Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

version-bump

Étoiles1

Forks0

Mis à jour23 juin 2026 à 04:42

Bump the semver version in pyproject.toml (major, minor, or patch) and prepend a Keep-a-Changelog entry to CHANGELOG.md. Use when preparing a release, before creating a PR (the version-check CI job blocks merge if you don't), or when the user says "bump version", "release", or "increment version".

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

agentculture

agentculture/agentfront

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

Explorateur de fichiers

2 fichiers

SKILL.md

readonly

name	version-bump
description	Bump the semver version in pyproject.toml (major, minor, or patch) and prepend a Keep-a-Changelog entry to CHANGELOG.md. Use when preparing a release, before creating a PR (the version-check CI job blocks merge if you don't), or when the user says "bump version", "release", or "increment version".

Version Bump

Bump the semver version in pyproject.toml and prepend a new entry to CHANGELOG.md. Mirrors the AgentCulture workflow used by culture and other org repos; imported here so the repo is self-contained.

Usage

Run from the repo root.

# With changelog content (pipe JSON via stdin):
echo '{"added":["New X"],"changed":["Refactored Y"],"fixed":["Bug in Z"]}' \
  | python3 .claude/skills/version-bump/scripts/bump.py minor

# Without changelog content (inserts empty ### Added/Changed/Fixed stubs):
python3 .claude/skills/version-bump/scripts/bump.py patch

# Check current version without bumping:
python3 .claude/skills/version-bump/scripts/bump.py show

Bump Types

Type	Example	When to use
`major`	0.1.0 → 1.0.0	Breaking changes, namespace restructures, CLI surface breaks
`minor`	0.1.0 → 0.2.0	New features, new commands, new modules
`patch`	0.1.0 → 0.1.1	Bug fixes, doc updates, dependency bumps, CI-only changes
`show`	prints `0.1.0`	Read-only — no files changed

Changelog JSON Format

Pass via stdin. All fields are optional — only non-empty sections are rendered.

{
  "added":   ["List of new features"],
  "changed": ["List of changes to existing functionality"],
  "fixed":   ["List of bug fixes"]
}

What It Updates

pyproject.toml — the version = "x.y.z" field (single source of truth; agentfront/__init__.py reads it via importlib.metadata, so there is no separate __version__ string to keep in sync).
CHANGELOG.md — inserts a new ## [x.y.z] - YYYY-MM-DD entry at the top.
packaging/teken/pyproject.toml — the compatibility wrapper's own version and its agentfront==<version> dependency pin, kept in lockstep with the root version (a CI guard in tests.yml fails the PR on drift).

Workflow

When invoking this skill, the agent should:

Determine the bump type from the staged/unstaged diff (patch for fixes, minor for new features, major for breaking changes).
Summarize the changes into added / changed / fixed lists.
Pipe the JSON and run the script.
Verify with show.
Commit the bumped pyproject.toml + CHANGELOG.md alongside the code changes, so the version-check CI job sees a consistent bump.

Why repo-local (not the user-global skill)

A matching skill exists at ~/.claude/skills/version-bump/ for personal use, but committing it into this repo means:

The skill travels with the clone — CI hooks, other contributors, and agents on fresh machines all discover it without personal configuration.
The .md paths in this SKILL.md reference the in-repo script, so the guidance is accurate regardless of whether the user has the global skill.

Plus depuis ce dépôt

même dépôt

ask-colleague

agentculture/agentfront

Ask colleague — a *different* backend/model than you (e.g. a local vLLM Qwen) — to take a scoped repo task off your plate, then fold its answer back. The point isn't a stronger model; it's a second, independent mind, and that diversity is the value: `ask-colleague review` gets a candid second opinion on a diff, `ask-colleague explore` gets a fresh read of an area, `ask-colleague write` hands off a small implementation, `ask-colleague feedback` grades a finished work item (the ROI loop), and `ask-colleague clean` reaps stale/corrupt `colleague/*` branches a crashed run left behind (which can break `git fetch`). Pilot a running work item with `monitor`/`guide`/`stop`. Reach for it REFLEXIVELY, the way you'd lean over to the teammate at the next desk — not only when asked: before you present or open a PR on a non-trivial committed diff, run `review` for a diverse second opinion; for a fresh read of an unfamiliar area whose answer is independent of your current context, run `explore`. Both are read-only — isolate

2026-07-021

recall

agentculture/agentfront

Search the shared eidetic memory store and get back ranked, provenanced records. Drives `eidetic recall` with four search modes — exact (verbatim substring), approximate (vector/semantic), keyword (BM25 lexical), and hybrid (a weighted blend of vector+keyword, the default) — each hit carrying its text, full metadata, a relevance `score`, and a freshness `signal`. Recall passively reinforces matched records (bumps last_recall + recall_count). Shadowed and archived records are excluded by default; use --include-shadowed / --include-archived to retrieve them. The store lives at ~/.eidetic/memory (a home-dir path outside any git worktree); the wrapper defaults queries to this agent's PERSONAL, PRIVATE scope (`--scope agentfront --visibility private`, suffix read from culture.yaml) — matching where /remember writes — so a no-flag recall returns this agent's own private records plus the shared public pool, and Claude and the colleague backend recall each other's memories because both resolve the same suffix via thi

