Grill With Docs

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 — None to install this skill — no account, no key, no payment. Two dependencies to know before using it: this entry point calls two separate skills from the same repository, grilling and domain-modeling, so both must be installed too, otherwise it does nothing; and when it is used, the interview writes documentation files (decision records and a glossary) into my own project. It is user-invoked only: it starts when I ask for it by name, never on its own. Install "Grill With Docs" for me. It is a small, user-invoked entry point: when I invoke it, it calls two skills together — grilling, which runs a relentless interview to sharpen a plan or design, and domain-modeling, which keeps the paperwork as we go — so the decisions the interview settles are written down as architecture decision records and the project glossary is created or updated with the terms we pin down. The folder itself contains only that two-call instruction plus its agent policy file; the interview behaviour and the document formats live in the two companion skills, which are separate installs from the same repository. Unlike grill-me, which is the interview alone, this version leaves documents behind in my project. Repository: https://github.com/mattpocock/skills (the skill is the whole skills/engineering/grill-with-docs/ folder at the pinned commit: SKILL.md and agents/openai.yaml only, 2 files) Pinned version: install the code at commit 5beb35b040e3de97e54fa9e386d7e42d15c295c2 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/mattpocock/skills into a temporary folder, check out commit 5beb35b040e3de97e54fa9e386d7e42d15c295c2, and copy the skills/engineering/grill-with-docs/ 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 7de372c13488f1ee96cc11cd8907b56b6809cc93eef776eeddd37de6b6cbe3fe - agents/openai.yaml: SHA-256 94cd0ab161fb468a836349f5ed482ba58ce8e709a05c57ce533d739dbd35cca9 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 2 files only: a 247-byte SKILL.md whose single instruction is to call the grilling and domain-modeling skills, and agents/openai.yaml declaring its display name and its user-only invocation policy. There is no script and no other code in it. - Nothing is sent anywhere during installation itself, and no document is written during installation; the only download at install time is the skill folder from GitHub at the pinned commit. - At use time, the exchanges stay inside my own conversation and my own project: the interview runs locally and, through domain-modeling, writes decision records and glossary files into my project as decisions settle. No personal information or credentials are read or sent to any third party. The behaviour comes from the separate grilling and domain-modeling skills, which this install does not include or modify. - Do not start any interview, do not call either companion skill, do not write any document, and do not use the skill in any way during this install: using it is a separate step that only starts when I invoke it by name later. 3. When I say "yes, install", install it as a skill: copy the whole grill-with-docs folder into the agent's skills directory, in a folder named exactly "grill-with-docs", keeping its 2 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: grill-with-docs), the 2 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 the separate grilling and domain-modeling skills must also be installed for this one to do anything, that this skill is user-invoked only, and that using it writes decision and glossary files into my project; using it is a separate step that only starts when I invoke it). 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.