New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Goal

by cwinvestments in cwinvestments/memstack

A skill your agent uses when the user says 'goal', 'set a goal', 'define the goal', 'plan this properly', or starts a task that needs a clear finish line and verification.

MITAuto-check passed

Install Goal

skills CLI
$ npx skills add cwinvestments/memstack --skill goal -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cwinvestments/memstack goal --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cwinvestments/memstack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/goal .claude/skills/goal && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
goal
GitHub stars
423
Token cost
~1.6k tokens
SKILL.md length
757 words
Files
1
Skills in repo
87
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user says 'goal', 'set a goal', 'define the goal', 'plan this properly', or starts a task that needs a clear finish line and verification.

  • Works in 5 steps: TASK: what to do. The concrete action,… → WHY: why it matters / who it's for.… → OUTCOME: the exact finished result, the… → …
  • The user says goal
  • SKILL.md covers Activation, Context Guard, The Five Fields and How It Works, plus 5 more sections
  • Calls python

What it does

Goal is an agent skill from cwinvestments/memstack. Use when the user says 'goal', 'set a goal', 'define the goal', 'plan this properly', or starts a task that needs a clear finish line and verification. Structures work into TASK / WHY / OUTCOME / CONSTRAINTS / VERIFICATION before execution begins.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Structured skill framework for Claude Code. 130 skills, persistent memory, TokenStack compression, localhost dashboard with 3-agent runner, real-time streaming, MCP tools. The licence is MIT.

When your agent uses it

  • The user says goal
  • Define the goal
  • Plan this properly
  • Starts a task that needs a clear finish line and verification

Example prompts

  • “set a goal”
  • “define the goal”
  • “plan this properly”
  • “/goal”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. TASK: what to do. The concrete action, in one sentence. Required.
  2. WHY: why it matters / who it's for. Optional, but it keeps scope honest and kills gold-plating. Skip it if it's obvious.
  3. OUTCOME: the exact finished result, the definition of done. Not "improve X" but the specific end state that exists when you're finished…
  4. CONSTRAINTS: what must or must not be done. Boundaries: no new dependencies, don't change the public API, stay under budget. Optional…
  5. VERIFICATION: how you'll PROVE the outcome is complete. A concrete, observable, checkable criterion: a command to run, an output to see, a…

What it can do on your machine

Read from SKILL.md and the folder at commit 00370ce. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Goal loads about 1.6k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 757 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cwinvestments/memstack at commit 00370ce, republished under its MIT licence (© cwinvestments). 757 words, ~1,607 tokens.

Download SKILL.mdSave it as .claude/skills/goal/SKILL.md (or your agent's skills folder).
name
goal
description
Use when the user says 'goal', 'set a goal', 'define the goal', 'plan this properly', or starts a task that needs a clear finish line and verification. Structures work into TASK / WHY / OUTCOME / CONSTRAINTS / VERIFICATION before execution begins.
version
1.0.0

🎯 Goal: Finish Line Defined

Define what "done" looks like and how you'll prove it, before you write a line of code.

Activation

When this skill activates, output:

🎯 Goal: Finish line defined.

Then walk the user through the five fields in order, one prompt at a time or as a single template: whichever fits the flow. Fill in what the request already tells you; ask only for what's missing. Put the most weight on VERIFICATION: it is the field that is required, the field that is skipped most often, and the field that turns "I think it's done" into "I can show it's done." Do not let a goal close without a concrete, checkable verification criterion.

Context Guard

ContextStatus
User says "goal", "set a goal", "define the goal", "plan this properly"ACTIVE: structure the five fields
User is starting a non-trivial task with a fuzzy finish lineACTIVE, offer to define the goal first
User asks "how will we know this is done?" / "what's the definition of done?"ACTIVE: VERIFICATION-first
User is mid-execution and just wants the next stepDORMANT: use work, not goal
The goal is already clearly stated with a checkable outcomeDORMANT, don't re-litigate a good goal
Casual question, chit-chat, or a one-line lookupDORMANT: do not activate

The Five Fields

A goal is a task with a finish line you can stand on. Five fields:

  1. TASK: what to do. The concrete action, in one sentence. Required.
  2. WHY: why it matters / who it's for. Optional, but it keeps scope honest and kills gold-plating. Skip it if it's obvious.
  3. OUTCOME: the exact finished result, the definition of done. Not "improve X" but the specific end state that exists when you're finished. Required.
  4. CONSTRAINTS: what must or must not be done. Boundaries: no new dependencies, don't change the public API, stay under budget. Optional; list as many as apply.
  5. VERIFICATION: how you'll PROVE the outcome is complete. A concrete, observable, checkable criterion: a command to run, an output to see, a behavior to reproduce. Required, and load-bearing.

