Agent skill

Release

by parcadei in parcadei/Continuous-Claude-v3

Release preparation workflow - security audit → E2E tests → review → changelog → docs

MITAuto-check passedDevelopment

Install Release

skills CLI
$ npx skills add parcadei/Continuous-Claude-v3 --skill release -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install parcadei/Continuous-Claude-v3 release --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/release .claude/skills/release && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
release
GitHub stars
3.9k
Used in
1 other repo
Token cost
~1.3k tokens
SKILL.md length
190 words
Files
1
Skills in repo
141
Repo updated
First seen
Licence
MIT

At a glance

Release preparation workflow - security audit → E2E tests → review → changelog → docs

  • Works in 5 steps: Security Audit → E2E Tests → Final Review → …
  • Tasks that involve Changelog and release notes
  • SKILL.md covers When to Use, Workflow Overview, Agent Sequence and Why This Order?, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Release is an agent skill from parcadei/Continuous-Claude-v3. Release preparation workflow - security audit → E2E tests → review → changelog → docs

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Changelog and release notes, End-to-end testing and Security review. The repository describes itself as: Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows. The licence is MIT.

When your agent uses it

  • Tasks that involve Changelog and release notes
  • Tasks that involve End-to-end testing
  • Tasks that involve Security review

Example prompts

  • “/release”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Security Audit
  2. E2E Tests
  3. Final Review
  4. Version Bump & Changelog
  5. Release Notes

What it can do on your machine

Read from SKILL.md and the folder at commit d07ff4b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Release loads about 1.3k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 190 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from parcadei/Continuous-Claude-v3 at commit d07ff4b, republished under its MIT licence (© parcadei). 190 words, ~1,294 tokens.

Download SKILL.mdSave it as .claude/skills/release/SKILL.md (or your agent's skills folder).
name
release
description
Release preparation workflow - security audit → E2E tests → review → changelog → docs

/release - Release Workflow

Structured release preparation to ship with confidence.

When to Use

  • "Prepare a release"
  • "Ship version X"
  • "Release to production"
  • "Cut a release"
  • "Ready to deploy"
  • Before any production deployment

Workflow Overview

┌─────────┐    ┌─────────┐    ┌──────────────┐    ┌──────────┐    ┌─────────┐
│  aegis  │───▶│  atlas  │───▶│ review-agent │───▶│  herald  │───▶│  scribe │
│         │    │         │    │              │    │          │    │         │
└─────────┘    └─────────┘    └──────────────┘    └──────────┘    └─────────┘
  Security       E2E            Final              Version         Release
  audit          tests          review             bump            notes

Agent Sequence

#AgentRoleOutput
1aegisSecurity vulnerability scanSecurity report
2atlasRun full E2E test suiteTest report
3review-agentFinal release reviewRelease approval
4heraldVersion bump, changelog generationUpdated version files
5scribeRelease notes, documentationRELEASE.md, docs

Why This Order?

  1. Security first: Catch vulnerabilities before they ship
  2. E2E tests: Verify full system works end-to-end
  3. Final review: Human-in-the-loop approval
  4. Version bump: Only after approval
  5. Documentation: Ship with proper release notes

Execution

Phase 1: Security Audit
Task(
  subagent_type="aegis",
  prompt="""
  Security audit for release: [VERSION]

  Scan for:
  - Dependency vulnerabilities (npm audit, pip audit)
  - Hardcoded secrets/credentials
  - SQL injection, XSS, CSRF risks
  - Authentication/authorization issues
  - Insecure configurations

  Output: Security report with severity levels
  """
)
Phase 2: E2E Tests
Task(
  subagent_type="atlas",
  prompt="""
  Run E2E tests for release: [VERSION]

  Execute:
  - Full E2E test suite
  - Critical path tests
  - Integration tests
  - Performance benchmarks (if applicable)

  Output: Test report with pass/fail counts
  """
)
Phase 3: Final Review
Task(
  subagent_type="review-agent",
  prompt="""
  Final release review: [VERSION]

