How do I install the Makegoal skill?

Run npx skillmds@latest add barkleesanders/makegoal in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Makegoal safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Makegoal?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Makegoal free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Makegoal?

barkleesanders (@barkleesanders) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Makegoal by barkleesanders — Agent Skill

Name: Makegoal
Rating: 4.666666666666667 (3 reviews)
Author: barkleesanders

Makegoal

MERGED into /goal (2026-08-26) — kept as a redirect for muscle memory and for the openai.yaml implicit invocation. The brief-fill + parallel-subgoal + synthesis workflow is now `/goal make <task>` (aliases `/goal build`, `/goal parallel`). Invoking /makegoal routes there. Use when the user types /makegoal, asks for parallel goals for a task, asks to fill the build-task template, or asks to solve a task with parallel goals or parallel agents.

barkleesanders 4456dac 2 files · 2.3 KB Updated Sep 10, 2026

File contents

/makegoal → merged into `/goal make` (2026-08-26)

This skill no longer holds the workflow. It was 92 lines of prompt pattern with no code of its own, and its own Goal Setup section already said "In Claude, use /goal" — it was a front-end for the /goal engine, not an alternative to it.

Everything it did now lives in the /goal skill:

Was	Now
`/makegoal <task>`	`/goal make <task>` (also `/goal build`, `/goal parallel`)
The filled build brief template	`~/.claude/skills/goal/references/make-mode.md` § Step 1
Parallel subgoal dispatch + agent prompt shape	same file, § Step 4 — now opt-in, see below
Synthesis + final response	same file, §§ 5–6

What the merge improved: subgoals now land in the /goal deliverable ledger, so the evidence gate, stall escalation, and anti-abandonment steering apply to them. Under the old skill they lived only in the prompt and evaporated. Also, parallel dispatch is now explicitly gated on the user asking for agents (per the global "do not call the AgentTool unless the user requested it" rule), instead of being the unconditional default.

What to do when this skill is invoked

Read ~/.claude/skills/goal/references/make-mode.md.
Follow it, treating everything after /makegoal as the raw task.

Do not re-implement the old flow from this file — it is a stub. The pre-merge original is preserved beside it as SKILL.md.pre-merge-20260826.bak for reference only.

---name: makegoaldescription: MERGED into /goal (2026-08-26) — kept as a redirect for muscle memory and for the openai.yaml implicit invocation. The brief-fill + parallel-subgoal + synthesis workflow is now `/goal make <task>` (aliases `/goal build`, `/goal parallel`). Invoking /makegoal routes there. Use when the user types /makegoal, asks for parallel goals for a task, asks to fill the build-task template, or asks to solve a task with parallel goals or parallel agents.---# /makegoal → merged into `/goal make` (2026-08-26)**This skill no longer holds the workflow.** It was 92 lines of prompt pattern with nocode of its own, and its own Goal Setup section already said *"In Claude, use `/goal`"* —it was a front-end for the `/goal` engine, not an alternative to it.Everything it did now lives in the `/goal` skill:| Was | Now ||---|---|| `/makegoal <task>` | `/goal make <task>` (also `/goal build`, `/goal parallel`) || The filled build brief template | `~/.claude/skills/goal/references/make-mode.md` § Step 1 || Parallel subgoal dispatch + agent prompt shape | same file, § Step 4 — now **opt-in**, see below || Synthesis + final response | same file, §§ 5–6 |**What the merge improved:** subgoals now land in the `/goal` **deliverable ledger**, sothe evidence gate, stall escalation, and anti-abandonment steering apply to them. Underthe old skill they lived only in the prompt and evaporated. Also, parallel dispatch isnow explicitly gated on the user asking for agents (per the global "do not call theAgentTool unless the user requested it" rule), instead of being the unconditionaldefault.## What to do when this skill is invoked1. Read `~/.claude/skills/goal/references/make-mode.md`.2. Follow it, treating everything after `/makegoal` as the raw task.Do not re-implement the old flow from this file — it is a stub. The pre-merge originalis preserved beside it as `SKILL.md.pre-merge-20260826.bak` for reference only.

Frequently asked questions