Claude Market
Menu
SkillsMCPPluginsSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Claude Market
SkillsMCPPluginsSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free →
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free →
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off
Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed
Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off
Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw
Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.
Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams
Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit
Try DataForSEO free →
Reach 47,000+ AI builders
Advertise here →
Skills/boshu2/agentops/release
release logo

release

boshu2/agentops
859 installs392 stars
Run it on Hostinger →up to 70% off + an extra 10% with code ZACAARON10Free API →

Installation

npx skills add https://github.com/boshu2/agentops --skill release

Summary

Run release validation.

SKILL.md

Release Skill

Purpose: Take a project from "code is ready" to "tagged, pushed by the operator, and verified green on the exact tagged SHA."

Pre-flight validation, changelog from git history, version bumps across package files, release commit, annotated tag, curated release notes, and post-push exact-SHA CI verification. Local preparation is reversible. Publishing (including the GitHub Release page) is CI's job.

---

Quick Start

/release 1.7.0                # full release: changelog + bump + commit + tag
/release 1.7.0 --dry-run      # show what would happen, change nothing
/release --check               # readiness validation only (GO/NO-GO)
/release                       # suggest version from commit analysis

---

Arguments

ArgumentRequiredDescription
versionNoSemver string (e.g., 1.7.0). If omitted, suggest based on commit analysis
--checkNoReadiness validation only — don't generate or write anything
--dry-runNoShow generated changelog + version bumps without writing
--skip-checksNoSkip pre-flight validation (tests, lint)
--changelog-onlyNoOnly update CHANGELOG.md — no version bumps, no commit, no tag

---

Modes

ModeInvocationBehavior
Full Release/release [version]Pre-flight → changelog → release notes → version bump → user review → write → release commit → tag → push guidance → exact-SHA CI verification.
Check/release --checkPre-flight checks only; reports GO/NO-GO. Composable with /validate. No writes.
Changelog Only/release X.Y.Z --changelog-onlyUpdates CHANGELOG.md only — no version bumps, no commit, no tag.

---

Workflow

Read references/release-workflow-detail.md for the full per-step procedure — bash commands, check tables, expected output, audit-record template, and worked examples. The index below is for orientation only; the agent must execute against release-workflow-detail.md for correctness.

  1. Pre-flight — run scripts/ci-local-release.sh (blocking) plus version/lint/test/branch/changelog/SBOM/security checks. --check mode stops after this step.
  2. Determine range — <last-tag>..HEAD. For non-HEAD cuts, see references/release-cut-and-bump.md.
  3. Read git history — git log --oneline --no-merges <range> plus stats for ambiguity resolution.
  4. Classify and group — Added / Changed / Fixed / Removed for CHANGELOG.md. Notes prose uses the richer 8-label set per references/release-notes.md.
  5. Suggest version — major if breaking, minor if features, patch if only fixes. Confirm via AskUserQuestion.
  6. Generate changelog entry — Keep-a-Changelog format, today's date, style-matched to the most recent existing entry.
  7. Detect and offer version bumps — generic patterns (package.json, pyproject.toml, etc.) plus AgentOps-specific manifests per references/release-cut-and-bump.md.
  8. User review — show generated changelog and version diffs; AskUserQuestion to proceed. --dry-run stops here.
  9. Write changes — CHANGELOG.md update + version file edits.
  10. Generate release notes — curated docs/releases/YYYY-MM-DD-v<version>-notes.md per references/release-notes.md. MUST be staged before the release commit.
  11. Write audit trail — docs/releases/YYYY-MM-DD-v<version>-audit.md resolved via scripts/resolve-release-artifacts.sh. Format in workflow-detail Step 16.
  12. Release commit — git commit -m "Release v<version>" with all release artifacts staged.
  13. Tag — annotated git tag -a v<version> -m "Release v<version>".
  14. GitHub Release (CI handles this) — do NOT gh release create locally; GoReleaser is sole creator.
  15. Post-push exact-SHA CI verification — after the operator pushes, run scripts/verify-release-ci.sh v<version> and ao reconcile --json; do not declare the release complete until exact-SHA verification prints GO release-ci and reconciliation shows the latest release tag Validate as green or a newer tag explicitly supersedes an older failed tag.
  16. Post-release guidance — show push commands and the verification command; do NOT push.
  17. Audit trail format — see workflow-detail for the markdown template.

