principles
The twenty-two engineering principles dstack works from, one rule each, grouped as core, architecture, verification, delegation, and meta.
Skill by dumkydewilde
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/dumkydewilde-principles
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: productivity, 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/principles
What's inside
- Skill name
principles- Description
- The twenty-two engineering principles dstack works from, one rule each, grouped as core, architecture, verification, delegation, and meta. Use at the start of any multi-step task, when dstack-mode's todolist says to read the principles, or when another skill names a principle by bolded name and you need its full rule.
- License
- NOASSERTION
- Instructions
- 46 lines in SKILL.md · view on GitHub
Files (23)
- SKILL.md
- boundary-discipline.md · references/
- build-the-lever.md · references/
- encode-lessons-in-structure.md · references/
- exhaust-the-design-space.md · references/
- experience-first.md · references/
- fix-root-causes.md · references/
- foundational-thinking.md · references/
- guard-the-context-window.md · references/
- keep-history-out-of-the-artifact.md · references/
- laziness-protocol.md · references/
- make-operations-idempotent.md · references/
- migrate-callers-then-delete-legacy-apis.md · references/
- minimize-reader-load.md · references/
- model-the-domain.md · references/
- never-block-on-the-human.md · references/
- outcome-oriented-execution.md · references/
- prove-it-works.md · references/
- redesign-from-first-principles.md · references/
- separate-before-serializing-shared-state.md · references/
- sequence-verifiable-units.md · references/
- subtract-before-you-add.md · references/
- type-system-discipline.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from dumkydewilde/agent-skills
- 0.587score
dstack-mode
dumkydewilde
Dumky's rigorous engineering mode for non-trivial work.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
reflect
dumkydewilde
Spawn four parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
dehistorize
dumkydewilde
Strip leaked edit history from an existing artifact: v2 names, 'now supports' docs, '(was X)' UI copy, comments that describe the change instead of the code.
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
authoring-skills
dumkydewilde
Write or edit a SKILL.md that actually changes agent behavior, and package it so both Claude Code and Codex load it.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
interrogate
dumkydewilde
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "review this plan", "attack this plan", "find…
SkillAFreshness: A★ 1Claude Code +9 - 0.559score
architect
dumkydewilde
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: A★ 1Claude Code +9 - 0.539score
setup-dstack
dumkydewilde
Configure which model dstack uses per role.
SkillBFreshness: B★ 1Claude Code +9 - 0.536score
no-comments
dumkydewilde
Spawn comment-sicko, fix accepted findings, and offer encodings for claimed constraints.
SkillBFreshness: B★ 1Claude Code +9 - 0.519score
create-verification-skill
dumkydewilde
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillBFreshness: B★ 1Claude Code +9 - 0.517score
figure-it-out
dumkydewilde
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.
SkillBFreshness: B★ 1Claude Code +9 - 0.514score
arena
dumkydewilde
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 9, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- NOASSERTION
- Repository
- github.com/dumkydewilde/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dumkydewilde
- 0.587score
dstack-mode
dumkydewilde
Dumky's rigorous engineering mode for non-trivial work.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
reflect
dumkydewilde
Spawn four parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
dehistorize
dumkydewilde
Strip leaked edit history from an existing artifact: v2 names, 'now supports' docs, '(was X)' UI copy, comments that describe the change instead of the code.
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
authoring-skills
dumkydewilde
Write or edit a SKILL.md that actually changes agent behavior, and package it so both Claude Code and Codex load it.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
interrogate
dumkydewilde
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "review this plan", "attack this plan", "find…
SkillAFreshness: A★ 1Claude Code +9 - 0.559score
architect
dumkydewilde
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
principles skill. Agent Mart. https://agentmart.dev/skills/dumkydewilde-principles (last updated 2026-10-24)