how
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
Skill by FireTheDevil
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/firethedevil-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
- 31 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- explainer-prompt.md · references/
- explorer-prompt.md · references/
SKILL.md (first lines)
# How For Herdsman launch, discovered definitions, asynchronous results, external isolation, and tool prerequisites, read [Herdsman runtime](../poteto-mode/references/herdsman-runtime.md) when needed. Required capabilities must be available before launch. 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. Use effective discovered definitions and read-only assignments throughout. Models and tools come from definitions, not requests. A missing capability blocks the route. The lead delegates and integrates asynchronous results; leaves report to their owner. ## 1. Assess complexity State your interpretation if the scope is ambiguous. For a narrow question in one module, delegate one pstack-advisor to explore and explain in one pass, with `references/explainer-prompt.md` and no explorer-findings section. Then go to step 4. When in doubt, take this simple path. For a subsystem or cross-cutting question, go to step 2. ## 2. Explore (complex only) Split the question into 2 to 4 distinct angles. Delegate each to a fresh explorer using Herdsman definition: `pstack-how-explorer`, with `references/explorer-prompt.md` and its angle filled in. Continue independent work or end the turn and yield. Do not poll. Integrate all required asynchronous results before step 3. ## 3. Synthesize (complex only) Delegate a fresh pstack-advisor with `references/explainer-prompt.md`, the question, and every exact explorer result ref through files. Do not restate their reports. End the turn and yield when only dependencies remain; integrate its result before presenting. ## 4. Present Present the explainer's output. Light edits for clarity or context are fine. Do not substantially rewrite it. ## Output format Use the sections in `references/explainer-prompt.md`, dropping those that do not apply: Overview, Key Concepts, How It Works, Where Things Live, Gotchas.
From FireTheDevil/pi-pstack-herdsman, MIT.
More from FireTheDevil/pi-pstack-herdsman
- 0.606score
poteto-help
FireTheDevil
Answer questions about Pi pstack setup, workflow selection, and prompt wording without starting the work.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
ketchup
FireTheDevil
Catch up on what changed in this chat in plain words and small evidence-backed visuals, with concise human decisions.
SkillAFreshness: A★ 3Claude Code +9 - 0.581score
interrogate
FireTheDevil
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
benchmark-checklist
FireTheDevil
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
automate-me
FireTheDevil
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how…
SkillAFreshness: A★ 3Claude Code +9 - 0.578score
no-comments
FireTheDevil
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
SkillAFreshness: A★ 3Claude Code +9 - 0.576score
figure-it-out
FireTheDevil
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work reviewed after stepping away.
SkillAFreshness: A★ 3Claude Code +9 - 0.576score
blast-radius
FireTheDevil
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: A★ 3Claude Code +9 - 0.568score
in-your-own-words
FireTheDevil
Restate the user's goals and the problem they are trying to solve.
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 15, 2026 (14 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from FireTheDevil
- 0.606score
poteto-help
FireTheDevil
Answer questions about Pi pstack setup, workflow selection, and prompt wording without starting the work.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
ketchup
FireTheDevil
Catch up on what changed in this chat in plain words and small evidence-backed visuals, with concise human decisions.
SkillAFreshness: A★ 3Claude Code +9 - 0.581score
interrogate
FireTheDevil
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
benchmark-checklist
FireTheDevil
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
automate-me
FireTheDevil
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how…
SkillAFreshness: A★ 3Claude Code +9 - 0.578score
no-comments
FireTheDevil
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
SkillAFreshness: A★ 3Claude Code +9
Cite this page
how skill. Agent Mart. https://agentmart.dev/skills/firethedevil-how (last updated 2026-10-24)