release
Orchestrates the release management and approval process.
Install
mkdir -p .claude/skills/release-adpigft && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13655" && unzip -o skill.zip -d .claude/skills/release-adpigft && rm skill.zipInstalls to .claude/skills/release-adpigft
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Prepare release readiness evidence, release notes, rollback, monitoring, risks, and approvals.Key capabilities
- →Confirm validation evidence and release scope.
- →Review CI, security, quality, operational, and deployment readiness evidence.
- →Define rollback approach, monitoring checks, and smoke tests.
- →Record known risks, limitations, and support handoff.
- →Prepare release notes or a release readiness summary.
How it works
The skill confirms validation evidence and scope, reviews various readiness proofs, defines operational procedures like rollback and monitoring, records risks, and then prepares a release readiness summary and notes.
Inputs & outputs
When to use release
- →Preparing release notes
- →Managing approval gates
- →Documenting release risks
About this skill
Release Skill
Purpose
Prepare release readiness evidence and make release blockers, risks, approvals, rollback, monitoring, and support needs explicit.
When To Use
Use $release when validated scope is ready for release readiness review or release management.
Inputs Needed
- Release scope
- Validation report and test evidence
- CI, build, security, quality, or deployment evidence
- Known risks, limitations, and waivers
- Rollback, monitoring, smoke test, and support notes
- Required approval references where available
Framework Adapter
When this skill is used inside this repository, context loading, artifact placement, approval gates, and lifecycle behavior are defined by:
framework/02-context-control/context/skill-context-adapter.mdframework/03-delivery-governance/artifact-placement-model.mdframework/01-lifecycle/skill-orchestration-adapter.md
Procedure
- Confirm validation evidence exists and does not block release.
- Confirm release scope and excluded scope.
- Review CI, security, quality, operational, and deployment readiness evidence.
- Define rollback approach, monitoring checks, smoke checks, known risks, and support handoff.
- Record release blockers or partial/non-production constraints when applicable.
- Prepare release notes or release readiness summary.
- Stop for required release approvals before claiming release approval.
Outputs Produced
- Release readiness summary
- Release notes or release package evidence
- Rollback and monitoring plan
- Known risks, limitations, and support handoff notes
- Approval checklist and blocker summary
Example Output
- Scope:
feature release - Status:
not ready - Blockers:
missing validation evidence
Artifact Structure
- Scope
- Changes Included
- Validation Evidence
- Deployment Approach
- Risks
- Rollback Plan
- Monitoring & Smoke Checks
- Approval Status
Quality Checks
- Validation evidence supports the release claim.
- CI, quality, and security gate status is visible.
- Rollback and monitoring are practical.
- Known risks and exclusions are explicit.
- Required approvers are identified.
- Release approval is not claimed without human approval.
Stop Conditions
- Validation says release is not ready.
- Release notes, CI/security/quality evidence, rollback, monitoring, or approval package is missing.
- Remaining slices or scope are not validated unless explicitly marked as partial/non-production release.
- Release evidence conflicts with validation or traceability.
Human Approval Expectations
PO, QA, Architect, DevSecOps, and any required operational owners must approve before production release.
Do Not
- Do not modify external systems unless explicitly approved.
- Do not create, update, delete, or transition Jira, Confluence, GitHub, Wynxx Story Creator, or source-code artifacts unless the skill explicitly allows it and the user approves.
- Do not expose secrets, tokens, credentials, or sensitive data.
- Do not fabricate missing requirements, evidence, source references, or approval status.
- Do not treat inferred content as confirmed fact.
- Do not bypass validation, traceability, approval, or stop-for-review rules.
- Do not execute releases.
- Do not create tags, deployments, or production changes.
- Do not claim release readiness without traceability and validation evidence.
Standard Response Format
Created/Updated:
- ...
Pending Review:
- ...
Blockers:
- ...
Next:
- ...
When not to use it
- →When the validated scope is not ready for release readiness review.
- →When the user wants to execute releases, create tags, deployments, or production changes.
Limitations
- →The skill does not execute releases, create tags, deployments, or production changes.
- →The skill does not claim release approval without human approval.
How it compares
This skill automates the aggregation and structured presentation of all necessary evidence and plans for release readiness, ensuring all critical aspects are covered before approval, which is more systematic than a manual checklist.
Compared to similar skills
release side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| release (this skill) | 0 | 2mo | No flags | Advanced |
| dev-release | 0 | 2mo | Review | Intermediate |
| agent-workflow-automation | 4 | 6mo | Review | Advanced |
| agent-project-board-sync | 0 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
dev-release
forecast-bio
Use to drive a guided release pipeline — version bump, changelog drafting, doc review, test/lint, PR creation, tag, GitHub release, and back-merge. Mixes agent steps (the agent does them) with user-only steps (push / merge / tag, blocked by policy and printed for the user). Trigger when the user say
agent-workflow-automation
ruvnet
Agent skill for workflow-automation - invoke with $agent-workflow-automation
agent-project-board-sync
ruvnet
Agent skill for project-board-sync - invoke with $agent-project-board-sync
project-os
Peiiii
AI project OS for autonomous loop, automated orchestration, and rule-driven execution.
project-tooling
alinaqi
gh, vercel, supabase, render CLI and deployment platform setup
release-version
corvo007
Use when releasing a new version - guides through version bump, changelog generation, commit grouping, tagging, and GitHub CI tracking. Triggers on "发布新版本", "release", "发版", or version release requests.