  Review:
  - Security audit results
  - E2E test results
  - Changes since last release (git log)
  - Breaking changes
  - Migration requirements

  Output: RELEASE_APPROVED or RELEASE_BLOCKED with reasons
  """
)
Phase 4: Version Bump & Changelog
Task(
  subagent_type="herald",
  prompt="""
  Prepare release: [VERSION]

  Tasks:
  - Bump version in package.json/pyproject.toml
  - Generate CHANGELOG.md entry
  - Update version constants in code
  - Tag commit (don't push yet)

  Follow semantic versioning.
  """
)
Phase 5: Release Notes
Task(
  subagent_type="scribe",
  prompt="""
  Write release notes: [VERSION]

  Include:
  - Summary of changes
  - New features
  - Bug fixes
  - Breaking changes
  - Migration guide (if needed)
  - Contributors

  Output: RELEASE.md or update docs
  """
)

Release Types

Major Release (Breaking Changes)
/release --major
→ Full workflow with migration guide
Minor Release (New Features)
/release --minor
→ Full workflow, lighter security review
Patch Release (Bug Fixes)
/release --patch
→ Security + tests + quick review
Hotfix
/release --hotfix
→ Expedited: aegis → atlas → herald

Example

User: /release v2.0.0

Claude: Starting /release workflow for v2.0.0...

Phase 1: Security audit...
[Spawns aegis]
✅ No critical vulnerabilities
⚠️ 2 low-severity issues (documented)

Phase 2: E2E tests...
[Spawns atlas]
✅ 156/156 E2E tests passing

Phase 3: Final review...
[Spawns review-agent]
✅ RELEASE_APPROVED
- 47 commits since v1.9.0
- 3 new features
- 12 bug fixes
- No breaking changes

Phase 4: Version bump...
[Spawns herald]
✅ Version bumped to 2.0.0
✅ CHANGELOG.md updated
✅ Git tag created

Phase 5: Release notes...
[Spawns scribe]
✅ RELEASE-v2.0.0.md created

┌─────────────────────────────────────────┐
│ Release v2.0.0 Ready                    │
├─────────────────────────────────────────┤
│ Security: ✅ Passed                     │
│ Tests: ✅ 156/156                       │
│ Review: ✅ Approved                     │
│                                         │
│ Next steps:                             │
│ 1. git push origin v2.0.0              │
│ 2. Create GitHub release               │
│ 3. Deploy to production                │
└─────────────────────────────────────────┘

Blockers

The workflow stops if:

  • Critical security vulnerability found
  • E2E tests failing
  • Review verdict is RELEASE_BLOCKED
Phase 1: Security audit...
❌ CRITICAL: SQL injection in user.py:45

Release blocked. Fix critical issues before proceeding.

Flags

  • --major/--minor/--patch: Semantic version type
  • --hotfix: Expedited release path
  • --skip-security: Skip security audit (not recommended)
  • --dry-run: Run checks without bumping version

© parcadei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/release of parcadei/Continuous-Claude-v3.

Open the folder on GitHubat commit d07ff4b

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in parcadei/Continuous-Claude-v3, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Release next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Release compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Release this skillparcadei/Continuous-Claude-v33.9k1 repos~1.3kAutomated safety check: PassMIT
Dependency Update BotVarnan-Tech/opendirectory674—~3kAutomated safety check: NotesMIT
Openiap Workflowshyodotdev/openiap154—~2kAutomated safety check: PassMIT
Tag Releasevfarcic/dot-agent-deck109—~5.6kAutomated safety check: PassMIT
Security UpdatesSmilyOrg/photofield608—~808Automated safety check: PassMIT
Release CLIheygen-com/heygen-cli145—~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Dependency Update Bot

    Varnan-Tech/opendirectory

    Scans your project for outdated npm, pip, Cargo, Go, or Ruby packages.

    674 GitHub stars~3k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes
  • Openiap Workflows

    hyodotdev/openiap

    A skill your agent uses for OpenIAP monorepo work that should follow the repository's shared agent workflows, including review-pr, audit-code, audit-security, audit-iapkit, compile-knowledge…

    154 GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Tag Release

    vfarcic/dot-agent-deck

    Cut a release from the accumulated changelog fragments by dispatching the Tag Release workflow, then clean up what working sessions left behind.

