Test Evidence Review

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 "Test Evidence Review" for me. 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. The skill itself reviews the QUALITY of a game project's test files and manual evidence, beyond mere existence or passing: for each story in scope (a single story path, the current sprint, or a system/epic) it locates the evidence (unit/integration test files in the engine's test roots, retained screenshots and evidence documents under production/qa/evidence/, smoke reports), evaluates assertion coverage (3+ assertions per test function is normal; a test with 0 assertions is flagged BLOCKING at the story type's gate level), edge-case and formula traceability, naming quality, criterion linkage, sign-offs and staleness, and assigns each story a verdict: ADEQUATE, INCOMPLETE, MISSING, NOT ASSESSED (when the review could not be performed, which is never reported as MISSING) or WAIVED at qa.level minimal. It resolves the studio configuration by running the template's hooks/yaml-helper.sh (automation, workflow, qa.level, testing.strict), and checks evidence freshness by running the template's .claude/scripts/review-receipts.sh script, both template files outside this skill's folder. It presents the report in conversation and writes production/qa/evidence-review-[date].md only after asking. It does not fix tests and does not run the project's test suite itself. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/test-evidence-review/ folder at the pinned commit: 1 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/test-evidence-review/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 a7ab49090d3018910d1efc2a43bb16f8239c9150bc3b180bdfdaf8bca208c96f 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 1 file only: SKILL.md. Nothing in the folder is a program; it is instructions the agent 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 reviewed or modified. - Integrated-system reality, from the files: at use time the skill resolves studio configuration by running the template's hooks/yaml-helper.sh and checks evidence staleness by running the template's .claude/scripts/review-receipts.sh; both live outside this skill's folder and are absent in a standalone install. Inside the template it reads my project's stories, test files and QA evidence locally; it executes no test suite and contacts no network service. - At use time it writes only after asking: its one persistent output is the optional report at production/qa/evidence-review-[date].md. Its Collaborative Protocol says it reports quality issues and does not fix them; it never modifies test files or evidence documents. - Do not review any project, 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 test-evidence-review folder into the agent's skills directory, in a folder named exactly "test-evidence-review", keeping its 1 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: test-evidence-review), the 1 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, and what it does inside the template). 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.