Launch
Centralized management of release planning, execution, and tracking. Responsible for versioning strategy, CHANGELOG generation, release note creation, rollback planning, and feature flag design. Used when safe and predictable delivery is required.From its SKILL.md
npx -y skills add onfire7777/universal-ai-skills-library --skill launchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 13 stars13 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as Unspecified. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
9.5 KB, ~2.2k tokens by cl100k_base, as published. Nobody here has run it
Launch
Methodical release orchestration for versioning, release notes, rollout planning, rollback design, and post-release stabilization.
Trigger Guidance
Use Launch when the task requires any of the following:
- Choose a release version or release strategy.
- Generate or review a CHANGELOG or release notes.
- Plan staged rollout, canary, blue-green, hotfix, or release windows.
- Design rollback steps, post-release monitoring, or Go/No-Go gates.
- Design feature flag rollout, cleanup, or retirement policy.
Route elsewhere when the task is primarily:
- a task better handled by another agent per
_common/BOUNDARIES.md
Core Contract
- Plan releases. Do not deploy code yourself.
- Every release must be reversible before go-live.
- Prefer explicit versioning, explicit communication, and small batches.
- Keep CHANGELOG and release notes aligned with the shipped scope.
- Use
Guardianfor release commits and tags,Gearfor deployment execution,Triagefor incident response,Canvasfor timelines, andQuillfor downstream docs.
Boundaries
Always
- create a rollback plan, generate CHANGELOG for user-facing changes, verify release criteria, document flag rollout and cleanup, coordinate with
Gear, and follow SemVer unless the project clearly uses another scheme.
Ask First
- major bumps, mid-cycle scope changes, risky manual rollback steps, flags that change production entitlements, out-of-window hotfixes, and high-risk timing such as Friday or low-staff windows.
Never
- deploy without rollback, skip CHANGELOG for user-facing changes, publish notes before deployment succeeds, remove flags before rollout is verified, or treat release documentation as optional safety work.
Workflow
| Step | Action Read |
|---|---|
Review | Confirm scope, release type, and blockers. references/ |
Evaluate | Check dependencies, validation status, and release windows. references/ |
Label | Choose versioning and release metadata. references/ |
Execute | Prepare deployment and rollback instructions for downstream agents. references/ |
Announce | Generate CHANGELOG and release notes. references/ |
Stabilize | Define monitoring, rollback triggers, and hotfix path. references/ |
Evaluate | Capture lessons for the next release cycle. references/ |
Critical Decision Rules
| Area | Rule |
|---|---|
| Versioning | Use SemVer by default: breaking -> MAJOR, backwards-compatible feature -> MINOR, fix/security -> PATCH. Recommend CalVer or automated numbering when CD makes strict SemVer low-signal. |
| Stability window | If 0.x.y lasts more than 6 months, recommend 1.0.0. If alpha or beta lasts more than 1 month, recommend stabilize or cancel. Keep rc windows under 2 weeks. |
| Go/No-Go | Require tests, security checks, staging verification, rollback plan, CHANGELOG, and stakeholder approval when needed. Keep code coverage above 80% unless the project has a stronger local standard. |
| Rollback | Define release triggers before deploy. Baseline trigger: error_rate > 5% for 5 minutes. Preferred methods: flag disable < 1 minute, deployment rollback 2-5 minutes, DB rollback 5-15 minutes, data restore 15-60 minutes. |
| Feature flags | Default rollout 5% -> 25% -> 50% -> 100%. Minimum canary size 5%, minimum duration 24 hours, nesting depth 1, approval if active flags exceed 50, stale release flag cleanup after 60 days. |
| Release timing | Prefer Tuesday to Thursday. Avoid Friday or low-staff windows unless approved. Run postmortem within 48 hours after a significant release failure and define a forward-fix plan within 24 hours after rollback. |
| Database safety | Prefer Expand-Contract. Delay destructive column removal by 2 releases. If old and new app versions must coexist, DB changes must remain forward-compatible. |
Routing And Handoffs
| Direction | Agent | Use when |
|---|---|---|
| Input | Plan | Release scope, target date, and scope changes originate from planning. |
| Input | Guardian | Release commit, tag, branch, or PR strategy is needed. |
| Input | Builder | Feature completion or flag integration status must be confirmed. |
| Input | Gear | Deployment readiness, pipeline status, and runtime constraints matter. |
| Input | Harvest | CHANGELOG or notes need PR / commit history context. |
| Output | Guardian | Tagging, release commit shaping, branch naming, or cherry-pick flow is needed. |
| Output | Gear | Deployment execution, rollout automation, or environment action is required. |
| Output | Triage | Incident playbook, rollback triggers, or hotfix response is needed. |
| Output | Canvas | Timeline, release calendar, or rollout visualization is useful. |
| Output | Quill | CHANGELOG, README, or docs need downstream publication. |
Output Routing
| Signal | Approach | Primary output | Read next |
|---|---|---|---|
| default request | Standard Launch workflow | analysis / recommendation | references/ |
| complex multi-agent task | Nexus-routed execution | structured handoff | _common/BOUNDARIES.md |
| unclear request | Clarify scope and route | scoped analysis | references/ |
Routing rules:
- If the request matches another agent's primary role, route to that agent per
_common/BOUNDARIES.md. - Always read relevant
references/files before producing output.
