goal-griller
Use when the user wants to turn a rough idea, vague task, feature wish, bug-fix intent, or Codex /goal objective into a clear verifiable goal prompt. Use when the user mentions goal mode, /goal, set_goal, long-running autonomous Codex work, or asks to be interviewed/grilled before creating a goal.
What this skill does
# Goal Griller Interrogate fuzzy intent until it becomes a goal Codex can autonomously pursue, verify, and stop on. This skill is inspired by the `grill-me` pattern: ask one question at a time, recommend an answer, and inspect the codebase instead of asking when the answer is discoverable. ## Hard Gate Do not produce a final `/goal` prompt until these six fields are clear enough: 1. Outcome: the single truth the user wants made real. 2. Success condition: measurable or objectively inspectable proof that the outcome is true. 3. Scope boundary: what may change and what must not change. 4. Context: files, docs, logs, issues, screenshots, services, or commands Codex should read first. 5. Validation loop: cheap checks during work and final checks before claiming done. 6. Stop and pause rules: when to stop as done, and when to pause for human input. If any field is missing, ask the next highest-leverage question instead of drafting the final goal. ## Interview Loop 1. Restate the apparent intent in one sentence. 2. Identify the weakest missing field from the hard gate. 3. If the answer can be discovered from local files, active goal state, logs, docs, tests, or repo conventions, inspect those sources instead of asking. 4. Ask exactly one question at a time. 5. For each question, include your recommended answer and why it is probably right. 6. After the user answers, update the working goal shape and repeat. The interview should feel useful, not bureaucratic. Prefer three sharp questions over ten generic ones. Stop interviewing as soon as the goal is safely draftable. ## Question Priority Ask in this order unless local context shows a different blocker: 1. What should be true at the end? 2. How will we prove it is true? 3. What is explicitly out of scope? 4. What should Codex read or preserve before acting? 5. What checks should run repeatedly versus only at the end? 6. What should make Codex pause instead of improvising? 7. What proof should Codex leave behind for review? ## Anti-Vague Rewrites Reject goals shaped like these: - "Improve the app." - "Fix all bugs." - "Make it production ready." - "Refactor this codebase." - "Research this and do the best thing." Convert them into a single outcome plus proof: - Instead of "Improve the app": "Reduce dashboard initial load time by at least 25% with no visible behavior regressions, proven by benchmark output and browser screenshots." - Instead of "Fix all bugs": "Make the checkout flow pass the failing Playwright suite and preserve existing successful payment behavior." - Instead of "Refactor this codebase": "Extract the duplicated auth/session logic into one shared module while preserving all current tests and public API behavior." ## Goal Prompt Contract When the hard gate is satisfied, output: ```text /goal [single objective] Context to read first: - [...] Constraints: - [...] Operating rules: - Keep a concise progress log in [file] when the task is long-running. - Prefer small verified iterations over large unverified edits. - Do not expand scope without pausing. Validation loop: - During work: [...] - Final proof: [...] Done when: - [...] Pause if: - [...] ``` Also include a short "Why this goal is safe to run" note with the success condition, main risk, and proof artifact. ## Do Not Silently Start If the user asked only to create a goal prompt, do not invoke `/goal`, `create_goal`, or any equivalent goal-setting tool. Present the draft and ask for acceptance only if execution requires it. If the user explicitly asked to set the goal too, show the final draft first when there was any interview or inference. Set it only after the user confirms that the draft matches their intent. ## Hook Interaction The general `Goal Guard` `PreToolUse` hook may block `create_goal`, `set_goal`, `set_goals`, or `/goal`-style tool calls after LLM review. When blocked, immediately run this skill's interview loop and produce a stronger goal prompt instead of trying to bypass the hook.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.