Authoring Goal Prompts
Author a self-contained prompt for Claude Code's /goal command, run unattended in a separate session — a lead-to-staff handoff where this session researches, designs, and decides with full context, and a fresh executor session (Opus 5.5 or Fable 5.2, with none of that context) implements. Drafts a goal with measurable done-criteria, transcript-verifiable checks, scope + anti-cheat constraints, and stop rules; packages design intent, code examples, research findings, checklists, and pre-answered decisions as support files in a per-goal state directory whenever the executor would otherwise re-de
Install
/plugin marketplace add tomada1114/tomada-claude-pluginsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add tomada1114/tomada-claude-plugins --skill authoring-goal-promptsgit clone --depth 1 https://github.com/tomada1114/tomada-claude-plugins.git /tmp/tomada-claude-plugins
mkdir -p ~/.claude/skills
cp -r /tmp/tomada-claude-plugins/tomada-kit/skills/authoring-goal-prompts ~/.claude/skills/authoring-goal-promptsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Goal Prompt Author
Produce a ready-to-paste prompt for Claude Code's `/goal` command, which a person will run in a
**separate, unattended session**. Your output is the prompt itself plus its support files — you do
**not** run `/goal`.
**Don't use this skill for:** running or babysitting `/goal` yourself; one-turn tasks that finish
faster than setting up a goal; subjective goals with no measurable end state ("make the UX nicer").
## Five truths about `/goal` that drive every decision
1. **No human is reachable mid-run.** Every decision the goal session might otherwise ask about
must be pre-decided and encoded as a fallback rule.
2. **A small evaluator model judges only the transcript** — it runs no commands and reads no files.
"Done" must be provable by text the goal session prints (an exit code, a sentinel line, `git status`).
3. **Optimizing the transcript invites cheating.** A model graded on "looks done" may skip/`xfail`
tests, weaken assertions, or stub implementations. Forbid this explicitly.
4. **The executor knows nothing you don't write down.** This is a lead-engineer → staff-engineer
handoff: this session investigates, designs, and decides; the goal session — fresh, with zero
shared context, typically Opus 5.5, or Fable 5.2 at high effort for the hardest runs — executes. It is capable,
but it spends its effort on execution under a turn ceiling; whatever it has to re-derive costsDetails
- Skill name
authoring-goal-prompts- Repository
- tomada1114/tomada-claude-plugins
- Path
tomada-kit/skills/authoring-goal-prompts/SKILL.md- Repo updated
- 12 November 2026
FAQ
What does the Authoring Goal Prompts skill do?
Author a self-contained prompt for Claude Code's /goal command, run unattended in a separate session — a lead-to-staff handoff where this session researches, designs, and decides with full context, and a fresh executor session (Opus 5.5 or Fable 5.2, with none of that context) implements. Drafts a goal with measurable done-criteria, transcript-verifiable checks, scope + anti-cheat constraints, and stop rules; packages design intent, code examples, research findings, checklists, and pre-answered decisions as support files in a per-goal state directory whenever the executor would otherwise re-de
How do I install the Authoring Goal Prompts skill?
Claude Code plugin: /plugin marketplace add tomada1114/tomada-claude-plugins. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Authoring Goal Prompts popular?
It lives in tomada1114/tomada-claude-plugins, which has 5 GitHub stars and 0 forks.
Related skills
Auditing Prompt Docs
5tomada1114/tomada-claude-plugins
Audit and fix prompt-bearing documents — SKILL.md, CLAUDE.md, AGENTS.md, agent and command definitions, reference files, whole repositories — against Anthropic's published prompting guidance for current Claude models, proposing edits for approval before writing anything. Also answers how to prompt a specific model: holds the per- model guidance for Claude Fable 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 alongside the cross-model practices. Use when reviewing or slimming an instruction file, when instructions are ignored or fire too often, when migrating a prompt to a newer m
Auditing Repositories
5tomada1114/tomada-claude-plugins
Audit the repository you are in, often a template or an app cut from one, for technical debt and room to improve in four areas: architecture and design patterns; tests; file structure and code quality; and tooling, CI, dependencies and the agent harness. Design a safe, test-first fix for every evidenced finding, and file the findings as GitHub issues that follow the repository's own issue conventions (triaging-issues, issue forms, past issues). A finding inherited from the template is also filed in the template repository. Cheap read-only sub-agents collect the evidence and high-effort analyst
Bootstrapping From Templates
5tomada1114/tomada-claude-plugins
Cut a new GitHub repository from one of the user's template repositories and bring it to a clean first commit: create it from the template (public by default) with scripts/create_from_template.py, clone it under ghq, follow the template's own starting-an-app procedure for the rename or bootstrap (a script, a just recipe, or a placeholder inventory), write AGENTS.md's Product section from signed-off requirements, copy kickoff drafts into docs/, run the template's checks, sync its labels, and push. Use when creating a repository from a template, running a template's bootstrap or rename, a placeh
Close
5Magnus-Gille/claude-skills
Close a coding-agent session or produce its final handoff only when the user explicitly asks to close, wrap up, or produce an end-of-session handoff.
Configuring Cloud Environments
5tomada1114/tomada-claude-plugins
Inspect, create, and edit Claude Code cloud environments (the Name, Network access, Allowed domains, Setup script, and Environment variables behind claude.ai/code's environment selector) and decide what a repository needs from one — which hosts its toolchain downloads from and whether the Trusted allowlist covers them (bundled checker script), whether an existing environment fits or a new one is warranted, and what belongs in the environment's setup script versus the repository's SessionStart hook. Use when asked to look at, create, edit, or tune a cloud environment or its setup script, to add
AI Agents Architect
5Dreydrey9000/claude-skills
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ...
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.