Agent skill

Roam Release Readiness

by Cranot in Cranot/roam-code

Qualify a Roam commit or accumulated batch for package, website, or server publication; reconcile source, tests, review, CI and deployed identities, and identify the next authorized release step.

Apache-2.0Auto-check passedProduct & Project Management

Install Roam Release Readiness

skills CLI
$ npx skills add Cranot/roam-code --skill roam-release-readiness -a claude-code

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

GitHub CLI
$ gh skill install Cranot/roam-code roam-release-readiness --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/Cranot/roam-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/roam-release-readiness .claude/skills/roam-release-readiness && 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
roam-release-readiness
GitHub stars
517
Token cost
~1.7k tokens
SKILL.md length
885 words
Files
2
Skills in repo
9
Repo updated
First seen
Licence
Apache-2.0

At a glance

Qualify a Roam commit or accumulated batch for package, website, or server publication; reconcile source, tests, review, CI and deployed identities, and identify the next authorized release step.

  • Roam release/deployment
  • SKILL.md covers Bind the candidate and authority, Qualify the change that will… and Keep publication surfaces…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Synchronization readiness requests

What it does

Roam Release Readiness is an agent skill from Cranot/roam-code. Qualify a Roam commit or accumulated batch for package, website, or server publication; reconcile source, tests, review, CI and deployed identities, and identify the next authorized release step. Use for Roam release/deployment or synchronization readiness requests, not ordinary local edits, copywriting, or detector diagnosis.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Product & Project Management, covering Feature launches and release readiness, Copywriting and Deployment. It works with Model Context Protocol. The repository describes itself as: Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys. The licence is Apache-2.0.

When your agent uses it

  • Roam release/deployment
  • Synchronization readiness requests
  • Not ordinary local edits
  • Detector diagnosis

Example prompts

  • “/roam-release-readiness”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 4856519. 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

Roam Release Readiness loads about 1.7k tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 885 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 Cranot/roam-code at commit 4856519, republished under its Apache-2.0 licence (© Cranot). 885 words, ~1,688 tokens.

Download SKILL.mdSave it as .claude/skills/roam-release-readiness/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
roam-release-readiness
description
Qualify a Roam commit or accumulated batch for package, website, or server publication; reconcile source, tests, review, CI and deployed identities, and identify the next authorized release step. Use for Roam release/deployment or synchronization readiness requests, not ordinary local edits, copywriting, or detector diagnosis.

Roam release readiness

Determine what can advance, what remains unverified, and the next authorized operation for each requested surface. A readiness review is not publication; publication on one surface is not evidence for the others.

Bind the candidate and authority

Read current AGENTS.md, docs/repository-maintenance.md, and the relevant release owner: docs/releases.md for packages or docs/website-maintenance.md for Pages. Read docs/containers.md only when an image is requested, and docs/concepts/verification-evidence.md when assessing proof bundles, verdicts or review receipts. Use internal/EXECUTION-SEQUENCE.md for the active cursor when present; otherwise consult internal/INDEX.md and existing release-driver phase records without inventing a replacement board. Missing private context is a named limit, not an automatic veto of sufficient public release evidence. Treat earlier artifacts as dated context, not live facts. Follow the user's specific scope; a skill does not grant release approvals or alter policies.

Inventory HEAD/upstream, staged and unstaged changes, untracked files, relevant worktrees/stashes and remote/server state before synchronization or cleanup. Record exact identities and preserve unique work. A clean branch relationship does not prove a worktree or server is clean. Stage only reviewed explicit paths; never absorb unrelated edits, rewrite published history or move a release tag. For index-only executable-bit changes, follow AGENTS.md's Windows commit-pathspec exception and verify the staged set and resulting commit, not just command success.

Distinguish candidate contents, installed editable version, release tag, registry artifact, CI commit, review subject, server revision and Pages deployment. Check current state when a decision depends on it. Keep a compact per-surface record linking required evidence to its exact source and operation; do not reduce these identities to one green label.

Qualify the change that will actually land

Derive checks from the complete candidate, not the last small edit or commit message. Include relevant untracked files in the review packet and test scope. The venv roam --json verification-contract --files-from <list> can suggest obligations; inspect current help, its inspected denominator and skips. It does not replace the project release rules or expert review of the diff.