2026-06-261

remember

agentculture/agentfront

Ingest records into the shared eidetic memory store so they can be recalled later. Drives `eidetic remember`: accepts one record as a JSON object, or a batch as NDJSON on stdin for bulk ingest. Upsert is idempotent by id (and dedups by content hash) — re-remembering updates in place, never duplicates. Stamps a `created` date on every record at ingest time. Accepts `supersedes` (id of the record this one replaces, for within-scope shadowing via `sweep`) and `links` (list of related-memory ids). The store lives at ~/.eidetic/memory (a home-dir path outside any git worktree), and the wrapper defaults records to this agent's PERSONAL, PRIVATE scope (`--scope agentfront --visibility private`, suffix read from culture.yaml) so they don't leak to a default/other-scope recall — Claude and the colleague backend still share them because both resolve the same suffix via this skill. Pass `--visibility public` to contribute to the shared public pool instead. Use when the user says "remember this", "store this", "save to m

2026-06-261

cicd

agentculture/agentfront

agentfront's CI/CD lane (vendored from steward), layered on `agex pr`. Delegates lint / open / read / reply / delta to agex; adds two steward-derived extensions — `status` (SonarCloud quality gate + hotspots + unresolved-thread tally) and `await` (read --wait + status with non-zero exit on Sonar ERROR or unresolved threads). Use when: creating PRs in agentfront, handling review feedback, polling CI status, or the user says "create PR", "review comments", "address feedback", "resolve threads". Renamed from `pr-review` in steward 0.7.0; rebased on agex in 0.12.0.

2026-05-291

communicate

agentculture/agentfront

Cross-repo + mesh communication from agentfront (vendored from steward): file tracked GitHub issues on sibling repos, fetch issues from sibling repos to inline current state into briefs, and send live messages to Culture mesh channels. Use when the next step lives outside agentfront (a brief for a sibling-repo agent, a status ping for a Culture channel, or pulling an issue body + comments into context). Issue posts auto-sign with `- <nick> (Claude)` (agtag resolves `<nick>` from `culture.yaml`, falling back to repo basename); mesh messages are unsigned (the IRC nick is the speaker). Not for in-agentfront issues — use `gh issue create` or the `cicd` skill for those. Renamed from `coordinate` in steward 0.8.0; absorbed `gh-issues` in 0.9.1. Issue I/O is backed by `agtag` (>=0.1) starting in 0.11.0.

2026-05-291

lint-markdown

agentculture/agentfront

Use after editing any .md file in this repo, before committing, or when the pre-commit hook rejects a commit with markdownlint errors. Runs the repo lint script which auto-fixes violations.

2026-04-221

name	version-bump
description	Bump the semver version in pyproject.toml (major, minor, or patch) and prepend a Keep-a-Changelog entry to CHANGELOG.md. Use when preparing a release, before creating a PR (the version-check CI job blocks merge if you don't), or when the user says "bump version", "release", or "increment version".

Version Bump

Usage

Run from the repo root.

# With changelog content (pipe JSON via stdin):
echo '{"added":["New X"],"changed":["Refactored Y"],"fixed":["Bug in Z"]}' \
  | python3 .claude/skills/version-bump/scripts/bump.py minor

# Without changelog content (inserts empty ### Added/Changed/Fixed stubs):
python3 .claude/skills/version-bump/scripts/bump.py patch

# Check current version without bumping:
python3 .claude/skills/version-bump/scripts/bump.py show

Bump Types

Type	Example	When to use
`major`	0.1.0 → 1.0.0	Breaking changes, namespace restructures, CLI surface breaks
`minor`	0.1.0 → 0.2.0	New features, new commands, new modules
`patch`	0.1.0 → 0.1.1	Bug fixes, doc updates, dependency bumps, CI-only changes
`show`	prints `0.1.0`	Read-only — no files changed

Changelog JSON Format

Pass via stdin. All fields are optional — only non-empty sections are rendered.

{
  "added":   ["List of new features"],
  "changed": ["List of changes to existing functionality"],
  "fixed":   ["List of bug fixes"]
}

What It Updates

pyproject.toml — the version = "x.y.z" field (single source of truth; agentfront/__init__.py reads it via importlib.metadata, so there is no separate __version__ string to keep in sync).
CHANGELOG.md — inserts a new ## [x.y.z] - YYYY-MM-DD entry at the top.
packaging/teken/pyproject.toml — the compatibility wrapper's own version and its agentfront==<version> dependency pin, kept in lockstep with the root version (a CI guard in tests.yml fails the PR on drift).

Workflow

When invoking this skill, the agent should:

Determine the bump type from the staged/unstaged diff (patch for fixes, minor for new features, major for breaking changes).
Summarize the changes into added / changed / fixed lists.
Pipe the JSON and run the script.
Verify with show.
Commit the bumped pyproject.toml + CHANGELOG.md alongside the code changes, so the version-check CI job sees a consistent bump.

Why repo-local (not the user-global skill)

A matching skill exists at ~/.claude/skills/version-bump/ for personal use, but committing it into this repo means:

The skill travels with the clone — CI hooks, other contributors, and agents on fresh machines all discover it without personal configuration.
The .md paths in this SKILL.md reference the in-repo script, so the guidance is accurate regardless of whether the user has the global skill.