designing-goal-loops
Converts development tasks, bug reports, or feature ideas into robust, verifiable goal specifications for autonomous LLM execution (/goal or subagents).
Skill by stenalpjolly
Chalk Labs
Need help deploying designing-goal-loops?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/stenalpjolly-designing-goal-loops
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, writing, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/designing-goal-loops
What's inside
- Skill name
designing-goal-loops- Description
- Converts development tasks, bug reports, or feature ideas into robust, verifiable goal specifications for autonomous LLM execution (/goal or subagents). Use when preparing to run long-running or unmonitored agent loops that require self-contained context, atomic task boundaries, and executable verification criteria to prevent premature completion and looping. Don't use for executing code changes directly or for writing general product requirement documents (use refining-feature-requests).
- License
- unknown
- Instructions
- 61 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- goal-specification-template.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from stenalpjolly/llm-skills
- 0.569score
crafting-effective-prompts
stenalpjolly
Creates high-clarity, unambiguous, and effective prompts for LLMs and autonomous agents using structured prompt engineering techniques.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
bootstrapping-projects
stenalpjolly
Bootstraps a new project or initializes an existing directory with standard structures, documentation, planning files, version control setups, and…
SkillBFreshness: B★ 4Claude Code +9 - 0.561score
drafting-advisory-status-reports
stenalpjolly
Generates executive Google Cloud Advisory Weekly Status Report HTML documents with base64 logo embedding and A4 print-deterministic CSS.
SkillBFreshness: B★ 4Claude Code +9 - 0.519score
auditing-ui-ux
stenalpjolly
Performs a comprehensive UI/UX design audit on application screens or components.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
crawling-web-applications
stenalpjolly
Crawls, navigates, and audits a web application's links, buttons, and interactive elements.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
debugging-with-mantras
stenalpjolly
Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
designing-tasteful-frontends
stenalpjolly
Upgrades AI-built frontends (landing pages, portfolios, marketing sites) to premium, Awwwards-level quality.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
implementing-test-driven-issue-resolution
stenalpjolly
Converts user assumptions, feature requests, or bug reports into verified, test-driven code changes.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
generating-mermaid-diagrams
stenalpjolly
Generates syntax-valid, render-safe Mermaid.js diagrams (flowcharts, sequence diagrams, state diagrams, ERDs, Gantt charts).
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
generating-qa-scenarios
stenalpjolly
Generates conversational user evaluation scenarios and test case checklists for software flows or user journeys.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
code-reviewer
stenalpjolly
Use this skill to review code.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
migrating-nextjs-to-python
stenalpjolly
Translates Next.js JavaScript/TypeScript API routes (req, res) into clean FastAPI Python backend endpoints.
SkillCFreshness: C★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 14, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/stenalpjolly/llm-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from stenalpjolly
- 0.569score
crafting-effective-prompts
stenalpjolly
Creates high-clarity, unambiguous, and effective prompts for LLMs and autonomous agents using structured prompt engineering techniques.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
bootstrapping-projects
stenalpjolly
Bootstraps a new project or initializes an existing directory with standard structures, documentation, planning files, version control setups, and…
SkillBFreshness: B★ 4Claude Code +9 - 0.561score
drafting-advisory-status-reports
stenalpjolly
Generates executive Google Cloud Advisory Weekly Status Report HTML documents with base64 logo embedding and A4 print-deterministic CSS.
SkillBFreshness: B★ 4Claude Code +9 - 0.519score
crawling-web-applications
stenalpjolly
Crawls, navigates, and audits a web application's links, buttons, and interactive elements.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
auditing-ui-ux
stenalpjolly
Performs a comprehensive UI/UX design audit on application screens or components.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
implementing-test-driven-issue-resolution
stenalpjolly
Converts user assumptions, feature requests, or bug reports into verified, test-driven code changes.
SkillCFreshness: C★ 4Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get designing-goal-loops running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
designing-goal-loops skill. Agent Mart. https://agentmart.dev/skills/stenalpjolly-designing-goal-loops (last updated 2026-10-24)