FAST/FULL structural gates are not the release-sized suite. An accumulated release-sized batch needs scripts/prepush_check.py --release with a bounded worker budget in the locked venv. Read that run's actual coverage note rather than copying a stale list of unproven CI lanes. Capture start, command, selected scope, final exit and test outcomes. For long runs use a durable runner supported by the host with an explicit completion marker; a launched or abandoned process is pending, not green. Avoid concurrent heavy gates on a constrained workstation.

Bind independent review to the same artifact and requested model/effort when specified. A prompt, dispatch, tool-read count or schema-valid receipt is not a completed review. Preserve actual output, identity evidence and every finding's disposition. Editorial review does not approve runtime changes. Changed bytes need appropriate requalification; do not relabel an earlier verdict or accept residual risk on the owner's behalf. Skips and missing baselines stay explicit.

For material product-copy changes, record factual support, product-meaning review and owner acceptance separately from technical gates. Tests and browser checks cannot establish that the page communicates the intended product. Recheck current owner direction: an unresolved positioning objection is not superseded by a prior editorial label or a green suite. Keep the affected publication pending while advancing independent qualification; do not invent a new approval gate for typos.

Require the normal local gates before push and required CI on the exact pushed commit before tagging or production deployment. Local success does not predict all CI lanes. Do not bypass a failed gate or approve a protected older release just because the user wants the current website live.

Show full SKILL.md (295 more words)Show less

Keep publication surfaces independent

For package pins, distinguish the version being developed from a package users can actually install. A highest tag awaiting publication is not available PyPI evidence. Preserve verified pins and report that synchronization hold; use the maintained generators after publication, not global version replacement. Classify other literals by the release guide: deliberately lagging self-consuming action pins move only after their target is published; historical records and illustrative fixtures are not synchronization defects. Qualify actual wheel/ sdist contents and fresh installed-package behavior outside the source checkout; editable tests do not prove package completeness.

For the website, preserve the existing Cloudflare Pages project and committed- export workflow. A Git push or local preview is not deployment. Use the current scripts/stage_site.py/documented deploy route only after the clean candidate and exact-commit gates pass; staging alone proves byte identity. Verify the deployment URL and custom domain, representative content/assets, redirects and headers against the deployed SHA. Report browser/accessibility limits separately. A real website-only change need not wait for a Python release; a mixed batch does not become website-only by assertion. An independent container hold blocks the image, not automatically an otherwise qualified package or website.

For server updates, identify the actual host/checkout, process environment and local edits before changing anything. Use the existing deployment procedure and preserve recovery paths. Verify that the running installation uses the intended artifact; successful SSH or an HTTP response alone is not synchronization proof.

Advance independent in-scope checks while another step waits. Stop the blocked mutation when a missing decision, authority or evidence would materially change it; state the narrow choice and what can still proceed. Preserve a prior verified artifact for recovery without creating an unrequested rollback. At handoff update the existing execution cursor, link exact artifacts, and regenerate the private index.

© Cranot, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/roam-release-readiness of Cranot/roam-code.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 4856519

Compare with similar skills

Roam Release Readiness 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.

Roam Release Readiness compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Roam Release Readiness this skillCranot/roam-code517—~1.7kAutomated safety check: PassApache-2.0
Azsdk Common Prepare Release PlanAzure/azure-sdk-for-android121—~733Automated safety check: PassMIT
Repo Genomeruvnet/metaharness694—~772Automated safety check: PassMIT
Azsdk Common Prepare Release PlanAzure/azure-sdk-tools134—~2.7kAutomated safety check: PassMIT
Verify Witnessruvnet/metaharness694—~472Automated safety check: PassMIT
Pre Release Testherald-email/herald-mail-app144—~448Automated safety check: PassCustom licence

Similar skills

  • Azsdk Common Prepare Release Plan

    Azure/azure-sdk-for-android

    Official

    Create and manage release plan work items for Azure SDK releases across languages.

    121 GitHub stars~733 tokensUpdated 4 mo ago
    Product & Project ManagementAuto-check passed
  • Repo Genome

    ruvnet/metaharness

    7-section readiness scorecard for a LOCAL repo. An agent skill from ruvnet/metaharness.

    694 GitHub stars~772 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Official

    Create, get, update, abandon, and link SDK PRs to release plan work items for Azure SDK releases.

    134 GitHub stars~2.7k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Verify Witness

    ruvnet/metaharness

    Verify the Ed25519 witness manifest of a scaffolded harness.

