how
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
Skill by dotts-h
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/dotts-h-how
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/how
What's inside
- Skill name
how- Description
- Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
- License
- MIT
- Instructions
- 32 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- explainer-prompt.md · references/
- explorer-prompt.md · references/
SKILL.md (first lines)
# How Explore the codebase to answer "how does X work?" questions. Produce architectural explanations at the level of a senior engineer onboarding onto a subsystem, enough to build a working mental model, not so much that it reads like annotated source code. Every spawn is a Task subagent with `subagent_type: generalPurpose` and `readonly: true`. Explorers use the `how explorer` line in the `qstack-models.mdc` rule (default `grok-4.7-xhigh-fast`), and every explainer uses the `how explainer` line (default `claude-opus-5-5-xhigh`). Set `model` to that line's value, or to the default if the rule or the line is missing. Leave `model` unset when the value is `auto` or `inherit-parent`. If the Task tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message. ## 1. Assess complexity If the scope is ambiguous, state your interpretation and explore. The user can redirect. - **Simple** (a single module, a small utility, a narrow question such as "how does function X work"): no explorers. Spawn one explainer that explores and explains in one pass, built from `references/explainer-prompt.md` without the explorer-findings section. Go to step 4. - **Complex** (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): go to step 2. When in doubt, take the simple path. ## 2. Explore (complex only) Decompose the question into 2 to 4 angles, each a distinct slice of the subsystem. Spawn all explorers in a single message, each with `references/explorer-prompt.md` and its angle filled in. ## 3. Synthesize (complex only) Once all explorers have returned, spawn one explainer with `references/explainer-prompt.md` and every explorer's findings filled in. ## 4. Present Present the explainer's output. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it. ## Output format The explanation uses the sections defined in `references/explainer-prompt.md`, dropping any that do not apply: Overview, Key Concepts, How It Works, Where Things Live, Gotchas.
From dotts-h/qstack, MIT.
More from dotts-h/qstack
- 0.567score
qstack-mode
dotts-h
Run structured QA workflows in Cursor: test chartering, real-surface reproduction with recorded runs, defect triage, baseline-versus-patch fix verification…
SkillAFreshness: AClaude Code +9 - 0.567score
triage-defect
dotts-h
Triage bug reports with bounded cause tracing, duplicate detection, bug-versus-feature classification, and self-contained defect report formatting.
SkillAFreshness: AClaude Code +9 - 0.567score
reproduce-issue
dotts-h
Reproduce reported defects through the target app's real UI or CLI on at least two recorded runs, verify existing fixes against baseline and patched builds…
SkillAFreshness: AClaude Code +9 - 0.565score
setup-qstack
dotts-h
Configure which models the qstack how and why skills give their subagents and at what reasoning budget.
SkillAFreshness: AClaude Code +9 - 0.561score
regression-pin
dotts-h
Pin a reproduced bug or regression signal with a focused executable check that fails before the fix and passes after it, or select the closest live…
SkillAFreshness: AClaude Code +9 - 0.561score
principle-build-the-lever
dotts-h
Apply to any non-trivial work, including edits, migrations, analyses, and checks.
SkillAFreshness: AClaude Code +9 - 0.556score
principle-sequence-verifiable-units
dotts-h
Apply to multi-step work such as sweeps, migrations, and runs of similar edits, and to how you stack commits and PRs.
SkillAFreshness: AClaude Code +9 - 0.556score
in-your-own-words
dotts-h
Restate the testing goal, target surface, and risk hypothesis in your own words before test execution.
SkillAFreshness: AClaude Code +9 - 0.556score
principle-explain-the-number
dotts-h
Apply before you trust, report, or act on a number you measured.
SkillAFreshness: AClaude Code +9 - 0.556score
principle-never-block-on-the-human
dotts-h
Apply when tempted to ask 'should I do X?' on reversible work.
SkillAFreshness: AClaude Code +9 - 0.536score
maintain-verification-skill
dotts-h
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature…
SkillAFreshness: AClaude Code +9 - 0.536score
blast-radius
dotts-h
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…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (10 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/dotts-h/qstack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dotts-h
- 0.567score
qstack-mode
dotts-h
Run structured QA workflows in Cursor: test chartering, real-surface reproduction with recorded runs, defect triage, baseline-versus-patch fix verification…
SkillAFreshness: AClaude Code +9 - 0.567score
triage-defect
dotts-h
Triage bug reports with bounded cause tracing, duplicate detection, bug-versus-feature classification, and self-contained defect report formatting.
SkillAFreshness: AClaude Code +9 - 0.567score
reproduce-issue
dotts-h
Reproduce reported defects through the target app's real UI or CLI on at least two recorded runs, verify existing fixes against baseline and patched builds…
SkillAFreshness: AClaude Code +9 - 0.565score
setup-qstack
dotts-h
Configure which models the qstack how and why skills give their subagents and at what reasoning budget.
SkillAFreshness: AClaude Code +9 - 0.561score
regression-pin
dotts-h
Pin a reproduced bug or regression signal with a focused executable check that fails before the fix and passes after it, or select the closest live…
SkillAFreshness: AClaude Code +9 - 0.561score
principle-build-the-lever
dotts-h
Apply to any non-trivial work, including edits, migrations, analyses, and checks.
SkillAFreshness: AClaude Code +9
Cite this page
how skill. Agent Mart. https://agentmart.dev/skills/dotts-h-how (last updated 2026-10-24)