---

Boundaries

What this skill does

  • Pre-flight validation (tests, lint, clean tree, versions, branch)
  • Changelog generation from git history
  • Semver suggestion from commit classification
  • Version string bumps in package files
  • Release commit + annotated tag
  • Release notes (highlights + changelog) for GitHub Release page
  • Curated release notes for CI to publish on GitHub Release page
  • Post-release guidance plus exact-SHA CI verification instructions
  • Audit trail

What this skill does NOT do

  • No publishing — no npm publish, cargo publish, twine upload. CI handles this.
  • No building — no go build, npm pack, docker build. CI handles this.
  • No pushing — no git push, no git push --tags. The user decides when to push.
  • No CI triggering — the tag push (done by the user) triggers CI.
  • No monorepo multi-version — one version, one changelog, one tag. Scope for v2.

Everything this skill does is local and reversible:

  • Bad changelog → edit the file
  • Wrong version bump → git reset HEAD~1
  • Bad tag → git tag -d v<version>
  • Bad release notes → edit docs/releases/*-notes.md before push

---

Universal Rules

  • Don't invent — only document what git log shows
  • No commit hashes in the final output
  • No author names in the final output
  • Concise — one sentence per bullet, technical but readable
  • Adapt, don't impose — match the project's existing style rather than forcing a particular format
  • User confirms — never write without showing the draft first
  • Local only — never push, publish, or trigger remote actions
  • Not done at tag — after the user pushes, verify a green validate.yml run for the exact tagged SHA, run ao reconcile --json, and record the run id, conclusion, reconciliation overall status, and release-tag finding state in the handoff or release audit notes.
  • Supersede historical red tags deliberately — do not hand-wave an older failed tag Validate run. Either fix/rerun the tag pipeline when appropriate or cut a newer release tag whose ao reconcile release evidence is green.
  • Two audiences — CHANGELOG.md is for contributors (file paths, issue IDs, implementation detail). Release notes are for feed readers (plain English, user-visible impact, no insider jargon). Never copy-paste the changelog into the release notes.

---

Examples

User says: /release 1.7.0 Agent runs pre-flight → reads v1.6.0..HEAD git history → classifies commits → drafts CHANGELOG.md entry + curated release notes → detects version files (package.json, version.go, plugin manifests) → presents draft for review → on approval, writes files, creates release commit, creates annotated tag, prints push guidance, then after the user pushes verifies scripts/verify-release-ci.sh v1.7.0, runs ao reconcile --json, and records the run id/conclusion plus reconciliation state.

User says: /release --check Agent runs all pre-flight checks and outputs a GO/NO-GO summary table. No writes.

User says: /release (no version) Agent classifies commits and suggests a version (major if breaking, minor if features, patch if fixes only) with reasoning, then asks the user to confirm or override.

User says: /release 1.7.0 --dry-run Agent shows what the changelog entry + version bumps would look like, then stops without writing.

See references/release-workflow-detail.md for the full per-step example narration.

Troubleshooting

ProblemCauseSolution
"No commits since last tag" errorWorking tree clean, no new commitsCommit pending changes or skip release
Version mismatch warningpackage.json and go version disagreeManually sync before release, or pick one as source of truth
Tests fail during pre-flightBreaking change not caught earlierFix tests, or use --skip-checks (not recommended)
Dirty working tree warningUncommitted changes presentCommit or stash before release
GitHub Release page body is emptyGoReleaser conflict with existing draftCI deletes existing releases before GoReleaser runs; do NOT gh release create locally
ci-local-release.sh hangs on agents-hash~/.agents/patterns is largeSet AGENTS_HUB_OVERRIDE=/tmp/empty-hub before invocation

See references/release-workflow-detail.md for the full troubleshooting matrix.

See Also

  • security — Dependency audit and vulnerability scanning (absorbs deps)

When wiring or auditing the CI workflow that backs --check mode (or the tag-triggered release pipeline that consumes the curated notes), pull the relevant patterns from references/gh-actions-ci-patterns.md (general CI) or references/gh-actions-release-automation.md (tag-triggered, draft flow, asset upload). When generating the curated release-notes file or auditing CHANGELOG.md drift, treat the changelog as an orientation layer and use references/changelog-as-research-artifact.md for the structured-section, breaking-change-callout, and notes-vs-changelog rules.

