Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Bump

ASecurity

Use when discovering and confirming the next version from a project's own release scheme before cutting the release.

3 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsbashgit

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add tony/skills --skill bump --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Bump?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Bump
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tony-bump/badge)](https://www.skillsdirectory.com/skills/tony-bump)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: bump
description: "Use when discovering and confirming the next version from a project's own release scheme before cutting the release."
allowed-tools: ["Bash", "Read", "Grep", "Glob", "Edit", "AskUserQuestion"]
argument-hint: "[patch|minor|major|prerelease|final|<version>] [--push] [--tag] [--push-tag]"
user-invocable: true
disable-model-invocation: true
---


# Bump to the Next Version

Discover the project's current version and versioning scheme, work out
what "next" means, get the user's explicit choice, then run the full
`/release:cut` procedure at the chosen version.

Arguments: $ARGUMENTS

First, read `../../references/release-conventions.md`.
The safety contract in `../cut/SKILL.md` applies
here unchanged: no push, no tag, no tag push without the explicit
flags.

---

## Phase 1: Discover the Current Position

Gather three signals and check they agree:

1. **Manifest version** — from the version-bearing files (conventions
   reference).
2. **Latest tag** — `git tag --sort=-creatordate | head -20`, noting
   the prefix convention and the increment vocabulary the project has
   actually used (aN, bN, rcN, postN, devN, `-next.N`, plain semver).
3. **CHANGES unreleased header** — the version it already targets.
   A stable-track header like `## <project> 0.63.x (unreleased)`
   constrains the next release to the `0.63` series unless the user
   overrides; a prerelease-track header names the next version
   outright.

If the signals disagree (manifest ahead of tags, CHANGES targeting a
different series), surface the discrepancy before proposing anything.

## Phase 2: Enumerate Candidates

Build the candidate list from the project's scheme — concrete
versions, not abstract bump names:

- **Prerelease track** (e.g. current `0.1.9a1`):
  - Next prerelease: `0.1.9a2` — the routine increment
  - Graduate to final: `0.1.9`
  - Promote the segment (`a` → `b` → `rc`) — only if the project's
    tag history uses those segments
- **Stable track** (e.g. current `0.1.9`):
  - Patch: `0.1.10`
  - Minor: `0.2.0`
  - Major: `1.0.0`
  - Start a prerelease series: `0.2.0a0` (PEP 440) or the npm
    equivalent (`0.2.0-next.0`) — matching the project's vocabulary
- **npm prerelease track** (e.g. `0.1.0-next.11`): next prerelease
  `0.1.0-next.12`, or graduate to `0.1.0`.

Do not offer `post`/`dev` releases unless the user asks or the
argument names one.

## Phase 3: Resolve the Version

- **Explicit version argument** (e.g. `0.2.0a0`) — validate it sorts
  after the current version and fits the scheme, then proceed. If it
  breaks the scheme (a `-next.N` version in a PEP 440 project),
  stop and ask.
- **Bump-type argument** (`patch`, `minor`, `major`, `prerelease`,
  `final`) — map it to the concrete candidate. If the mapping is
  ambiguous for this scheme (`prerelease` on a stable track could
  mean `0.1.10a0` or `0.2.0a0`; `patch` on a prerelease track could
  mean the next prerelease or the graduated final), do not guess —
  present the interpretations via `AskUserQuestion`.
- **No argument** — present the Phase 2 candidates via
  `AskUserQuestion`. Recommend the increment the project performed
  most recently (its last two tags show the habitual step). Label
  each option with the concrete version and a one-line description of
  when it is the right choice.

Never proceed on an inferred version. The user picks; the panel
selection is the confirmation.

## Phase 4: Cut

Run the complete `/release:cut` procedure
(`../cut/SKILL.md`, Phase 1 onward) with the
chosen version, forwarding any `--push` / `--tag` / `--push-tag`
flags the user passed.

The CHANGES step must leave the **next** unreleased header in
`MAJOR.MINOR.x` form on stable-track projects. The typical precedent
is the next minor series — after cutting `1.70.1` the fresh
placeholder reads `## <project> 1.71.x (unreleased)` — but the file's
own past release-to-placeholder transitions are the specification;
mirror them. Prerelease-track projects instead name the full next
prerelease (after `0.0.1a35`, the placeholder is
`## <project> 0.0.1a36 (unreleased)`).

Attribution

tonytony
View sourceSee grades on GitHubMore from tony →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →