Install
$ agentstack add skill-alexstormwood-agentic-skills-conventional-commit-summary ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Conventional Commit Summary
Summarise the completed work as a single Conventional Commit message.
The output must be one line only. Do not include a body, bullet list, explanation, trailer, or extended description field.
Keep in mind how the Conventional Commit syntax maps to semver, if the project uses semver version numbering such as a package.json file for NodeJS projects.
fixcommits should translate toPATCHin semver numberingfeatcommits should translate toMINORin semver numberingfeat!orfeat()!commits should translate toMAJORin semver numbering
While you don't have to determine the new semver number, this framing can help with the developer's expectations and satisfaction with the computed commit message.
Format
Use this shape:
type(scope): concise summary
Use this shape when there is no useful scope:
type: concise summary
Use this shape for concise breaking changes:
type(scope)!: concise summary
Use this shape for concise breaking changes with no useful scope:
type!: concise summary
Keep the message brief enough to work as a git commit subject. Aim for roughly 50 to 72 characters when practical, but prefer clarity over forcing an exact length.
Breaking Changes
Use ! immediately before the colon when the change breaks an existing public contract, expected behaviour, API, command, schema, route, configuration format, package export, or documented workflow.
Do not add a BREAKING CHANGE: footer. This skill produces one-line commit subjects only.
Use the summary to name what changed, not just that something broke.
Good:
feat(auth)!: changed the password requirements
refactor(api)!: renamed user response fields
chore(config)!: replaced legacy environment variable names
Avoid:
feat(auth)!: breaking change
refactor!: changed stuff
Types
Choose the type that best describes the primary change:
feat: adds a user-facing feature, capability, content item, or new behaviourfix: fixes a bug, broken behaviour, typo with functional impact, or incorrect outputdocs: updates documentation, instructions, guides, examples, or prose-only contentstyle: changes formatting, whitespace, naming, or presentation without changing behaviourrefactor: restructures code without intended behaviour changestest: adds or updates tests, fixtures, mocks, or test configurationchore: performs maintenance, setup, dependency, tooling, metadata, or repo housekeeping workbuild: changes build scripts, packaging, bundling, or release artefactsci: changes continuous integration or deployment workflow configurationperf: improves performancerevert: reverts a previous change
Scope
Use a short lowercase scope when it helps identify the area changed.
Good scopes are concrete repository areas, features, packages, routes, components, tools, or content groups:
authbananasblogskillstylestestsdepsci
Omit the scope when it would be vague or forced.
Summary Rules
- Write one brief sentence fragment after the colon.
- Start the summary with a lowercase word unless the first word is a proper noun, acronym, file name, or product name.
- Use past tense or simple action phrasing when that best matches the user's style, such as
added,fixed,updated, orremoved. - Name the concrete thing that changed.
- Add
!only when the change is genuinely breaking. - Prefer specific nouns over generic words like
stuff,changes,updates, orimprovements. - Do not end with a full stop.
- Do not mention that an AI agent did the work unless that is the actual content of the change.
- Do not include issue numbers, co-author trailers, test results, or extra context unless the user explicitly asks for them.
Examples
feat(bananas): added more banana varieties to the spawn system
feat(auth)!: changed the password requirements
fix(auth): fixed token refresh after expired sessions
docs(readme): updated setup steps for local development
docs(skill): added anti-slop guardrails to Alex writing style
style(nav): tightened spacing between menu links
refactor(api)!: renamed user response fields
refactor(api): moved request validation into shared middleware
test(cart): added coverage for empty checkout states
chore(config)!: replaced legacy environment variable names
chore(deps): updated frontend package versions
build(vite): added production asset compression
ci(actions): added lint checks for pull requests
perf(search): reduced duplicate index lookups
revert(auth): reverted session cookie expiry change
Picking The Best Message
If multiple changes were made, choose the dominant user-visible or repository-significant change.
Examples:
- Code change plus tests: use
feat,fix, orrefactor, nottest. - Documentation-only change: use
docs. - Formatting-only change: use
style. - Dependency or tooling-only change: use
chore,build, orci. - Skill content change: usually use
docs(skill)orfeat(skill)depending on whether it only explains behaviour or adds a new reusable capability. - Breaking API, schema, config, route, CLI, or documented workflow change: add
!before the colon.
When unsure, choose the clearest honest summary over trying to encode every detail.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: AlexStormwood
- Source: AlexStormwood/agentic-skills
- License: MIT
- Homepage: https://www.skills.sh/alexstormwood/agentic-skills
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.