A goal without a concrete VERIFICATION criterion is incomplete, not merely unpolished. "It works," "done," and "tests pass" are not verification, they assert success without naming what you'd observe to confirm it. That gap is exactly how a green build ships the wrong behavior. State the check, not the vibe.

Show full SKILL.md (364 more words)Show less

How It Works

The skill shells out to the goal engine for parsing and validation (the same engine the Architect stage uses) so a drafted goal is checked the same way everywhere.

bash
# Print the blank five-field template
python -m memstack_skill_loader.goal template

# Validate a drafted goal (reads the labeled text, reports errors + warnings)
python -m memstack_skill_loader.goal validate

validate enforces the rules: TASK, OUTCOME, and VERIFICATION must be present; a present-but-vacuous VERIFICATION (e.g. "it works") comes back as a warning telling you to state a concrete, checkable criterion. Errors mean the goal isn't ready to execute; warnings mean tighten it before you trust it.

Note: the engine module (goal_engine.py) exists today; the thin CLI entry (python -m memstack_skill_loader.goal) is wired in a later registration step. If the command isn't callable yet, don't block, guide the user through the five fields by hand and show the template inline (below). The discipline is the point; the CLI is a convenience.

Inline template (fallback when the CLI isn't available):

TASK: (what to do)
WHY: (why it matters / who it's for - optional)
OUTCOME: (the exact finished result - what 'done' looks like)
CONSTRAINTS: (what must or must not be done - optional, one per line)
VERIFICATION: (how you'll prove the outcome is complete - a concrete, checkable criterion)

Quick Commands

  • /goal: start structuring a goal from the current request
  • /goal template: show the blank five-field template
  • "set a goal" / "define the goal" / "plan this properly": natural-language triggers that open the same flow

Example Usage

User: "make the scanner better"

That's a wish, not a goal, there's no finish line and no way to prove success. Structured:

🎯 Goal: Finish line defined.

TASK: Improve the site scanner's transport-security scoring
WHY: Users trust the score to flag insecure sites; today HTTP and HTTPS
     sites can score the same, which is misleading
OUTCOME: The scan assigns a strictly lower security score to a plain-HTTP
         site than to the same site served over HTTPS
CONSTRAINTS:
  - no new dependencies
  - don't change the score scale or the JSON output shape
VERIFICATION: run the scanner against http://example.test and
              https://example.test (same content) and confirm the HTTP
              scan's numeric score is lower than the HTTPS scan's

Why this matters: a vague version ("scanner feels better," "tests pass") could ship with the HTTP and HTTPS scores still identical and every existing test still green. The build passes while the behavior is wrong. The VERIFICATION line makes that failure impossible to miss: two scans, one comparison, a criterion you either meet or you don't. Define that line before execution, and "done" stops being a matter of opinion.

Inputs

  • The user's raw request or task description
  • Optional: a drafted goal in the five-field labeled format (for validate)
  • Engine: python -m memstack_skill_loader.goal (template / validate)

Outputs

  • A structured goal with all five fields, VERIFICATION concrete and checkable
  • Validation results: errors (not ready) and warnings (tighten before trusting)
  • A finish line that execution and review can both be measured against

Level History

  • Lv.1: Base: Five-field goal structuring (TASK / WHY / OUTCOME / CONSTRAINTS / VERIFICATION) with a required, checkable VERIFICATION criterion; backed by the shared goal engine (goal_engine.py) used by both this skill and the Architect stage. (Origin: MemStack, Jul 2026)

© cwinvestments, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/goal of cwinvestments/memstack.

Open the folder on GitHubat commit 00370ce

Compare with similar skills

Goal next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Goal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Goal this skillcwinvestments/memstack423—~1.6kAutomated safety check: PassMIT
Define Goallingxling/awesome-skills-cn302—~1.4kAutomated safety check: PassApache-2.0
Goalscodewhale-hq/Codewhale41k—~273Automated safety check: PassMIT
Agent Goal Plannerruvnet/ruflo74k2 repos~842Automated safety check: PassMIT
Goal Planruvnet/ruflo74k—~807Automated safety check: NotesMIT
Goal Loopsickn33/agentic-awesome-skills47k1 repos~2.6kAutomated safety check: PassMIT

Similar skills

  • Define Goal

    lingxling/awesome-skills-cn

    Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy…

    302 GitHub stars~1.4k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • Goals

    codewhale-hq/Codewhale

    Set, review, and update the user's goals. An agent skill from codewhale-hq/Codewhale.

