Skill Test

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. At use time, two of its four modes can write test-result and catalog files inside the template's studio-tests/ folder, only after asking; the other two write nothing, and no mode runs the skill it tests. Install "Skill Test" for me. The skill itself validates skills (.claude/skills/*/SKILL.md) and agents (.claude/agents/*.md) of the studio template for structural compliance and behavioural correctness, in four modes: static (a structural linter running 7 compliance checks per skill, plus unscored agent, delegation and compatibility observations produced by the template scripts .claude/scripts/agent-check.sh and .claude/scripts/compat-inventory.sh), spec (a behavioural verifier that evaluates each assertion and test case of a skill's or agent's test spec from studio-tests/, by reading, not by running it), category (checks against the category rubric in studio-tests/quality-rubric.md), and audit (a coverage report: specs written, last test dates, priority gaps). No mode executes the skill under test: a pass proves the file has the required structure or that its written instructions cover the spec's cases, never that it behaves that way when run. Static mode and audit mode write no files at all. Spec mode ends by offering to write its results to studio-tests/results/skill-test-spec-[name]-[date].md and to update the entry in studio-tests/catalog.yaml (last_spec, last_spec_result), only on a yes; category mode likewise offers a catalog update (last_category, last_category_result). A skill or agent that cannot be read is reported NOT ASSESSED with its reason, never silently dropped and never counted as passing, and every summary states how many files were actually examined. It resolves the automation mode by running the template's hooks/yaml-helper.sh, outside this skill's folder, and its frontmatter pins model: sonnet. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/skill-test/ folder at the pinned commit: 1 file 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/skill-test/ 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 c4a1775aabdac131a0fde02fa380bd741eaffb380516f4e004ae34cfedb363c9 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: SKILL.md only. 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 audited, read or modified. - Integrated-system reality, from the file: at use time the skill runs the template's hooks/yaml-helper.sh to resolve the automation mode, follows .claude/docs/automation-modes.md, reads the skills and agents under .claude/, the studio-tests/ catalog and quality rubric, and runs the template scripts .claude/scripts/agent-check.sh and .claude/scripts/compat-inventory.sh — files 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, static and audit modes write nothing; spec mode writes a results file under studio-tests/results/ and updates studio-tests/catalog.yaml only after its explicit "May I write these results" offer is accepted, and category mode offers the same kind of catalog update before writing. It runs the two template observation scripts locally; nothing is sent to any third party, and no account or credential is named in the file. - Do not test any skill or agent, 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 skill-test folder into the agent's skills directory, in a folder named exactly "skill-test", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: skill-test), the 1 file 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, reads the template's studio-tests/ framework and runs its .claude/scripts/ observation scripts), and that at use time its static and audit modes write nothing while spec and category write results or catalog updates only after asking). 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.