do-you-understand
Restate in the agent's own words the user's goals and the problem they are trying to solve, to check shared understanding before acting.
Skill by leaofelipe
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/leaofelipe-do-you-understand
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: 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/do-you-understand
What's inside
- Skill name
do-you-understand- Description
- Restate in the agent's own words the user's goals and the problem they are trying to solve, to check shared understanding before acting.
- License
- MIT
- Instructions
- 3 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
restate in your own words what you think my goals are and what the problem i'm trying to solve is
From leaofelipe/ia-stuff, MIT.
More from leaofelipe/ia-stuff
- 0.614score
spec-lean
Tech Leads Club - github.com/tech-leads-club
Spec-driven feature work that freezes obligations instead of the plan: one human-reviewed plan with EARS criteria, path, entities, interface and one-way…
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
explain-pr
leaofelipe
Teach a pull/merge request didactically in plain language, one item at a time, from foundation to connected pieces.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
explain-plan
leaofelipe
Explains a user-provided feature plan or spec (plan.md, spec, design doc or chat transcript) in a didactic way, topic by topic, showing what the plan defines…
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
to-story
leaofelipe
Turn a discovery dump, agent-generated text, existing Jira card, or one-line idea into a short human-readable Jira story.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
clarify
leaofelipe
Clarify a plan, decision, or idea through a relentless interview until shared understanding.
SkillAFreshness: A★ 4Claude Code +9 - 0.604score
simplify
leaofelipe
Simplify the scoped code by using parallel read-only review agents for code quality, performance, and reuse, then make targeted cleanup fixes.
SkillAFreshness: A★ 4Claude Code +9 - 0.584score
test-surgery
leaofelipe
Remove redundant unit test code in a scoped area without dropping use cases or coverage, proven by a per-line coverage diff before and after, and finish with…
SkillAFreshness: A★ 4Claude Code +9 - 0.579score
deslop
Cursor - github.com/cursor/plugins (cursor-team-kit/deslop)
Remove AI-generated code slop and clean up code style.
SkillAFreshness: A★ 4Claude Code +9 - 0.573score
handoff
leaofelipe
Compact the current conversation into a handoff document for another agent to pick up.
SkillAFreshness: A★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 1, 2026 (28 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/leaofelipe/ia-stuff
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from leaofelipe
- 0.609score
to-story
leaofelipe
Turn a discovery dump, agent-generated text, existing Jira card, or one-line idea into a short human-readable Jira story.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
explain-plan
leaofelipe
Explains a user-provided feature plan or spec (plan.md, spec, design doc or chat transcript) in a didactic way, topic by topic, showing what the plan defines…
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
explain-pr
leaofelipe
Teach a pull/merge request didactically in plain language, one item at a time, from foundation to connected pieces.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
clarify
leaofelipe
Clarify a plan, decision, or idea through a relentless interview until shared understanding.
SkillAFreshness: A★ 4Claude Code +9 - 0.604score
simplify
leaofelipe
Simplify the scoped code by using parallel read-only review agents for code quality, performance, and reuse, then make targeted cleanup fixes.
SkillAFreshness: A★ 4Claude Code +9 - 0.584score
test-surgery
leaofelipe
Remove redundant unit test code in a scoped area without dropping use cases or coverage, proven by a per-line coverage diff before and after, and finish with…
SkillAFreshness: A★ 4Claude Code +9
Cite this page
do-you-understand skill. Agent Mart. https://agentmart.dev/skills/leaofelipe-do-you-understand (last updated 2026-10-24)