Skip to content
Agentmart
Submit a tool

explain-history

Explain the evidence behind a design decision or past failure.

Skill by wcygan

IndexedMIT
Write a review

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/wcygan-explain-history

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.

We use your email only for this newsletter. Privacy

About

Explain the evidence behind a design decision or past failure. Use for rationale, tradeoffs, regressions, and prior attempts.

Use cases: design

Reviews

Write a review

No 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/explain-history

What's inside

Skill name
explain-history
Description
Explain the evidence behind a design decision or past failure. Use for rationale, tradeoffs, regressions, and prior attempts.
License
MIT
Metadata
kind: component · maintenance: local · upstream-path: pstack/skills/why · upstream-author: Lauren Tan · upstream-revision: 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8 · upstream-repository: https://github.com/cursor/plugins
Instructions
20 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • LICENSE.txt · references/

SKILL.md (first lines)

# Explain history

1. Anchor the question to code, a decision, or an observed failure. Trace earlier
   changes as well as the latest edit, including renames and reverted attempts.
2. Follow relevant evidence through change discussions, issues, design documents,
   incident records, and measurements that are available within the task's scope.
   Stop when the question is supported; expand the search when evidence conflicts.
3. Separate recorded facts, reasonable inferences, competing explanations, and
   unknowns. A plausible explanation of the code is not proof of its author's intent.
4. Cite the evidence for each consequential claim. Identify searched sources that
   returned nothing and relevant sources that were unavailable.
5. For a proposed change, translate the history into constraints: what to preserve,
   what can change, what previously failed, and what still needs checking.

Done when the rationale is supported or explicitly unknown, with the constraints
and remaining uncertainty clear enough to inform the next decision.

Adapted from pstack; [license and attribution](references/LICENSE.txt).

From wcygan/agent-skills, MIT.

More from wcygan/agent-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 14, 2026 (15 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/wcygan/agent-skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from wcygan

Cite this page

explain-history skill. Agent Mart. https://agentmart.dev/skills/wcygan-explain-history (last updated 2026-10-24)