Estimate

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 "Estimate" for me. It produces a structured effort estimate for a task: optimistic, expected and pessimistic scenarios in half-day increments, a recommended budget (always the expected scenario, never the optimistic one), a confidence level with its drivers, risk and dependency tables, and a suggested sub-task breakdown. It reads the task from its argument (asking for clarification when the description is too vague), reads CLAUDE.md for project context, reads the relevant design documents in design/gdd/ by section, measures the affected code with Grep counts only — non-blank lines for size, branch-and-operator lines as an approximation of cyclomatic complexity that it reports as an approximation, never as a measured complexity — checks existing test coverage, and reads past sprint data in production/sprints/ for historical velocity, stating plainly under Notes and Assumptions when no sprint history exists instead of silently padding the figures. It never gives a single number, never pads silently, and confidence is Low whenever the approach or the core requirements are undecided. This skill is read-only: its frontmatter allows only Read, Glob and Grep, it resolves no studio configuration and runs no hook or script, and it writes no files — the estimate exists only in the conversation. Its folder is a single SKILL.md. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/estimate/ 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/estimate/ 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 61d821627b3db4f4038f60b7ce799599a219b864036023ce15d5fc85348874f0 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 a single file: SKILL.md. Nothing in the folder is a program; it is estimation instructions the session 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 read or modified. - Integrated-system reality, from the files: this is the lightest skill in the set — it runs no template hook and no template script and spawns no agent; it only reads my project's CLAUDE.md, the design documents under design/gdd/ and past sprint data under production/sprints/ when they exist, following the template's project layout conventions. Outside the template those paths may simply be absent, and the skill says so in its output rather than inventing calibration data. - At use time it writes nothing at all: it is read-only (allowed tools: Read, Glob, Grep only) and the estimate is delivered in the conversation. Its code measurements are Grep line counts that approximate complexity, reported as approximations. No third-party service, account or credential is named in the file I read. - Do not estimate any task 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 estimate folder into the agent's skills directory, in a folder named exactly "estimate", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: estimate), 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 — that it belongs to the full Claude Code Game Studios template's project layout (it reads CLAUDE.md, design/gdd/ and production/sprints/ when they exist) but is itself read-only, writing nothing and running nothing, and that using it only produces an estimate in the conversation). 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.