    109 GitHub stars~5.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Security Updates

    SmilyOrg/photofield

    Check and apply security updates across the photofield project (api/Go, ui/npm, docs/npm, e2e/npm).

    608 GitHub stars~808 tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Release CLI

    heygen-com/heygen-cli

    Cut a stable (or dev) release of the heygen CLI end to end: run RELEASE.md's pre-release checklist, land pending PRs, check the command surface, run E2E, pick the version, write the changelog…

    145 GitHub stars~1.9k tokensUpdated today
    Testing & QAAuto-check passed
  • Create GitHub PR

    openJiuwen-ai/sciencediscovery

    Open or update a pull request on GitHub's openJiuwen-ai/sciencediscovery: run the UT/ST/E2E layers locally, push the branch to the operator's own GitHub fork, write a body that says what was…

    151 GitHub stars~3k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from parcadei/Continuous-Claude-v3

All 141 skills in this repo
  • Tldr Deep

    parcadei/Continuous-Claude-v3

    Full 5-layer analysis of a specific function. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 2 repos~677 tokens
    Auto-check passed
  • Compound Learnings

    parcadei/Continuous-Claude-v3

    Transform session learnings into permanent capabilities (skills, rules, agents).

    3.9k GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check: notes
  • Gradient Methods

    parcadei/Continuous-Claude-v3

    Problem-solving strategies for gradient methods in optimization

    3.9k GitHub starsUsed in 3 repos~1k tokens
    Auto-check: notes
  • Debug Hooks

    parcadei/Continuous-Claude-v3

    Systematic hook debugging workflow. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 1 repo~863 tokens
    Auto-check: notes
  • Math

    parcadei/Continuous-Claude-v3

    Unified math capabilities - computation, solving, and explanation.

    3.9k GitHub starsUsed in 3 repos~1.6k tokens
    Auto-check: notes
  • Math Model Selector

    parcadei/Continuous-Claude-v3

    Routes problems to appropriate mathematical frameworks using expert heuristics

    3.9k GitHub starsUsed in 3 repos~841 tokens
    Auto-check passed

Questions about Release

What does Release do?

Release preparation workflow - security audit → E2E tests → review → changelog → docs. Release is an agent skill from parcadei/Continuous-Claude-v3.

When should I use Release?

Release fits situations like: tasks that involve Changelog and release notes; tasks that involve End-to-end testing; tasks that involve Security review.

How do I install Release in Claude Code?

Run `npx skills add parcadei/Continuous-Claude-v3 --skill release -a claude-code`. Or copy the skill folder (.claude/skills/release in parcadei/Continuous-Claude-v3) into .claude/skills/release in your project. Claude Code loads it when a task matches its description.

How do I install Release in Codex?

Run `npx skills add parcadei/Continuous-Claude-v3 --skill release -a codex`. Or copy the skill folder (.claude/skills/release in parcadei/Continuous-Claude-v3) into .agents/skills/release in your project. Codex loads it when a task matches its description.

Can I use Release in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add parcadei/Continuous-Claude-v3 --skill release -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/release, .gemini/skills/release, .github/skills/release and .opencode/skills/release in your project.

What does Release need to run?

SKILL.md names no scripts, command-line tools or credentials: Release is instructions for the agent only.

Does Release access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Release safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Release use?

Release is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Release use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Release?

Skills that share tags, products or a category with Release: Dependency Update Bot (Varnan-Tech/opendirectory, 674 stars), Openiap Workflows (hyodotdev/openiap, 154 stars), Tag Release (vfarcic/dot-agent-deck, 109 stars) and Security Updates (SmilyOrg/photofield, 608 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Release?

parcadei (a GitHub user) maintains it in parcadei/Continuous-Claude-v3, which has 3,940 GitHub stars. The repository holds 141 skills in this directory. The repository was last updated on January 26, 2026.

Source: parcadei/Continuous-Claude-v3 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.