Agent skill
deploy
Use when shipping a release of Agent Sessions — bumping version, updating CHANGELOG, building, signing, notarizing, publishing appcast, and creating a GitHub release.
Install this agent skill to your Project
npx add-skill https://github.com/jazzyalex/agent-sessions/tree/main/.claude/skills/deploy
SKILL.md
Deployment Skill (Agent Sessions)
This skill is an agent-facing entrypoint that avoids duplicating the deployment runbook.
Canonical Sources (Single Source of Truth)
- Runbook:
docs/deployment.md - Unified tool:
tools/release/deploy(seetools/release/deploy --help) - Recommended pre-release QA checklist:
docs/release/pre-release-qa.md
If anything here disagrees with the runbook, follow docs/deployment.md.
Workspace Policy (Hard Rule)
- Always run deployment from the user's current local repository checkout.
- Do not clone to temporary directories and do not switch to alternate worktrees as a deployment workaround.
- If the local worktree is dirty, stop and tell the user to clean the tree first (commit, stash, or discard), then continue in the same local repo.
Recommended QA Gate (Before Deploy Steps)
- Before bump/release/verify commands, recommend running
docs/release/pre-release-qa.md. - Ask for QA status explicitly:
- Was the checklist run for this candidate build?
- Result:
GOorNO-GO? - Any known risk accepted for release?
- If QA was not run, pause deployment execution and recommend running the checklist first.
Before Starting (Ask the User)
- Target version (
X.Yfor major/minor releases,X.Y.Zonly for patch releases; never shipX.Y.0) - Any headline changes (new agents, major features) that must be reflected in
docs/CHANGELOG.md - Whether this is a major release that requires onboarding updates
- Public copy updates needed for README/GitHub Pages (major changes to highlight, renamed features, or outdated wording to fix)
Public Copy Update (Required for All Releases)
Always update (every release)
README.mddownload link:v{VERSION}/AgentSessions-{VERSION}.dmgand labelDownload Agent Sessions {VERSION} (DMG)README.mdOption A download link (second occurrence under Install section)docs/index.htmldownload button URL and labeldocs/index.html<meta name="description">content (mention current version + key change)docs/index.html<meta property="og:description">contentdocs/index.html<meta name="twitter:description">content
Update for minor/major or user-visible feature releases
README.md"What's New in X.Y" section: update heading to new version, rewrite TL;DR and Highlights to reflect this release's key changes (do not keep old version's copy)docs/index.htmlhero/feature copy if features were renamed or new agents added
Never add
- Versioned "What's New in X.Y" section to
docs/index.html - Detailed release notes to README or website (those live in
docs/CHANGELOG.md)
After pushing
- Verify GitHub Pages reflects updated
docs/index.html(check meta description and download button)
Pre-Deploy Checklist (Run Before Bump)
-
docs/CHANGELOG.md[Unreleased]section has full, accurate content for this release -
CHANGELOG.md(root, if present) mirrorsdocs/CHANGELOG.mdcontent - README.md download links updated to new version (both occurrences)
- README.md "What's New" section updated to new version heading + rewritten highlights
-
docs/index.htmldownload button URL and label updated -
docs/index.htmlmeta description, og:description, twitter:description updated with version + key change - All above files committed before running
deploy bump(or bump will overwrite)
Sparkle Release Notes (Approval Gate)
- The release pipeline generates structured Sparkle notes from
docs/CHANGELOG.md:- Highlights (current release)
- Other changes (summary)
- Reminder from the baseline release (for patch releases:
A.B)
- During
tools/release/deploy release <VERSION>, the deploy script prints a Sparkle release notes preview after build/sign/notarization and appcast validation. - If
SKIP_CONFIRMis not1, it will pause and ask for approval before publishing (pushing appcast, updating Homebrew, updating the GitHub release). - If you want fully unattended deploys, set
SKIP_CONFIRM=1(skips the notes prompt). - If the current release has no structured bullets, the generator adds a fallback highlight:
Small bug fixes and stability improvements.
Standard Workflow (Use the Unified Tool)
tools/release/deploy changelog [FROM_TAG]
tools/release/deploy bump [patch|minor|major]
git push origin main
tools/release/deploy release <VERSION> [--dry-run]
tools/release/deploy verify <VERSION>
Failure Handling
- First stop:
docs/deployment.md→ Troubleshooting, logs, and rollback guidance. - Rollback only after reviewing logs:
tools/release/rollback-release.sh <VERSION>.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-session-format-check
Verify agent session format compatibility for Agent Sessions. Use when any agent CLI updates, when monitoring flags drift, or when bumping max verified versions (fixtures + docs + tests). Covers session schema, usage/limits tracking, storage backends, and discovery path contracts for all supported agents.
agent-support-matrix
Maintain Agent Sessions agent support matrix and JSON/JSONL parsing compatibility. Use when checking upstream agent releases for session format changes, updating max verified versions in docs/agent-support/agent-support-matrix.yml, or updating docs/agent-json-tracking.md and fixtures/tests.
sc-skill
Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Didn't find tool you were looking for?