asc-explain-changes
Use after a Codex thread when the user wants a teach-me-something style debrief.
Skill by cavaunpeu
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/cavaunpeu-asc-explain-changes
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/asc-explain-changes
What's inside
- Skill name
asc-explain-changes- Description
- Use after a Codex thread when the user wants a teach-me-something style debrief. Teach incrementally, verify mastery at each step, and keep a running checklist of what the user should understand about the problem, the solution, and the broader impact.
- License
- MIT
- Instructions
- 70 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Asc Explain Changes Use this skill after a completed thread when the user wants to leave with a better mental model of the ideas behind the work. ## Teaching Loop ### 1. Start from the thread Extract the main concepts and any skills that were invoked. Keep a short working list of what the user should understand: - the main concepts discussed - any skills invoked on those concepts - the concrete way each concept affected the work Use the list as a teaching checklist, not as a transcript summary. ### 2. Teach one checkpoint at a time Do not explain everything at once. Teach the current checkpoint, then confirm mastery before moving on. For each checkpoint, cover three layers: - what the problem was - why it existed or why the solution worked - what broader effect the change has ### 3. Confirm understanding before moving on Before advancing, ask the user to restate the current checkpoint in their own words. If the restatement is weak, fill in the gap and ask again. If it is strong, move to the next checkpoint. ### 4. Keep the understanding checklist visible Track these checkpoints explicitly: - the problem - why the problem existed - the solution - why the solution was chosen - the edge cases and tradeoffs - the broader context - what the change affects ### 5. Drill down as needed Ask follow-up questions when the user is shaky. Prefer open-ended questions first. Use multiple-choice only when it helps isolate confusion quickly. ### 6. End only when mastery is demonstrated Do not end the skill until the user has shown they understand the checkpoints on the list. If needed, re-ask from a different angle until the gaps are gone. ## Output shape Use a conversational debrief, not a lecture. - Start by naming the checkpoint you are teaching. - Ask for the user’s current understanding. - Fill the gaps. - Move to the next checkpoint only after the current one is solid. Be specific about the work that happened. This skill is about turning a real thread into durable understanding.
From cavaunpeu/agent-skills-closet, MIT.
More from cavaunpeu/agent-skills-closet
- 0.476score
asc-entrypoint
cavaunpeu
ASC entrypoint's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
SkillCFreshness: CClaude Code +9 - 0.474score
asc-ml-entrypoint
cavaunpeu
Top-level ML routing skill for customer-facing model work.
SkillCFreshness: CClaude Code +9 - 0.474score
asc-ml-adaptation
cavaunpeu
Choose how to change model behavior with CPT, SFT, or RL-based preference tuning.
SkillCFreshness: CClaude Code +9 - 0.474score
asc-ml-system-design
cavaunpeu
Design an ML system from an ambiguous business problem.
SkillCFreshness: CClaude Code +9 - 0.474score
asc-ml-eval
cavaunpeu
Design and run ML evaluations, slices, and release gates.
SkillCFreshness: CClaude Code +9 - 0.471score
asc-model-setup
cavaunpeu
Configure which models the asc skills use per role.
SkillCFreshness: CClaude Code +9 - 0.469score
asc-entrypoint-explicit
cavaunpeu
Routing target for asc-entrypoint behavior with explicit, less insider-heavy communication.
SkillCFreshness: CClaude Code +9 - 0.455score
asc-how
cavaunpeu
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillCFreshness: CClaude Code +9 - 0.452score
asc-architect
cavaunpeu
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillCFreshness: CClaude Code +9 - 0.452score
asc-interrogate
cavaunpeu
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillCFreshness: CClaude Code +9 - 0.450score
asc-figure-it-out
cavaunpeu
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away.
SkillCFreshness: CClaude Code +9 - 0.447score
asc-blast-radius
cavaunpeu
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 20, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/cavaunpeu/agent-skills-closet
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cavaunpeu
- 0.476score
asc-entrypoint
cavaunpeu
ASC entrypoint's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
SkillCFreshness: CClaude Code +9 - 0.474score
asc-ml-system-design
cavaunpeu
Design an ML system from an ambiguous business problem.
SkillCFreshness: CClaude Code +9 - 0.474score
asc-ml-adaptation
cavaunpeu
Choose how to change model behavior with CPT, SFT, or RL-based preference tuning.
SkillCFreshness: CClaude Code +9 - 0.474score
asc-ml-entrypoint
cavaunpeu
Top-level ML routing skill for customer-facing model work.
SkillCFreshness: CClaude Code +9 - 0.474score
asc-ml-eval
cavaunpeu
Design and run ML evaluations, slices, and release gates.
SkillCFreshness: CClaude Code +9 - 0.471score
asc-model-setup
cavaunpeu
Configure which models the asc skills use per role.
SkillCFreshness: CClaude Code +9
Cite this page
asc-explain-changes skill. Agent Mart. https://agentmart.dev/skills/cavaunpeu-asc-explain-changes (last updated 2026-10-24)