output-savers
Engineering principles plus plain STE writing in one skill.
Skill by pahlevikun
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/pahlevikun-output-savers
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: backend, writing
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
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/output-savers
What's inside
- Skill name
output-savers- Description
- Engineering principles plus plain STE writing in one skill. Writes the smallest working change (YAGNI, minimal scope, DRY, SOLID, noslop backend filter), reviews for over-engineering, and audits repos for bloat. Replies, commit messages, review comments, and memory files use short Simplified Technical English (pilot and astronaut styles). Detects the job and picks the mode. Use for be brief, save tokens, yagni, minimal scope, is this over-engineered, commit message, review this diff, compress CLAUDE.md, shrink context. Not for prose written for human readers.
- License
- MIT
- Metadata
- version: 3.0.0
- Instructions
- 61 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (36)
- SKILL.md
- SKILL.md · concise/
- SKILL.md · concise/heavy/
- SKILL.md · concise/light/
- commit.md · concise/references/
- compress.md · concise/references/
- crew.md · concise/references/
- modes.md · concise/references/
- review.md · concise/references/
- ste-style.md · concise/references/
- benchmark.ts · concise/scripts/
- cli.ts · concise/scripts/
- compress.ts · concise/scripts/
- detect.ts · concise/scripts/
- scripts.test.ts · concise/scripts/
- tsconfig.json · concise/scripts/
- validate.ts · concise/scripts/
- SKILL.md · principles/
- dry.md · principles/references/
- engineering-principles.md · principles/references/
- review-over-engineering.md · principles/references/
- solid.md · principles/references/
- comments.md · principles/references/super-noslop/
- delivery-gate.md · principles/references/super-noslop/
- index.md · principles/references/super-noslop/
- mandatory-rules.md · principles/references/super-noslop/
- principles-and-cli-copy.md · principles/references/super-noslop/
- slop-patterns.md · principles/references/super-noslop/
- surfaces.md · principles/references/super-noslop/
- agents-md-pointer.md · principles/references/super-noslop/templates/
- architecture-read.md · principles/references/super-noslop/templates/
- audit-after-mode.md · principles/references/super-noslop/templates/
- workflow-gates.md · principles/references/super-noslop/
- yagni.md · principles/references/
- auto-detect.md · references/
- context-hygiene.md · references/
SKILL.md (first lines)
# Output savers One skill with two halves. They work together. - **Principles** keep the work small. Do less. Delete first. Build only what the task needs. See [principles/](principles/SKILL.md). - **STE style** keeps the words small and clear. It uses Simplified Technical English with the habits of pilots and astronauts. See [concise/](concise/SKILL.md). The first half shortens the diff. The second half shortens the reply. Both remove waste without removing facts. ## Step 0: detect the job Do this first and do not announce it. Signals and intensity rules are in [references/auto-detect.md](references/auto-detect.md). | If the user is doing this | Apply | Load | |---|---|---| | Writing or changing code, or choosing a dependency | Minimal scope and YAGNI. Code first, three short lines after. | [engineering-principles.md](principles/references/engineering-principles.md) | | Deciding on an abstraction, or adding "just in case" code | YAGNI, the deletion test, SOLID | [yagni.md](principles/references/yagni.md), [solid.md](principles/references/solid.md) | | Cleaning up duplication | Rule of three, then the jscpd workflow | [dry.md](principles/references/dry.md) | | Touching handlers, services, config, API text, or comments | The noslop filter and the delivery gate | [noslop/index.md](principles/references/noslop/index.md) | | Asking if code is over-engineered or auditing a repo for bloat | A tagged cut list or ranked audit | [review-over-engineering.md](principles/references/review-over-engineering.md) | | Asking for a commit message | A short Conventional Commit, message only | [commit.md](concise/references/commit.md) | | Reviewing a diff or pull request for bugs | One line per finding, with a severity word | [review.md](concise/references/review.md) | | Compressing a memory or instruction file | Backup, rewrite the prose in STE, validate | [compress.md](concise/references/compress.md) | | Delegating work to subagents | Pick the subagent and demand a short result | [crew.md](concise/references/crew.md) | | Facing a huge input (logs, big files, PDFs, screenshots) | Read less: search, filter, convert | [context-hygiene.md](references/context-hygiene.md) | | Asking a question, debugging, or needing a procedure | STE: pilot style, or astronaut style for steps | [ste-style.md](concise/references/ste-style.md) | | Needing prose that a person will read (docs, email, README, release notes) | **Do not compress.** Write plain, complete text. | none | Order of precedence: safety override, explicit user words, detected job. A security warning, an irreversible action, or an unclear sequence always gets full sentences. Never announce the mode. ## How the halves combine - **Coding chat:** the principles card decides what to build. STE decides how to say it. Code comes first. Three short lines follow at most. - **Review:** the review format keeps each finding on one line. The principles supply the tags (`delete`, `stdlib`, `native`, `yagni`, `shrink`). - **Procedures:** astronaut style writes the steps. The principles decide which steps are needed. When the two halves disagree, the stricter rule wins. Never use brevity or "do less" to skip validation, authorization, tests, or a stated requirement. ## Layout | Folder | Holds | |---|---| | [principles/](principles/SKILL.md) | YAGNI, minimal scope, DRY, SOLID, noslop (R-01 to R-38, delivery gate, comment hygiene), over-engineering review | | [concise/](concise/SKILL.md) | STE style, intensity files (`light/`, `heavy/`), commit, review, compress, crew, and the TypeScript compress scripts | | [references/](references/) | Job detection and context hygiene | ## Callers When another skill calls this one, it names the job. Skip detection. - `code-review`: apply noslop in **after** mode to the comment text. Use the review format for each inline comment. Never write one rollup block. - `write-mr-description`: apply noslop in **after** mode to the description. The description is prose for people, so do not compress it. ## Related skills - `safe-refactor`: the change is a behavior-preserving refactor. - `tdd`: the change is a feature or fix that needs a test first. - `noslop`: filter generated backend, UI or test code. - `polyglot-copywriter`: the text is for human readers, not for agents.
