), 387 deletions(-)
### Suggested Version Bump
- **Recommendation**: minor
- **Reason**: New features added, no breaking changes in public API
| Condition | Bump |
|---|---|
| Breaking changes in public API | major |
| New features, no breaking changes | minor |
| Bug fixes, refactoring, docs only | patch |
User: "What changed since last release?"
Output: Reads diff between v1.2.3 and HEAD, identifies 3 features, 2 fixes, 1 refactor, no breaking changes. Recommends minor bump to v1.3.0.
Inspired by: oh-my-opencode get-unpublished-changes command
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Applies abstract interpretation using different abstract domains (intervals, octagons, polyhedra, sign, congruence) to statically analyze program variables and infer invariants, value ranges, and relationships. Use when analyzing program properties, inferring loop invariants, detecting potential errors, or understanding variable relationships through static analysis.
日本語の概要は準備中です。原文の説明を表示しています。
Uses abstract interpretation to automatically infer loop invariants, function preconditions, and postconditions for formal verification. Generates invariants that capture program behavior and support correctness proofs in Dafny, Isabelle, Coq, and other verification systems. Use when adding formal specifications to code, generating verification conditions, inferring contracts for functions, or discovering loop invariants for proofs.
日本語の概要は準備中です。原文の説明を表示しています。
Performs abstract interpretation over source code to infer possible program states, variable ranges, and data properties without executing the program. Reports potential runtime errors including out-of-bounds accesses, null dereferences, type inconsistencies, division by zero, and integer overflows. Use when analyzing code for potential runtime errors, performing static analysis, checking safety properties, or verifying program behavior without execution.
日本語の概要は準備中です。原文の説明を表示しています。
Performs abstract interpretation to produce summarized execution traces and high-level program behavior representations. Highlights key control flow paths, variable relationships, loop invariants, function summaries, and potential runtime states using abstract domains (intervals, signs, nullness, etc.). Use when analyzing program behavior, understanding execution paths, computing loop invariants, tracking variable ranges, detecting potential runtime errors, or generating program summaries without concrete execution.
日本語の概要は準備中です。原文の説明を表示しています。
Create ACSL (ANSI/ISO C Specification Language) formal annotations for C/C++ programs. Use this skill when working with formal verification, adding function contracts (requires/ensures), loop invariants, assertions, memory safety annotations, or any ACSL specifications. Supports Frama-C verification and generates comprehensive formal specifications for C/C++ code.
日本語の概要は準備中です。原文の説明を表示しています。
CLI-based browser automation with persistent page state using ref-based element interaction. Use when users ask to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
日本語の概要は準備中です。原文の説明を表示しています。