    41k GitHub stars~273 tokensUpdated today
    Auto-check passed

  • Agent Goal Planner

    ruvnet/ruflo

    Agent skill for goal-planner - invoke with $agent-goal-planner

    74k GitHub starsUsed in 2 repos~842 tokens
    Auto-check passed

  • Goal Plan

    ruvnet/ruflo

    Create and execute Goal-Oriented Action Plans (GOAP) with precondition analysis, cost optimization, and adaptive replanning

    74k GitHub stars~807 tokensUpdated today
    Auto-check: notes

  • Goal Loop

    sickn33/agentic-awesome-skills

    Draft and explain persistent goal-loop prompts for long-running agent work with clear stop conditions.

    47k GitHub starsUsed in 1 repo~2.6k tokens
    Agent WorkflowsAuto-check passed

  • Agent Code Goal Planner

    ruvnet/ruflo

    Agent skill for code-goal-planner - invoke with $agent-code-goal-planner

    74k GitHub starsUsed in 2 repos~3.6k tokens
    Agent WorkflowsAuto-check passed

More from cwinvestments/memstack

All 87 skills in this repo

  • Memstack SEO Site Audit

    cwinvestments/memstack

    A skill your agent uses when the user says 'SEO audit', 'site audit', 'check SEO', 'audit my site', 'SEO check', 'technical SEO', or is evaluating a website's search engine optimization health, meta…

    423 GitHub stars~3.5k tokensUpdated 14 days ago
    Auto-check passed

  • Memstack SEO Schema Markup

    cwinvestments/memstack

    A skill your agent uses when the user says 'add schema', 'schema markup', 'JSON-LD', 'structured data', 'rich results', 'rich snippets', or is adding or fixing schema.org structured data for better…

    423 GitHub stars~2.7k tokensUpdated 14 days ago
    Auto-check passed

  • Compress

    cwinvestments/memstack

    A skill your agent uses when the user says 'tokenstack', 'compression', 'token savings', 'proxy status', or asks about context window usage.

    423 GitHub stars~1.2k tokensUpdated 14 days ago
    Auto-check passed

  • Diary

    cwinvestments/memstack

    A skill your agent uses when the user says 'save diary', 'log session', 'wrapping up', or at end of a productive session.

    423 GitHub stars~5k tokensUpdated 14 days ago
    Auto-check passed

  • Echo

    cwinvestments/memstack

    A skill your agent uses when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.

    423 GitHub stars~1.7k tokensUpdated 14 days ago
    Auto-check passed

  • Familiar

    cwinvestments/memstack

    A skill your agent uses when the user says 'dispatch', 'send familiar', 'split task', or needs work split across parallel CC sessions.

    423 GitHub stars~556 tokensUpdated 14 days ago
    Auto-check passed

Questions about Goal

What does Goal do?

A skill your agent uses when the user says 'goal', 'set a goal', 'define the goal', 'plan this properly', or starts a task that needs a clear finish line and verification. Goal is an agent skill from cwinvestments/memstack. Use when the user says 'goal', 'set a goal', 'define the goal', 'plan this properly', or starts a task that needs a clear finish line and verification.

When should I use Goal?

Goal fits situations like: the user says goal; define the goal; plan this properly; starts a task that needs a clear finish line and verification.

How do I install Goal in Claude Code?

Run `npx skills add cwinvestments/memstack --skill goal -a claude-code`. Or copy the skill folder (skills/goal in cwinvestments/memstack) into .claude/skills/goal in your project. Claude Code loads it when a task matches its description.

How do I install Goal in Codex?

Run `npx skills add cwinvestments/memstack --skill goal -a codex`. Or copy the skill folder (skills/goal in cwinvestments/memstack) into .agents/skills/goal in your project. Codex loads it when a task matches its description.

Can I use Goal in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cwinvestments/memstack --skill goal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/goal, .gemini/skills/goal, .github/skills/goal and .opencode/skills/goal in your project.

What does Goal need to run?

Going by SKILL.md and its folder, Goal needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Goal access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Goal safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Goal use?

Goal is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Goal use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Goal?

Skills that share tags, products or a category with Goal: Define Goal (lingxling/awesome-skills-cn, 302 stars), Goals (codewhale-hq/Codewhale, 41k stars), Agent Goal Planner (ruvnet/ruflo, 74k stars) and Goal Plan (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Goal?

cwinvestments (a GitHub user) maintains it in cwinvestments/memstack, which has 423 GitHub stars. The repository holds 87 skills in this directory. The repository was last updated on September 26, 2026.

Source: cwinvestments/memstack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.