Story Readiness

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — INTEGRATED SYSTEM FIRST: this skill is one piece of the complete "Claude Code Game Studios" template (49 agents, 74 skills, studio templates and a studio CLAUDE.md, per the repository README). Each skill assumes that template is installed, with its conventions, its project.yaml / project.local.yaml configuration, its .claude/docs/ mode documents, its hooks (for example hooks/yaml-helper.sh, outside this skill's folder) and its .claude/scripts/ helpers. Installing this listing alone copies only this skill's folder, without the rest of the system: the skill may reference template agents, files, hooks or scripts that are absent outside the full template, and it may not run as designed on its own. No account, no key and no payment are needed to copy the files, and nothing is run during installation. Install "Story Readiness" for me. The skill itself checks that a story file holds everything a developer needs before writing code — no design questions mid-build, no guessing, no vague acceptance criteria. Its scope is one story path, an epic, 'sprint' or 'all' (every story-*.md under production/epics/); an empty scope stops with NOT ASSESSED and never prints a clean zero summary. It gathers its facts once per run through the template scripts (.claude/scripts/story-facts.sh --lint for the stories, .claude/scripts/adr-status.sh for every referenced ADR), plus the control manifest version and the TR registry, then applies a six-group checklist (design completeness, architecture completeness, scope clarity, open questions, asset references checked for existence only, definition of done), with the tier deciding which groups block. Verdicts per story, first match wins: BLOCKED (a referenced ADR is missing, Proposed, Deprecated or Superseded — blocking at every tier —, a dependency story is missing or Draft, or an unresolved design question), NEEDS WORK, NOT ASSESSED (something needed could not be read; it is never READY), or READY (advisory gaps still listed). In full review mode it hands each story to the template's qa-lead agent for the QL-STORY-READY gate (references/qa-lead-gate.md); in solo or lean mode that gate is skipped and the report says so. The skill is strictly read-only: it never writes or edits a file under any circumstance, and when the user accepts its closing offer it drafts the missing parts in the conversation only, leaving the writing to the user or /create-stories. It resolves its configuration by running the template's hooks/yaml-helper.sh, outside this skill's folder, and CONTRACT.md states the same read-only guarantee as a handoff contract. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/story-readiness/ folder at the pinned commit: 3 files in total) Pinned version: install the code at commit 05ad7c8a5b8aa2aa86bbd3439ae7cf7295cac418 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/Donchitos/Claude-Code-Game-Studios into a temporary folder, check out commit 05ad7c8a5b8aa2aa86bbd3439ae7cf7295cac418, and copy the .claude/skills/story-readiness/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - CONTRACT.md: SHA-256 9f72e5fad1591d91ddb19f295ef392ac31d227908c248354b7584327ebd73891 - SKILL.md: SHA-256 0c73e0a2c22b13a711a40ea4682a1d31c3c61cd8ad4a5a5115c41f8270659d12 - references/qa-lead-gate.md: SHA-256 f919c5e0cfc94d1caccd0c68c4ab5b97b64fca75c24d1632ab6f2297a534c226 If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 3 files: SKILL.md, CONTRACT.md (its handoff contract, which restates the strictly read-only guarantee) and references/qa-lead-gate.md (the Phase 5 qa-lead review gate). Nothing in the folder is a program; the files are instructions and a contract the skill reads and follows at use time. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit, and no project of mine is audited, read or modified. - Integrated-system reality, from the files: at use time the skill runs the template's hooks/yaml-helper.sh (many resolved keys) and the template scripts .claude/scripts/story-facts.sh and adr-status.sh, reads my project's story files, ADRs, TR registry, control manifest, sprint files and referenced assets, follows .claude/docs/director-gates.md when its gate runs, and in full review mode spawns the template's qa-lead agent — hooks, scripts, docs and an agent that live outside this skill's folder and are absent in a standalone install, so it cannot run as designed on its own. - At use time it writes nothing at all, under any circumstance: its CONTRACT.md guarantees no file modifications, and its closing offer only drafts missing parts in the conversation. No third-party service, account or credential is named in the files. - Do not check any story's readiness, do not run any template hook or script, and do not use the skill in any way during this install: using it is a separate step that only starts when I ask for it later. 3. When I say "yes, install", install it as a skill: copy the whole story-readiness folder into the agent's skills directory, in a folder named exactly "story-readiness", keeping its 3 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: story-readiness), the 3 files in place with matching fingerprints. Do not run anything from the folder and do not use the skill to verify. 5. Report what was installed, where, and what I still need to do myself (for example: that it belongs to the full Claude Code Game Studios template and may not run standalone (it resolves its settings through the template's yaml-helper hook, works through its .claude/scripts/ helpers and, in full review mode, its qa-lead agent), and that at use time it is strictly read-only and never writes or edits any file). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.