    694 GitHub stars~472 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Pre Release Test

    herald-email/herald-mail-app

    A skill your agent uses when preparing a Herald beta release, checking release readiness, or running broad deterministic integration gates across TUI themes, inline images, SSH, and MCP before…

    144 GitHub stars~448 tokensUpdated 2 mo ago
    Product & Project ManagementAuto-check passed
  • Zach Product Research

    zach22-1999/amazon-skills

    基于Sorftime MCP的选品分析,发现高潜力市场机会、多维度属性标注与交叉分析、验证竞争格局、测算投入产出、输出Go/No-Go决策与选品报告。

    208 GitHub starsUsed in 1 repo~9.6k tokens
    Product & Project ManagementAuto-check: notes

More from Cranot/roam-code

All 9 skills in this repo
  • Roam

    Cranot/roam-code

    Codebase comprehension via roam-code CLI. An agent skill from Cranot/roam-code.

    517 GitHub stars~2.4k tokensUpdated 6 days ago
    Auto-check passed
  • Roam Agent Guidance

    Cranot/roam-code

    Review and maintain the technical instructions Roam gives coding agents: shipped skills, tool descriptions, preset guidance and generated instruction blocks.

    517 GitHub stars~1.3k tokensUpdated 6 days ago
    Auto-check passed
  • Roam Evidence Hardening

    Cranot/roam-code

    Investigate and harden Roam detectors, CLI/MCP result contracts, and evidence consumers when dogfooding or correcting incomplete, misleading, or inconsistent analysis.

    517 GitHub stars~1.5k tokensUpdated 6 days ago
    Auto-check passed
  • Roam Lesson Maintenance

    Cranot/roam-code

    Turn a reproduced or recurring Roam failure into a durable correction, regression control or narrowly scoped project skill, and reconcile conflicting lessons.

    517 GitHub stars~1.2k tokensUpdated 6 days ago
    Auto-check passed
  • Roam Measurement Design

    Cranot/roam-code

    Design or interpret a comparison of Roam performance, detector accuracy, retrieval or workflow value.

    517 GitHub stars~1.2k tokensUpdated 6 days ago
    Auto-check passed
  • Roam Milestone Planning

    Cranot/roam-code

    Define or revise a Roam product milestone and its engineering, adoption and offer-readiness sequence.

    517 GitHub stars~1.2k tokensUpdated 6 days ago
    Auto-check passed

Questions about Roam Release Readiness

What does Roam Release Readiness do?

Qualify a Roam commit or accumulated batch for package, website, or server publication; reconcile source, tests, review, CI and deployed identities, and identify the next authorized release step. Roam Release Readiness is an agent skill from Cranot/roam-code. Qualify a Roam commit or accumulated batch for package, website, or server publication; reconcile source, tests, review, CI and deployed identities, and identify the next authorized release step.

When should I use Roam Release Readiness?

Roam Release Readiness fits situations like: roam release/deployment; synchronization readiness requests; not ordinary local edits; detector diagnosis.

How do I install Roam Release Readiness in Claude Code?

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

How do I install Roam Release Readiness in Codex?

Run `npx skills add Cranot/roam-code --skill roam-release-readiness -a codex`. Or copy the skill folder (.agents/skills/roam-release-readiness in Cranot/roam-code) into .agents/skills/roam-release-readiness in your project. Codex loads it when a task matches its description.

Can I use Roam Release Readiness 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 Cranot/roam-code --skill roam-release-readiness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/roam-release-readiness, .gemini/skills/roam-release-readiness, .github/skills/roam-release-readiness and .opencode/skills/roam-release-readiness in your project.

What does Roam Release Readiness need to run?

SKILL.md names no scripts, command-line tools or credentials: Roam Release Readiness is instructions for the agent only. Our summary lists: Python 3.

Does Roam Release Readiness 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 Roam Release Readiness 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 Roam Release Readiness use?

Roam Release Readiness is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Roam Release Readiness use?

About 1.7k tokens (SKILL.md is roughly 6.8k 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 Roam Release Readiness?

Skills that share tags, products or a category with Roam Release Readiness: Azsdk Common Prepare Release Plan (Azure/azure-sdk-for-android, 121 stars), Repo Genome (ruvnet/metaharness, 694 stars), Azsdk Common Prepare Release Plan (Azure/azure-sdk-tools, 134 stars) and Verify Witness (ruvnet/metaharness, 694 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Roam Release Readiness?

Cranot (a GitHub user) maintains it in Cranot/roam-code, which has 517 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 3, 2026.

Source: Cranot/roam-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.