release
Open the PR for a verified task branch, and after the human merges it, log the tasks.csv row, run the metrics report and update release evidence.
Skill by YIlyaA
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/yilyaa-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: documents, spreadsheets, 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 Nov 2, 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
- Open the PR for a verified task branch, and after the human merges it, log the tasks.csv row, run the metrics report and update release evidence. Use when a task's verifier verdict is PASS.
- License
- MIT
- Instructions
- 32 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: scripts/metrics_report.py
Files (1)
- SKILL.md
SKILL.md (first lines)
# Release Skill ## Purpose Close the loop so every merged task is measured. No log, no credit. ## Agent Instructions ### Step 1: Open the PR Push the task branch (never `main`): `git push -u origin task/<id>-<slug>`. Then `gh pr create --base main --title "<id>: <title>" --body-file <tmp>`. The body has the goal, acceptance criteria checked off, the check output and the verifier verdict. ### Step 2: Merge on request Ask the human to review the PR and report their review minutes. Merge only when they ask for it: `gh pr merge <n> --squash --delete-branch` (an `ask` rule, so they confirm in the permission prompt). Never merge with failing CI. ### Step 3: Log the task After the merge, propose one row for `session-log/tasks.csv`: `id,date,type,method,est_hours_old_way,my_active_minutes,agent_runtime_minutes,start,end,tests_green,review_findings,rolled_back,outcome` - `est_hours_old_way` is copied from the task file, unchanged. - `my_active_minutes` comes from `scripts/metrics_report.py` (event gaps capped at 10 min) plus the review minutes. - `tests_green` is `yes` only if the first verifier run passed. The human confirms the row; then append it. Set the task to `status: done`. ### Step 4: Report and evidence Run `uv run python scripts/metrics_report.py` and show the real output. Add one line to `docs/release-evidence.md` (date, claim, command, output excerpt). ## Expected Output PR URL, the confirmed CSV row, and the report excerpt. ## Guardrails - Merge only on the human's request and only with green CI. Never push directly to `main`, never force push. - Never edit an existing `tasks.csv` row; corrections are a new note in the task file.
From YIlyaA/agent-workbench, MIT.
More from YIlyaA/agent-workbench
- 0.566score
bootstrap
YIlyaA
Set up the agent work environment in a new or existing project (AGENTS.md, CONTEXT.md, skills, planner/builder/verifier agents, guardrails, metrics, readiness…
SkillAFreshness: AClaude Code +9 - 0.565score
plan-task
YIlyaA
Turn a goal for Agents Workbench into one or more task files in tasks/ with a frozen est_hours_old_way, then stop for approval.
SkillAFreshness: AClaude Code +9 - 0.565score
verify-diff
YIlyaA
Independent review of a builder's branch by the verifier agent in a fresh context; records the verdict and finding count in the task file.
SkillAFreshness: AClaude Code +9 - 0.565score
implement-task
YIlyaA
Run approved task files through builder agents in isolated worktrees, up to 3 in parallel, test-first.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 16, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/YIlyaA/agent-workbench
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from YIlyaA
- 0.566score
bootstrap
YIlyaA
Set up the agent work environment in a new or existing project (AGENTS.md, CONTEXT.md, skills, planner/builder/verifier agents, guardrails, metrics, readiness…
SkillAFreshness: AClaude Code +9 - 0.565score
plan-task
YIlyaA
Turn a goal for Agents Workbench into one or more task files in tasks/ with a frozen est_hours_old_way, then stop for approval.
SkillAFreshness: AClaude Code +9 - 0.565score
verify-diff
YIlyaA
Independent review of a builder's branch by the verifier agent in a fresh context; records the verdict and finding count in the task file.
SkillAFreshness: AClaude Code +9 - 0.565score
implement-task
YIlyaA
Run approved task files through builder agents in isolated worktrees, up to 3 in parallel, test-first.
SkillAFreshness: AClaude 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/yilyaa-release (last updated 2026-10-24)