thinking-through
Use when the user asks for ideas, brainstorming, discussion, exploration, possibilities, pros and cons, tradeoffs, or to "think through" something.
Skill by szokeasaurusrex
Chalk Labs
Need help deploying thinking-through?
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/szokeasaurusrex-thinking-through
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
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/thinking-through
What's inside
- Skill name
thinking-through- Description
- Use when the user asks for ideas, brainstorming, discussion, exploration, possibilities, pros and cons, tradeoffs, or to "think through" something.
- License
- MIT
- Instructions
- 22 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Thinking Through Use this mode for exploratory, advisory, or discussion-focused requests. ## Behavior - Focus on understanding the question, investigating relevant context, and sharing thoughts, options, tradeoffs, risks, and open questions. - Ask clarifying questions when the goal, constraints, or desired depth are unclear. - Do not implement changes or modify workspace files by default. - If investigation requires trying something out, use a temporary directory under `$TMPDIR`, not the workspace. - You may read workspace files when useful for context. - You may modify files only when the user explicitly asks you to record findings in a markdown, text, or other document. - If the user shifts from discussion to implementation, confirm before making workspace changes unless the request is explicit. ## Output - Present possibilities with concise reasoning. - Include pros and cons or tradeoffs when comparing options. - Call out assumptions and uncertainty. - Suggest next steps, but do not perform them unless asked.
From szokeasaurusrex/pi-agent, MIT.
More from szokeasaurusrex/pi-agent
- 0.599score
commit
szokeasaurusrex
Use this skill when asked to create or amend a commit.
SkillAFreshness: A★ 2Claude Code +9 - 0.557score
value-challenge
szokeasaurusrex
Mandatory adversarial value gate for every nontrivial code, configuration, documentation, process, or product change.
SkillBFreshness: B★ 2Claude Code +9 - 0.511score
plan
szokeasaurusrex
Use this skill when asked to plan something, or plan and implement.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
cargo
szokeasaurusrex
Use when initializing Rust projects or modifying Cargo.toml, Cargo.lock, cargo config, or other cargo-related files.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
delegation-plan
szokeasaurusrex
Write plans intended for a cheaper or less capable implementation model.
SkillCFreshness: C★ 2Claude Code +9 - 0.448score
split-commit
szokeasaurusrex
Split an existing commit or PR into smaller reviewable pieces through a one-hunk patch queue.
SkillDFreshness: D★ 2Claude Code +9 - 0.447score
github-issues-draft
szokeasaurusrex
Use when asked to create or draft GitHub issues.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
technical-writing
szokeasaurusrex
Use when drafting or editing persisted technical writing artifacts such as commit messages, issue bodies, PR descriptions, documentation comments, or…
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
github-bare-worktree-clone
szokeasaurusrex
Create a GitHub repo as repo/.bare with repo/<branch> worktrees and origin-tracking branches.
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
sentry-docs
szokeasaurusrex
Use whenever fetching documentation from docs.sentry.io or develop.sentry.dev.
SkillDFreshness: D★ 2Claude Code +9 - 0.439score
context-fork
szokeasaurusrex
Checkpoint, inspect, and return through session tree branches.
SkillDFreshness: D★ 2Claude Code +9 - 0.438score
skill-writing
szokeasaurusrex
Use when creating or updating agent skills (`skills/<name>/SKILL.md` files).
SkillDFreshness: D★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 3, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/szokeasaurusrex/pi-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from szokeasaurusrex
- 0.599score
commit
szokeasaurusrex
Use this skill when asked to create or amend a commit.
SkillAFreshness: A★ 2Claude Code +9 - 0.557score
value-challenge
szokeasaurusrex
Mandatory adversarial value gate for every nontrivial code, configuration, documentation, process, or product change.
SkillBFreshness: B★ 2Claude Code +9 - 0.511score
plan
szokeasaurusrex
Use this skill when asked to plan something, or plan and implement.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
cargo
szokeasaurusrex
Use when initializing Rust projects or modifying Cargo.toml, Cargo.lock, cargo config, or other cargo-related files.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
delegation-plan
szokeasaurusrex
Write plans intended for a cheaper or less capable implementation model.
SkillCFreshness: C★ 2Claude Code +9 - 0.448score
split-commit
szokeasaurusrex
Split an existing commit or PR into smaller reviewable pieces through a one-hunk patch queue.
SkillDFreshness: D★ 2Claude 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 thinking-through 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
thinking-through skill. Agent Mart. https://agentmart.dev/skills/szokeasaurusrex-thinking-through (last updated 2026-10-24)