shipping-a-release
Use when implementation is complete and the user explicitly asks to wrap up, ship, release, merge, or publish the work.
Skill by Roflochinsky
Chalk Labs
Need help deploying shipping-a-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/roflochinsky-shipping-a-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
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. 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/shipping-a-release
What's inside
- Skill name
shipping-a-release- Description
- Use when implementation is complete and the user explicitly asks to wrap up, ship, release, merge, or publish the work. Never self-initiate a release.
- License
- MIT
- Instructions
- 57 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Shipping a Release ## Overview Completion is an agent's blind spot: work stranded on branches, versions guessed, changelogs forgotten, "shipped" claimed while CI is still running. This is a checklist pipeline — run it top to bottom, only on the user's explicit ask. Copy this checklist and check items off as you go: ``` Ship Progress: - [ ] 1. Verification AFTER the last edit - [ ] 2. Diff review - [ ] 3. Version + changelog per repo convention - [ ] 4. Commit (explicit paths) - [ ] 5. PR / merge through CI - [ ] 6. Honest status report ``` ## 1. Verification after the LAST edit A green run before your latest edits proves nothing. Re-run now: full test suite, lint/typecheck, build, and the project's mandatory verification block if CLAUDE.md defines one. Then **run the actual app and observe the shipped feature working** (use the project's run skill / `verify`) — unit tests passing is not the feature working. If anything fails: stop, fix, re-run. "Ship broken fast" is never an option. ## 2. Diff review `git diff` against the base branch, looking for: debug leftovers, accidental files, secrets, unrelated changes. If the diff is more than trivial, dispatch a fresh-context reviewer sub-agent (superpowers:requesting-code-review) — a 60-second self-skim under time pressure is how bugs ship. ## 3. Version + changelog — by convention, not by guess Check how THIS repo versions: `git tag -l | tail`, recent release commits, CHANGELOG format, release config (semantic-release, changesets, etc.). If tooling automates versioning — don't fight it. If manual: bump per semver from the actual change type, add the changelog entry for this release only (don't backfill history silently — note it as follow-up). ## 4. Commit Explicit paths (`git add <files>`), never `-A` blindly. Message per repo convention (check `git log`). Reference the issue it closes. ## 5. PR / merge — CI is the gate - Push the branch; create a PR with real context: what, why, how verified, what's deferred. - **Never bypass CI**, never force-merge, never push directly to a deploy branch to save time. If the user is leaving: arm auto-merge (`gh pr merge --auto`) so it lands when checks pass. - Force-push or rebase of published commits — only with the user's explicit OK. ## 6. Honest status report - CI green and merged → "shipped". - Auto-merge armed, CI running → "queued to ship", NOT "shipped". Never claim a deploy you haven't observed. - Report: what shipped, verification evidence, corners explicitly cut (and they must be named), follow-ups filed in the tracker. ## Red flags — you are rationalizing | Thought | Reality | |---|---| | "Tests were green 10 minutes ago" | Before your last edits = unknown state. Re-run. | | "User leaves in 10 min, skip the smoke run" | A feature nobody watched working is unverified. Say "queued", verify after, or do it now. | | "Minor bump, obviously" | The repo's convention decides, not your intuition. Check tags first. | | "I'll merge directly, CI is slow" | CI is the only verification beyond your machine. Auto-merge exists for exactly this. | | "I'll quietly skip the changelog" | Skipping is fine only when said out loud and filed as follow-up. |
From Roflochinsky/workshopskills, MIT.
More from Roflochinsky/workshopskills
- 0.474score
classifying-tasks
Roflochinsky
Use when receiving any new work request, before writing code or choosing an approach — especially multi-item requests, vague one-liners, "quick" asks, or work…
SkillCFreshness: CClaude Code +9 - 0.474score
decomposing-to-issues
Roflochinsky
Use when breaking a spec or plan into tracker issues for execution — especially when different agents or sessions will pick the pieces up independently.
SkillCFreshness: CClaude Code +9 - 0.474score
delivering-heavy-features
Roflochinsky
Use when a task is classified heavy — a new feature with its own business logic, work spanning several layers with a new or changed contract, or anything…
SkillCFreshness: CClaude Code +9 - 0.474score
doctor
Roflochinsky
Use before running heavy composite workflows (delivering-heavy-features etc.), when a required skill or tool is missing, when setting up a new machine or…
SkillCFreshness: CClaude Code +9 - 0.474score
fixing-incidents
Roflochinsky
Use when production is down or degraded, users are reporting errors, or the user demands an urgent fix ("prod is down", "fix it now", "clients are calling") —…
SkillCFreshness: CClaude Code +9 - 0.474score
getting-second-opinion
Roflochinsky
Use when about to approve, merge, or sign off on non-trivial work you authored yourself — especially when feeling confident, when the user says "I trust your…
SkillCFreshness: CClaude Code +9 - 0.474score
onboarding-codebase
Roflochinsky
Use when working in a repository for the first time, or in an unfamiliar area of a large repo — before making any edit, especially when the task "should be…
SkillCFreshness: CClaude Code +9 - 0.474score
upgrading-dependencies
Roflochinsky
Use when asked to update, upgrade, or bump dependencies, fix dependency vulnerabilities, or when CI flags outdated/vulnerable packages — before running any…
SkillCFreshness: CClaude Code +9 - 0.474score
codifying-learnings
Roflochinsky
Use when the user corrects you, repeats an instruction they gave before, or you notice you've made the same mistake or received the same feedback more than…
SkillCFreshness: CClaude Code +9 - 0.471score
heavy-task-pipeline
Roflochinsky
Use for Tier 2 / heavy Workwatch tasks — a new dashboard section with its own business logic, anything spanning API + DB migrations + UI, or any ADR-gate…
SkillCFreshness: CClaude Code +9 - 0.471score
runtime-sql-review
Roflochinsky
Mandatory write→review loop for runtime-/live-only fixes the test suite cannot catch — raw SQL via SQLAlchemy text() / asyncpg, migrations, queries, any…
SkillCFreshness: CClaude Code +9 - 0.445score
grill-me
Roflochinsky
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 16, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Roflochinsky/workshopskills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Roflochinsky
- 0.474score
classifying-tasks
Roflochinsky
Use when receiving any new work request, before writing code or choosing an approach — especially multi-item requests, vague one-liners, "quick" asks, or work…
SkillCFreshness: CClaude Code +9 - 0.474score
decomposing-to-issues
Roflochinsky
Use when breaking a spec or plan into tracker issues for execution — especially when different agents or sessions will pick the pieces up independently.
SkillCFreshness: CClaude Code +9 - 0.474score
delivering-heavy-features
Roflochinsky
Use when a task is classified heavy — a new feature with its own business logic, work spanning several layers with a new or changed contract, or anything…
SkillCFreshness: CClaude Code +9 - 0.474score
doctor
Roflochinsky
Use before running heavy composite workflows (delivering-heavy-features etc.), when a required skill or tool is missing, when setting up a new machine or…
SkillCFreshness: CClaude Code +9 - 0.474score
fixing-incidents
Roflochinsky
Use when production is down or degraded, users are reporting errors, or the user demands an urgent fix ("prod is down", "fix it now", "clients are calling") —…
SkillCFreshness: CClaude Code +9 - 0.474score
getting-second-opinion
Roflochinsky
Use when about to approve, merge, or sign off on non-trivial work you authored yourself — especially when feeling confident, when the user says "I trust your…
SkillCFreshness: CClaude 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 shipping-a-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
shipping-a-release skill. Agent Mart. https://agentmart.dev/skills/roflochinsky-shipping-a-release (last updated 2026-10-24)