Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Changelog Orchestrator — measured AI agent skill | DecimalAI

jeremylongshore/changelog-orchestrator

NewSkillScoreMaintained

Draft changelog PRs by collecting GitHub/Slack/Git changes, formatting with templates, running quality gates, and preparing a branch/PR. Use when generating weekly/monthly release notes or when the user asks to create a changelog from recent merges. Trigger with "changelog weekly", "generate release notes", "draft changelog", "create changelog PR".

Documentationby jeremylongshore

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Doc Ops pack

decimalai skills pull jeremylongshore-changelog-orchestrator

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/jeremylongshore-changelog-orchestrator/SKILL.md

Raw file: /s/jeremylongshore-changelog-orchestrator/SKILL.md ↗ · machine-readable summary at /s/jeremylongshore-changelog-orchestrator.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—-4% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-8%	0%
case-08	✗→✓	▲ Improved	-36%	0%
case-09	✗→✓	▲ Improved	-33%	0%
case-12	✗→✓	▲ Improved	-38%	0%
case-14	✗→✓	▲ Improved	-18%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jeremylongshore / claude-code-plugins-plus-skills

skills/.curated/changelog-orchestrator/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 9 files · scripts

Skill contents

scripts/

references/

assets/

SKILL.md

Changelog Orchestrator

Overview

This skill turns raw repo activity (merged PRs, issues, commits, optional Slack updates) into a publishable changelog draft and prepares a branch/PR for review.

Prerequisites

A project config file at .changelog-config.json in the target repo.
Required environment variables set (at minimum GITHUB_TOKEN for GitHub source).
Git available in PATH; gh optional (used for PR creation if configured).

Instructions

Read .changelog-config.json from the repo root.
Validate it with ${CLAUDE_SKILL_DIR}/scripts/validate_config.py.
Decide date range:
Load the configured markdown template (or fall back to ${CLAUDE_SKILL_DIR}/assets/weekly-template.md).
Render the final markdown using ${CLAUDE_SKILL_DIR}/scripts/render_template.py.
Ensure frontmatter contains at least date (ISO) and version (SemVer if known; otherwise 0.0.0).
Run deterministic checks using ${CLAUDE_SKILL_DIR}/scripts/quality_score.py.
If score is below threshold:
Write the changelog file to the configured output_path.
Create a branch changelog-YYYY-MM-DD, commit with docs: add changelog for YYYY-MM-DD.
If gh is configured, open a PR; otherwise, print the exact commands the user should run.

See ${CLAUDE_SKILL_DIR}/references/implementation.md for detailed implementation guide.

Output

A markdown changelog draft (usually CHANGELOG.md), plus an optional PR URL.
A quality report (score + findings) from ${CLAUDE_SKILL_DIR}/scripts/quality_score.py.

Error Handling

See ${CLAUDE_SKILL_DIR}/references/errors.md for comprehensive error handling.

Examples

See ${CLAUDE_SKILL_DIR}/references/examples.md for detailed examples.

Resources

Validate config: ${CLAUDE_SKILL_DIR}/scripts/validate_config.py
Render template: ${CLAUDE_SKILL_DIR}/scripts/render_template.py
Quality scoring: ${CLAUDE_SKILL_DIR}/scripts/quality_score.py
Default templates:
${CLAUDE_SKILL_DIR}/assets/default-changelog.md
${CLAUDE_SKILL_DIR}/assets/weekly-template.md
${CLAUDE_SKILL_DIR}/assets/release-template.md

Want to see if jeremylongshore/changelog-orchestrator would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.