get-goal-prompt
Generate a /goal command to execute an ideation project's specs autonomously. Reads the contract, builds a goal prompt with phase ordering and spec paths, copies it to clipboard, and prints it. The user pastes the /goal command to start autonomous execution. Use when the user says 'goal', 'run as goal', 'get goal prompt', 'goal prompt', or wants to execute specs via /goal instead of /ideation:autopilot.
What this skill does
# Generate /goal Command for Spec Execution
## Arguments: $ARGUMENTS
Build a `/goal` command that will autonomously execute all specs in an ideation project, then copy it to the user's clipboard.
## Step 1: Find the Contract
- If a path was provided in `$ARGUMENTS`, use it
- Otherwise, glob for `./docs/ideation/*/contract.md`
- If multiple found, pick the most recently modified
Read `contract.md` and extract:
1. **Project name and directory** from the contract path
2. **Phases** — title, spec path, and dependency ordering from the Execution Plan section
3. **Already-completed phases** — run `git log --oneline --grep="spec-phase"` to find commits referencing spec files. Exclude completed phases from the goal.
If no uncompleted phases remain, tell the user and stop.
## Step 2: Build the Goal Prompt
Construct a `/goal` condition under 4000 characters. The condition serves as both the directive (what Claude should do) and the completion check (what the evaluator verifies).
Use this template, filling in the project-specific values:
```
/goal Execute all implementation specs for {project-name} in dependency order. For each phase, read the spec file, implement all changes following the spec's implementation details, run validation commands from the spec, and commit with a descriptive message referencing the spec.
Phases (execute in this order, respecting dependencies):
{numbered list of phases with spec paths and dependency notes}
How to execute each phase:
1. Read the spec file completely before starting
2. Follow the spec's "Implementation Details" section for what to build
3. Use the spec's "Feedback Strategy" inner-loop command after each component
4. Run all "Validation Commands" from the spec before committing
5. Commit only when all validations pass — message format: "feat({slug}): implement phase N — {title}"
Done when: git log shows a commit for every listed phase with passing validation. If a phase's validation fails after 3 attempts, stop and report which phase failed and why.
```
**Phase list format** — one line per phase:
```
1. {title} → {spec-path} (blocking)
2. {title} → {spec-path} (after phase 1)
3. {title} → {spec-path} (after phase 1, parallel with 2)
```
Omit completed phases from the list. If phases were skipped, note: "Phases {list} already committed — starting from phase {N}."
**Keep it under 4000 characters.** If the phase list is long, abbreviate notes. The spec files contain all the detail — the goal prompt just needs ordering and paths.
## Step 3: Output and Copy
1. Copy the full `/goal` command to clipboard:
```bash
echo '<goal command>' | pbcopy # macOS
```
On Linux, try `xclip -selection clipboard` or `xsel --clipboard`.
2. Print the command to screen so the user can see what they're about to run:
```
Copied to clipboard. Paste to start:
/goal Execute all implementation specs for ...
```
3. Remind the user: "Make sure auto mode is enabled so tool calls don't block each turn. Run `/auto` first if needed."
That's it. The skill's job is done once the command is on the clipboard. `/goal` handles the rest.
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.