release
Use when preparing, validating, publishing, promoting, or recovering claude-code-router releases, including CI readiness, live E2E evidence…
Skill by hishamkaram
Chalk Labs
Need help deploying release?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hishamkaram-release
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, devops, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/release
What's inside
- Skill name
release- Description
- Use when preparing, validating, publishing, promoting, or recovering claude-code-router releases, including CI readiness, live E2E evidence, changelog/release-note updates, draft GitHub releases, GHCR browser images, and Homebrew promotion.
- License
- MIT
- Instructions
- 58 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: scripts/publish-homebrew-formula.sh
Files (7)
- SKILL.md
- openai.yaml · agents/
- acceptance-template.md · assets/
- pr-body-template.md · assets/
- release-notes-template.md · assets/
- gates.md · references/
- recovery.md · references/
SKILL.md (first lines)
# CCR Release Use this skill for version-neutral CCR release work. Keep claims tied to evidence; a skipped live gate is not a release pass. ## Required Reading Read these repo files before non-trivial release work: - `AGENTS.md` - `agents/_data/ai-agent-quality-contract.md` - `agents/_data/engineering-quality-gate.md` - `agents/_data/live-e2e-contract.md` - `agents/_data/router-product-invariants.md` - `agents/_data/cli-contract.md` - `agents/docs-updater.md` When changing release mechanics, also read: - `docs/releasing.md` - `.github/workflows/release.yml` - `.goreleaser.yaml` - `scripts/publish-homebrew-formula.sh` ## Workflow 1. Confirm the target version and scope. Use `vX.Y.Z` placeholders in reusable docs and the exact tag only in versioned release notes or acceptance files. 2. Update `CHANGELOG.md`, `docs/releases/vX.Y.Z.md`, and `docs/acceptance/vX.Y.Z.md`. Do not document unimplemented behavior as shipped. Wording may describe expected release behavior only when the acceptance checklist still requires evidence before publication. 3. Run local gates in the order described in `docs/releasing.md`. Read `references/gates.md` when deciding whether evidence is sufficient. 4. Tag only after the acceptance file records reproducible pre-tag evidence. 5. Let the tag workflow create a draft GitHub Release, checksums, provenance attestations, and signed GHCR browser image. Homebrew must wait. 6. Verify the draft release assets and image, then manually promote the release workflow. Promotion publishes GitHub Release and updates Homebrew. 7. Keep macOS helper wording source-built and unsigned; do not claim it is included in Homebrew, GoReleaser archives, signed, notarized, or hardened. 8. Append immutable post-publication evidence to the acceptance file. ## Recovery For partial draft/public release failures, read `references/recovery.md` before changing tags, releases, or Homebrew. Prefer idempotent reruns over manual mutation. ## Templates Use these assets when drafting release artifacts: - `assets/release-notes-template.md` - `assets/acceptance-template.md` - `assets/pr-body-template.md`
From hishamkaram/claude-code-router, MIT.
More from hishamkaram/claude-code-router
- 0.629score
cli-ux
hishamkaram
Use when designing or changing claude-code-router CLI commands, flags, validation, help text, onboarding, provider/model setup, doctor output, or error…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
docs-updater
hishamkaram
Use when updating claude-code-router README, CLI help text, examples, command docs, compatibility docs, live E2E docs, or release notes.
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
go-concurrency
hishamkaram
Use when implementing or reviewing concurrent Go code in claude-code-router, especially HTTP/SSE streams, provider requests, sessions, goroutines…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
go-implementer
hishamkaram
Use when implementing Go code in claude-code-router, including CLI commands, SQLite storage, secret handling, gateway code, provider adapters, sessions, and…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
live-e2e
hishamkaram
Use when adding, running, or reviewing live Claude Code E2E tests for claude-code-router model switching, gateway routing, tools, subagents, workflows…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
research
hishamkaram
Use when researching current Claude Code, Anthropic, OpenRouter, LiteLLM, OpenAI, vLLM, or provider protocol behavior for claude-code-router without…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
router-architect
hishamkaram
Use when designing or reviewing claude-code-router gateway architecture, provider boundaries, SQLite schema, compatibility policy, model switching, or Claude…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
security-auditor
hishamkaram
Use when handling or reviewing claude-code-router provider API keys, auth headers, local gateway exposure, secret redaction, logs, traces, SQLite storage, or…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
go-test-writer
hishamkaram
Use when writing tests for claude-code-router, including CLI tests, SQLite tests, fake provider tests, conformance tests, and live Claude Code E2E tests.
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
go-reviewer
hishamkaram
Use when reviewing Go code in claude-code-router for interfaces, errors, secrets, CLI validation, SQLite behavior, concurrency, tests, and live E2E coverage.
SkillAFreshness: A★ 12Claude Code +9
Signals
- Stars
- 12
- Forks
- 5
- Open issues
- 0
- Last commit (this folder)
- Oct 6, 2026 (25 days ago)
- Last release
- Oct 15, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hishamkaram
- 0.629score
cli-ux
hishamkaram
Use when designing or changing claude-code-router CLI commands, flags, validation, help text, onboarding, provider/model setup, doctor output, or error…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
docs-updater
hishamkaram
Use when updating claude-code-router README, CLI help text, examples, command docs, compatibility docs, live E2E docs, or release notes.
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
go-concurrency
hishamkaram
Use when implementing or reviewing concurrent Go code in claude-code-router, especially HTTP/SSE streams, provider requests, sessions, goroutines…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
go-implementer
hishamkaram
Use when implementing Go code in claude-code-router, including CLI commands, SQLite storage, secret handling, gateway code, provider adapters, sessions, and…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
live-e2e
hishamkaram
Use when adding, running, or reviewing live Claude Code E2E tests for claude-code-router model switching, gateway routing, tools, subagents, workflows…
SkillAFreshness: A★ 12Claude Code +9 - 0.629score
research
hishamkaram
Use when researching current Claude Code, Anthropic, OpenRouter, LiteLLM, OpenAI, vLLM, or provider protocol behavior for claude-code-router without…
SkillAFreshness: A★ 12Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get release running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
release skill. Agent Mart. https://agentmart.dev/skills/hishamkaram-release (last updated 2026-10-24)