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/astro-han-goal-writer
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: writing
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
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/goal-writer
What's inside
- Skill name
goal-writer- Description
- Draft or review minimal, testable goals. Use only when the user explicitly asks to write, revise, or review a goal.
- License
- MIT
- Instructions
- 38 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (3)
- SKILL.md
- cdc-case.md · references/
- lint_goal.py · scripts/
SKILL.md (first lines)
# Goal Writer Turn rough intent into the smallest copy-ready execution contract that makes completion decidable. Produce the contract; do not activate it unless explicitly asked. ## Draft 1. Look up facts in the request, named sources, and available environment instead of asking or inventing them. Ask only for user-owned decisions that materially change the contract; state reversible assumptions. 2. Preserve the requested outcome. Do not invent limits or substitute a safer intermediate objective. 3. Write one coherent acceptance decision containing the observable result that should exist and the criterion for accepting it as complete. 4. Add another fact only when deleting it would change the goal's meaning, authorization, or real-world risk. State the boundary directly instead of creating a field for it. Define acceptance before execution. Completion requires evidence that every necessary condition holds; partial progress is not completion. For open-ended research or long search tasks, read [the CDC prompt case](references/cdc-case.md) to see how a real goal excludes plausible false completions and governs evidence-seeking iteration. ## Examples A routine goal can be one sentence: ```text 修复登录超时后的错误跳转;完成以新增回归测试通过且正常登录测试仍通过为准。 ``` A real authorization boundary earns one additional sentence, not a new template: ```text Prepare the customer-data migration and make its dry run pass against the approved fixture with a reviewed rollback plan. Do not execute the production migration without explicit approval. ``` The examples show required meaning, not required structure. Domain workflows belong to the relevant task skill and repository instructions. ## Output and validation Aim for at most 1000 characters. Return only the contract unless a consequential assumption must be disclosed or the user asks for explanation. Run `python3 scripts/lint_goal.py -` with the contract on stdin, or pass one or more files. The linter rejects empty contracts, explicit placeholder tokens, and text over 4000 characters; it warns above 2000. Use `--max-chars N` when the target has a stricter hard limit.
From Astro-Han/skills, MIT.
More from Astro-Han/skills
- 0.634score
wrap-up
Astro-Han
Close a session cleanly by resolving session-owned loose ends and reporting the final state.
SkillAFreshness: A★ 12Claude Code +9 - 0.596score
pr-review
Astro-Han
Review a pull request or queue from problem value through code correctness.
SkillBFreshness: B★ 12Claude Code +9 - 0.594score
learn-anything
Astro-Han
Teach with adaptive guidance, retrieval practice, and Socratic questioning.
SkillBFreshness: B★ 12Claude Code +9 - 0.594score
simplify-audit
Astro-Han
Audit an existing repository or scoped architecture area for simplification opportunities, separating proven removals from those still blocked on a fact or a…
SkillBFreshness: B★ 12Claude Code +9 - 0.594score
review-feedback
Astro-Han
Adjudicate and act on existing code-review feedback: PR comments, inline threads, or findings from reviewers, review tools, external models, or delegated…
SkillBFreshness: B★ 12Claude Code +9 - 0.591score
tdd
Astro-Han
Use test-driven development when requested, or when a clear behavior change has a trustworthy automated seam and test-first feedback is worth its cost.
SkillBFreshness: B★ 12Claude Code +9 - 0.589score
shape
Astro-Han
Interview the user to resolve material branches of a decision tree and converge on a shared plan before acting.
SkillBFreshness: B★ 12Claude Code +9 - 0.583score
eli5
Astro-Han
Create simple, beautiful visual explainers for people new to a topic.
SkillBFreshness: B★ 12Claude Code +9 - 0.549score
craft-skill
Astro-Han
Create or improve agent skills from concrete behavior and evidence.
SkillCFreshness: C★ 12Claude Code +9 - 0.544score
parallel-research
Astro-Han
Research with parallel agents, independent evidence angles, and cross-validation.
SkillCFreshness: C★ 12Claude Code +9 - 0.544score
debug
Astro-Han
Diagnose and fix bugs, failures, and performance regressions.
SkillCFreshness: C★ 12Claude Code +9
Signals
- Stars
- 12
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- Aug 21, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Astro-Han/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Astro-Han
- 0.737score
karpathy-llm-wiki
Astro-Han
Use when building or maintaining a personal LLM-powered knowledge base.
SkillCFreshness: C★ 2.6KClaude Code +9 - 0.634score
wrap-up
Astro-Han
Close a session cleanly by resolving session-owned loose ends and reporting the final state.
SkillAFreshness: A★ 12Claude Code +9 - 0.596score
pr-review
Astro-Han
Review a pull request or queue from problem value through code correctness.
SkillBFreshness: B★ 12Claude Code +9 - 0.594score
review-feedback
Astro-Han
Adjudicate and act on existing code-review feedback: PR comments, inline threads, or findings from reviewers, review tools, external models, or delegated…
SkillBFreshness: B★ 12Claude Code +9 - 0.594score
learn-anything
Astro-Han
Teach with adaptive guidance, retrieval practice, and Socratic questioning.
SkillBFreshness: B★ 12Claude Code +9 - 0.594score
simplify-audit
Astro-Han
Audit an existing repository or scoped architecture area for simplification opportunities, separating proven removals from those still blocked on a fact or a…
SkillBFreshness: B★ 12Claude Code +9
Cite this page
goal-writer skill. Agent Mart. https://agentmart.dev/skills/astro-han-goal-writer (last updated 2026-10-24)