From pahlevikun/levistack, MIT.
More from pahlevikun/levistack
- 0.570score
create-jira-story
pahlevikun
Draft or create Jira stories and tasks with a lean Context/Goal/DoD template and plain-language prose via polyglot-copywriter.
SkillAFreshness: AClaude Code +9 - 0.570score
convert-as-skill
pahlevikun
Convert existing material into a skill, or merge existing skills into one.
SkillAFreshness: AClaude Code +9 - 0.570score
create-agent
pahlevikun
Create, audit, test or improve subagents (agents/*.md for Claude Code and Cursor), including prompts, tool and model choice, multi-agent orchestration and…
SkillAFreshness: AClaude Code +9 - 0.570score
create-agents-md
pahlevikun
Create, audit or refresh AGENTS.md files: the repo root, nested package files, and the user-level global file, for Claude Code, Cursor and Codex.
SkillAFreshness: AClaude Code +9 - 0.570score
create-command
pahlevikun
Create, audit or improve slash commands (commands/*.md, .claude/commands, .cursor/commands): saved prompts you run as /name, with arguments and tool…
SkillAFreshness: AClaude Code +9 - 0.570score
create-hook
pahlevikun
Create, wire up, test and debug agent hooks: Claude Code settings.json or plugin hooks, Cursor hooks.json, or a shared hooks/ tree, with working recipes.
SkillAFreshness: AClaude Code +9 - 0.570score
create-rule
pahlevikun
Create, audit or tighten persistent rules for coding agents: .claude/rules/*.md, .cursor/rules/*.mdc, a catalog rules/ tree, CLAUDE.md or AGENTS.md.
SkillAFreshness: AClaude Code +9 - 0.570score
create-skill
pahlevikun
Create, audit, grow or repair agent skills (a folder with SKILL.md) for Claude Code, Cursor, Codex and the skills CLI, including skills that write or run plans.
SkillAFreshness: AClaude Code +9 - 0.570score
super-architecture
pahlevikun
Detect, choose, build, evaluate, migrate and document software architecture.
SkillAFreshness: AClaude Code +9 - 0.570score
super-caching
pahlevikun
Super caching: domain router for web (browser, CDN, service worker, HTTP Cache-Control, BFF/API route cache), mobile (on-device, offline, image cache…
SkillAFreshness: AClaude Code +9 - 0.570score
super-protobuf
pahlevikun
Protocol Buffers (proto3) design, buf.yaml/buf.gen.yaml, Connect and gRPC services, protovalidate, lint and breaking checks, schema evolution, mixed-version…
SkillAFreshness: AClaude Code +9 - 0.570score
super-tech-blueprint
pahlevikun
Choose or generate a target technology stack: compare frameworks with TCO, security and ecosystem scoring, plan a migration, or write a blueprint for a new or…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 5, 2026 (23 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 3.0.0
- License
- MIT
- Repository
- github.com/pahlevikun/levistack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from pahlevikun
- 0.570score
convert-as-skill
pahlevikun
Convert existing material into a skill, or merge existing skills into one.
SkillAFreshness: AClaude Code +9 - 0.570score
create-agent
pahlevikun
Create, audit, test or improve subagents (agents/*.md for Claude Code and Cursor), including prompts, tool and model choice, multi-agent orchestration and…
SkillAFreshness: AClaude Code +9 - 0.570score
create-agents-md
pahlevikun
Create, audit or refresh AGENTS.md files: the repo root, nested package files, and the user-level global file, for Claude Code, Cursor and Codex.
SkillAFreshness: AClaude Code +9 - 0.570score
create-command
pahlevikun
Create, audit or improve slash commands (commands/*.md, .claude/commands, .cursor/commands): saved prompts you run as /name, with arguments and tool…
SkillAFreshness: AClaude Code +9 - 0.570score
create-hook
pahlevikun
Create, wire up, test and debug agent hooks: Claude Code settings.json or plugin hooks, Cursor hooks.json, or a shared hooks/ tree, with working recipes.
SkillAFreshness: AClaude Code +9 - 0.570score
create-rule
pahlevikun
Create, audit or tighten persistent rules for coding agents: .claude/rules/*.md, .cursor/rules/*.mdc, a catalog rules/ tree, CLAUDE.md or AGENTS.md.
SkillAFreshness: AClaude Code +9
Cite this page
output-savers skill. Agent Mart. https://agentmart.dev/skills/pahlevikun-output-savers (last updated 2026-10-24)