coding-principles
Software coding principles for planning and performing code changes.
Skill by AlterEgo7
Chalk Labs
Need help deploying coding-principles?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/alterego7-coding-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: testing, devops, 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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/coding-principles
What's inside
- Skill name
coding-principles- Description
- Software coding principles for planning and performing code changes. Always use alongside planning skills when a plan is intended to produce code, tests, build, CI, or configuration changes; also use during implementation, editing, refactoring, testing, debugging, and review. Do not use for documentation-only work, planning with no intended software change, or operational summaries.
- License
- MIT
- Instructions
- 43 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Coding Principles
## Scope
- Make the smallest safe change that fully satisfies the requirement; avoid speculative work and unrelated refactors.
- Preserve existing implementations. Do not rewrite or replace them, or add backward-compatibility behavior, without explicit approval.
- Prefer simple, maintainable solutions. Remove duplication introduced or exposed by the change when that stays within scope; do not broaden the task only to deduplicate unrelated code.
- Follow the nearest repository instructions and the surrounding code's conventions.
## Clarity
- Name code for its current domain purpose, not its history, implementation mechanism, or unnecessary pattern jargon.
- Prefer clear names for identifiers (variables, class, traits etc) over short names.
- Import symbols and use their declared class, type, function, or value names without namespace prefixes whenever this is unambiguous. When names conflict, first prefer an import rename or alias in languages that support it; otherwise use the shortest namespace prefix that resolves the ambiguity. Use longer or fully qualified names only when neither option is available.
For example, in Scala:
```scala
import example.library.{Config as LibraryConfig, Parser}
val parser = Parser(...)
val config = LibraryConfig(...)
```
Prefer this over repeating `example.library.Parser(...)` or another unnecessarily long namespace at each use site.
- Add a short, precise comment only when it usefully explains non-obvious rationale that the code cannot express clearly; when in doubt, omit it.
- For necessary comments about an entire declaration, prefer the language's supported documentation-comment format, such as Javadoc, Scaladoc, or equivalent. Use a plain code comment only when a documentation comment is inappropriate.
- Keep comments current and preserve existing comments; only remove or correct one when it is demonstrably false. Do not narrate change history.
## Verification
- Keep planning, review, and verification proportional to the task's scope and risk. Require only checks that can materially affect the requested behavior.
- Test real behavior. Mocks may isolate collaborators, but assertions must cover the subject's behavior; do not use mocks in end-to-end tests.
- Do not delete or weaken failing tests; preserve meaningful coverage for changed behavior.
- Run relevant validation and inspect its output. Do not ignore, suppress, or misreport failures.
- Do not block or iterate on optional, redundant, unrelated, or pre-existing validation concerns; note them briefly and proceed. Investigate failures only when the change caused them or they undermine confidence in the requested outcome.
- Stop once sufficient evidence shows that the requested behavior works. Do not pursue low-impact verification rabbit holes or additional checks that cannot change the conclusion.
## Debugging
- Diagnose and fix root causes, not symptoms or workarounds. Reproduce the failure, prove the cause with the smallest failing case, and verify the fix against it.From AlterEgo7/agent-skills, MIT.
More from AlterEgo7/agent-skills
- 0.559score
commit-messages
AlterEgo7
VCS commit message format.
SkillAFreshness: AClaude Code +9 - 0.556score
scala-coding-preferences
AlterEgo7
Personal Scala coding preferences.
SkillAFreshness: AClaude Code +9 - 0.524score
technical-writing
AlterEgo7
Technical writing for software and computer engineering.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/AlterEgo7/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AlterEgo7
- 0.559score
commit-messages
AlterEgo7
VCS commit message format.
SkillAFreshness: AClaude Code +9 - 0.556score
scala-coding-preferences
AlterEgo7
Personal Scala coding preferences.
SkillAFreshness: AClaude Code +9 - 0.524score
technical-writing
AlterEgo7
Technical writing for software and computer engineering.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get coding-principles running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
coding-principles skill. Agent Mart. https://agentmart.dev/skills/alterego7-coding-principles (last updated 2026-10-24)