Reference Documents

  • references/release-workflow-detail.md — full per-step procedure
  • references/release-cut-and-bump.md — non-HEAD cut + AgentOps-specific bump targets
  • references/release-notes.md — curated notes format + product-area taxonomy
  • references/release-preflight-and-publishers.md
  • references/release-cadence.md
  • references/changelog-as-research-artifact.md
  • references/gh-actions-ci-patterns.md
  • references/gh-actions-release-automation.md
  • references/release.feature — Executable spec: --check readiness, curated notes + CHANGELOG reconcile, operator-performed tag/push, exact-SHA green verification (soc-qk4b)

Score

0–100
55/ 100

Grade

C

Popularity15/30

859 installs — growing adoption.

Completeness19/30

Documented: full SKILL.md body, one-line install. Missing: description, category/license metadata.

Trust15/25

Community skill with a public GitHub source repository you can review.

Freshness6/15

No update timestamp is tracked for this skill in our catalog.

Scored automatically from popularity, completeness, trust, and freshness — computed only from data in our catalog, never fabricated.

Proud of your score? Add this badge to your README.

Paste a snippet into your GitHub README. The badge updates automatically and links back to this page.

Release skill score badge previewScore badge

Markdown

[![Release skill](https://www.claudemarket.ai/skills/boshu2/agentops/release/badges/score.svg)](https://www.claudemarket.ai/skills/boshu2/agentops/release)

HTML

<a href="https://www.claudemarket.ai/skills/boshu2/agentops/release"><img src="https://www.claudemarket.ai/skills/boshu2/agentops/release/badges/score.svg" alt="Release skill"/></a>

Release FAQ

How do I install the Release skill?

Run “npx skills add https://github.com/boshu2/agentops --skill release” in your terminal. The skill is added to your agent's skills directory and picked up automatically on the next run — no restart or extra configuration needed.

What does the Release skill do?

Run release validation. The full SKILL.md on this page shows the exact instructions the skill gives your agent.

Is the Release skill free?

Yes. Release is a free, open-source skill published from boshu2/agentops. As with any third-party skill, review the source repository before installing it into an agent with sensitive access.

Does Release work with Claude Code and OpenClaw?

Yes. Skills use the portable SKILL.md format, so Release works with Claude Code, OpenClaw, Codex, Hermes, and any other agent that reads SKILL.md skills.

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free →
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free →
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off
Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed
Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off
Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw
Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.
Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams
Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit
Try DataForSEO free →
Reach 47,000+ AI builders
Advertise here →
View on GitHub

Recommended skills

Browse all →
find-skills logo

find-skills

vercel-labs/skills

2.8M installsInstall
frontend-design logo

frontend-design

anthropics/skills

731K installsInstall
grill-me logo

grill-me

mattpocock/skills

727K installsInstall
grill-with-docs logo

grill-with-docs

mattpocock/skills

616K installsInstall
agent-browser logo

agent-browser

vercel-labs/agent-browser

612K installsInstall
vercel-react-best-practices logo

vercel-react-best-practices

vercel-labs/agent-skills

599K installsInstall

Related guides

Hand-picked reading to help you choose, install, and use agent skills.

GuideBest Openclaw Skills 2026GuideHow To Evaluate Openclaw Skill Before InstallingGuideOpenclaw Skills Complete Guide

Skills by category

FrontendBackend & APIsTesting & QASecurityDevOps & CI/CDMCP & ToolingAutomationData & Analysis+20 more

MCP servers by category

AI & MLDeveloper ToolsVector & MemoryFiles & DocsDatabasesFinance & PaymentsBrowser & ScrapingCommunication+8 more

Marketplaces by category

developmentproductivitycommunicationdesignsecuritydatabaseworkflowcompliance+34 more

Claude Market

AI agent skills directory, marketplace, and workflow hub for OpenClaw, Hermes Agent, Claude Code, Codex, and MCP-powered operator stacks.

Independent project, not affiliated with Anthropic.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Plugins

More

  • Submit a Tool
  • Advertise
  • Free Tools
  • API
  • Shipping
  • Contact
  • Terms
  • Privacy

Know a company that should advertise here? Refer them and earn 10% — up to $300 per referral.

© 2026 Claude Market
Fazier badgeFeatured on Twelve ToolsFeatured on Wired BusinessRemote OpenClaw - Featured on AI Agents DirectoryListed on Turbo0Featured on Uneed