Agent skill · Audited from source
Changelog Generator
skill · borghei/Claude-SkillsNOASSERTION licenceAudited 19 Oct 2026 · source 6e3fcbdbb5cf
Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 6e3fcbdbb5cf and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 5 findings, 0 critical or high. What it does: Generate changelogs and release notes from Conventional Commits with semver bump detection, Keep a Changelog formatting, and monorepo scopes. Use when preparing releases, enforcing commit standards, or automating…
Cite
Cite this page
ModelsAtlas. “Changelog Generator (borghei/Claude-Skills)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/borghei/changelog-generator
6 skills are called “Changelog Generator”. You are viewing borghei/Claude-Skills.
- borghei/Claude-Skills★ 949!CAUTION
- alirezarezvani/claude-skills★ 28k!CAUTION
- mohitagw15856/pm-claude-skills★ 1.4k!CAUTION
- revfactory/harness-100★ 1.3k✓SAFE
- skillcreatorai/ai-agent-skills★ 1.2k✓SAFE
and 1 more with this name.
Trust audit
Audit 0.4.1 · source read 19 Oct 2026
CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | WARN | 5 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | PASS | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (5)
MEDIUMInventory / provenanceinv.symlink · .codex/skills/a11y-audit
.codex/skills/a11y-audit
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .codex/skills/ab-test-setup
.codex/skills/ab-test-setup
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .codex/skills/account-executive
.codex/skills/account-executive
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .codex/skills/ad-creative
.codex/skills/ad-creative
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .codex/skills/aeo
.codex/skills/aeo
- Why
- link not followed
- Fix
- —
Audit 0.4.1 · source sha 6e3fcbdbb5cf · 19 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherborghei GitHub userOwner of the repository this skill is read from
- Source folderborghei/Claude-Skills/engineering/changelog-generatorThe exact folder we audited
- LicenceNOASSERTIONAs the repository states it
- Commit pinned for this verdict6e3fcbdbb5cfA new audit runs when the source changes
- Repository statusNot archivedLast push 12 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Generate changelogs and release notes from Conventional Commits with semver bump detection, Keep a Changelog formatting, and monorepo scopes. Use when preparing releases, enforcing commit standards, or automating…
--- name: changelog-generator description: > Generate changelogs and release notes from Conventional Commits with semver bump detection, Keep a Changelog formatting, and monorepo scopes. Use when preparing releases, enforcing commit standards, or automating release notes. license: MIT + Commons Clause metadata: version: 1.1.0 author: borghei category: engineering domain: release-management tier: POWERFUL updated: 2026-06-17 frameworks: conventional-commits, keep-a-changelog, semantic-versioning --- # Changelog Generator Generate consistent, auditable changelogs and release notes from Conventional Commits. Parses commit messages, detects semantic version bumps (major/minor/patch), renders Keep a Changelog sections, supports monorepo scoped changelogs, integrates with CI for automated release notes, and enforces commit format with linting. Separates commit parsing, bump logic, and rendering so teams can automate releases without losing editorial control. ## Keywords changelog, release notes, conventional commits, semantic versioning, semver, Keep a Changelog, commit linting, release automation, monorepo changelog ## Core Capabilities - **Commit parsing** — parse Conventional Commit messages into structured data (type, scope, description, body, footer); detect breaking changes from `!` and `BREAKING CHANGE:`. - **Semantic version detection** — map commit types to bump levels (breaking→major, feat→minor, others→patch); support pre-release versions. - **Changelog rendering** — Keep a Changelog, GitHub release notes, plain markdown, and JSON output grouped by type. - **Quality enforcement** — commit message linter for CI and pre-commit hooks, strict mode, scope validation, breaking-change documentation requirements. ## When to Use - Before publishing a release tag - During CI to generate release notes automatically - In PR checks to enforce commit message standards - In monorepos where package changelogs need scoped filtering - When converting raw git history into user-facing notes - As a pre-release checklist step ## Clarify First Before generating the changelog, confirm these inputs. If any is unknown or vague, ASK — do not assume: - [ ] **Commit range** — since which tag or commit (defines what history is included) - [ ] **Output format** — Keep a Changelog, GitHub release notes, plain markdown, or JSON (sets `changelog_formatter.py --format`) - [ ] **Version & scope** — the release version, and in a monorepo which package scope to filter (sets `--version` and scoped filtering) Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact. ## Tools | Tool | Purpose | Command | |------|---------|---------| | `commit_parser.py` | Parse `git log` (with `---COMMIT_END---` delimiters) into structured changelog entries | `git log --pretty=format:'%H%n%s%n%b%n---COMMIT_END---' --no-merges \| python scripts/commit_parser.py --json` | | `breaking_change_detector.py` | Scan commit messages/diffs for breaking-change indicators | `python scripts/breaking_change_detector.py -f gitlog.txt --severity high` | | `changelog_formatter.py` | Format parsed commits into Keep a Changelog or GitHub markdown | `python scripts/changelog_formatter.py -f parsed.json --version 1.4.0 --format keepachangelog` | ## References Load the reference that matches the task — keep this file lean and pull detail on demand: - **[references/commit-format-and-rendering.md](references/commit-format-and-rendering.md)** — the Conventional Commit grammar, type→section/semver mapping table, breaking-change rules, and the Keep a Changelog and GitHub Release Notes output formats. Read when defining commit standards or output style. - **[references/generation-and-linting.md](references/generation-and-linting.md)** — the 4-step parse→bump→render workflow with Python code, the pre-commit hook and CI commitlint config, monorepo scoped-changelog strategy, and the release-workflow integration diagram. Read when building the pipeline or enforcing format. - **[references/quality-and-troubleshooting.md](references/quality-and-troubleshooting.md)** — the pre-publish quality checklist, common pitfalls, best practices, troubleshooting table, and success criteria. Read before publishing a changelog or when diagnosing an issue. ## Scope & Limitations **This skill covers:** - Parsing Conventional Commit messages into structured data for changelog generation - Determining semantic version bumps (major/minor/patch) from commit history - Rendering changelogs in Keep a Changelog, GitHub Release Notes, plain markdown, and JSON formats - Enforcing commit message standards via pre-commit hooks and CI linting **This skill does NOT cover:** - Actual release publishing or deployment pipeline execution — see `engineering/ci-cd-pipeline-design` - Git tag management, branch strategies, or merge workflows — see `engineering/git-workflow-automation` - Writing or improving commit messages themselves — see `standards/git/git-workflow-standards.md` - Coordinated multi-package versioning with tools like Changesets or Lerna — referenced in monorepo strategy but not implemented here ## Integration Points | Skill | Integration | Data Flow | |-------|-------------|-----------| | `engineering/ci-cd-pipeline-design` | Changelog generation runs as a CI stage before release publishing | Parsed commits and rendered changelog feed into the release pipeline as artifacts | | `engineering/git-workflow-automation` | Commit linting hooks enforce format before commits reach the changelog generator | Pre-commit validation ensures only parseable commits enter the git history | | `engineering/code-review-automation` | PR checks verify commit messages conform to Conventional Commits before merge | Linting results gate PR approval, preventing unparseable commits from reaching main | | `engineering/api-versioning-strategy` | Breaking change detection aligns API versi
Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 6e3fcbd
git clone https://github.com/borghei/Claude-Skills git -C Claude-Skills checkout 6e3fcbdbb5cf
The author documents no install command, so this uses the repository directly. Our verdict covers commit 6e3fcbdbb5cf only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- !CAUTION B 89 / 100
first audit · source
6e3fcbdbb5cf
Similar skills
All coding & review skills →borghei/Claude-Skills
This skill should be used when the user asks to "check accessibility", "audit WCAG compliance", "scan HTML for a11y issues", "check color contrast", or "find accessibility violations in web pages".
borghei/Claude-Skills
Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when building AI agent systems, designing agent workflows, creating tool schemas, or evaluating agent…
borghei/Claude-Skills
Design AI agent communication protocols: MCP tool schemas, A2A, function calling, and inter- agent messaging. Use when building multi-agent systems, defining tool interfaces, or implementing agent-to-agent communication.
borghei/Claude-Skills
Design multi-agent orchestration with workflow DAGs, routing, handoff protocols, and state management. Use when building pipelines of specialized agents, designing fan-out/fan-in patterns, or implementing fault-tolerant…
borghei/Claude-Skills
Multi-agent DAG orchestration for workflows where AI agents collaborate via dependency graphs, covering agent spawning, output merging, and quality evaluation. Use when a task needs multiple specialized agents or to…
borghei/Claude-Skills
Analytics engineering across data modeling, dbt, transformation, and semantic layers. Use when building dbt models, designing star schemas, writing staging or mart SQL, configuring data tests, or optimizing warehouse…
Questions about Changelog Generator
What does the Changelog Generator skill do?
Is Changelog Generator safe to install?
What can Changelog Generator access on my machine?
How current is this page?
Sources
- github.com/borghei/Claude-Skills/tree/main/engineering/changelog — the audited source at commit 6e3fcbdbb5cf and every finding aboveObserved · 19 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the Changelog Generator skill do?
- Is Changelog Generator safe to install?
- What can Changelog Generator access on my machine?