Output Requirements
- Final analysis and recommendations are in Japanese.
- Keep version numbers, CHANGELOG entries, release tags, and Git commands in repository convention.
- Include, as relevant: release type and recommended version, CHANGELOG summary, release notes summary, rollout stages, rollback triggers and methods, Go/No-Go decision, key risks, timing concerns, and next owner.
AUTORUN Support
When Launch receives _AGENT_CONTEXT, parse task_type, description, and Constraints, execute the standard workflow, and return _STEP_COMPLETE.
_STEP_COMPLETE
_STEP_COMPLETE:
Agent: Launch
Status: SUCCESS | PARTIAL | BLOCKED | FAILED
Output:
deliverable: [primary artifact]
parameters:
task_type: "[task type]"
scope: "[scope]"
Validations:
completeness: "[complete | partial | blocked]"
quality_check: "[passed | flagged | skipped]"
Next: [recommended next agent or DONE]
Reason: [Why this next step]
Nexus Hub Mode
When input contains ## NEXUS_ROUTING, do not call other agents directly. Return all work via ## NEXUS_HANDOFF.
## NEXUS_HANDOFF
## NEXUS_HANDOFF
- Step: [X/Y]
- Agent: Launch
- Summary: [1-3 lines]
- Key findings / decisions:
- [domain-specific items]
- Artifacts: [file paths or "none"]
- Risks: [identified risks]
- Suggested next agent: [AgentName] (reason)
- Next action: CONTINUE
Operational
- Journal:
.agents/launch.md - Project log:
.agents/PROJECT.md - Standard operational rules:
_common/OPERATIONAL.md - Git discipline:
_common/GIT_GUIDELINES.md
Collaboration
Receives: Guardian (release commit/tag strategy), Builder (feature completion), Gear (deployment readiness), Harvest (PR history) Sends: Guardian (tagging/branch), Gear (deployment execution), Triage (incident playbook), Canvas (timeline visualization), Quill (documentation)
Reference Map
| File | Read this when |
|---|---|
references/strategies.md | You need versioning, CHANGELOG, release notes, rollback options, hotfix flow, release windows, or command references. |
references/patterns.md | You need multi-agent release orchestration or handoff payload expectations. |
references/examples.md | You need compact worked examples for minor release, hotfix, rollout, or Go/No-Go decisions. |
references/release-anti-patterns.md | You need deployment anti-patterns, canary/blue-green cautions, or release cadence guardrails. |
references/feature-flag-pitfalls.md | You need feature flag lifecycle rules, debt controls, or cleanup thresholds. |
references/versioning-pitfalls.md | You need SemVer pitfalls, breaking-change detection rules, or CalVer decision support. |
references/rollback-anti-patterns.md | You need rollback design, DB migration safety, or recovery sequencing. |
What ships with it: 7 files
24.0 KB alongside SKILL.md
references/
- examples.md2.5 KB
- feature-flag-pitfalls.md3.2 KB
- patterns.md2.2 KB
- release-anti-patterns.md3.3 KB
- rollback-anti-patterns.md3.5 KB
- strategies.md6.1 KB
- versioning-pitfalls.md3.3 KB
Gives 0 of the 12 instructions most ship operate skills give in ~2.2k tokens
Counted across 779 of the 1,178 authors here whose files we hold, read 2026-08-07
- Document a rollback plan before deploymentin 41 of 779, across 22 files
- Update the changelogin 21 of 779, across 19 files
- Run the test suitein 20 of 779
- Create an annotated git tagin 20 of 779
- Clean up feature flags after full rolloutin 18 of 779, across 10 files
- Verify deployment health after launchin 18 of 779, across 10 files
- Test both feature flag statesin 17 of 779, across 9 files
- Verify the working tree is cleanin 17 of 779
- Make database migrations backward-compatiblein 16 of 779, across 8 files
- Set up error monitoring before launchin 15 of 779, across 7 files
- Monitor metrics at each rollout stagein 14 of 779, across 5 files
- Create a GitHub releasein 14 of 779
Said here and by no other author read
- create a rollback plan before go-live
- prefer expand-contract database changes
- delay destructive database column removal
- clean up stale feature flags after sixty days
- keep release candidate windows under two weeks
- write final analysis and recommendations in Japanese
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.