language-aware-planning
Plan a non-trivial change in the target language idioms.
Skill by plantgreytrees
Chalk Labs
Need help deploying language-aware-planning?
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/plantgreytrees-language-aware-planning
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/language-aware-planning
What's inside
- Skill name
language-aware-planning- Description
- Plan a non-trivial change in the target language idioms. Not for small edits.
- License
- MIT
- Instructions
- 49 lines in SKILL.md · view on GitHub
Files (23)
- SKILL.md
- architecture-template.md · references/
- cpp.md · references/
- csharp.md · references/
- data-science.md · references/
- dockerfile.md · references/
- generic.md · references/
- go.md · references/
- idea-template.md · references/
- java.md · references/
- javascript.md · references/
- kotlin.md · references/
- kubernetes.md · references/
- php.md · references/
- plan-template.md · references/
- python.md · references/
- react-native.md · references/
- ruby.md · references/
- rust.md · references/
- shell.md · references/
- swift.md · references/
- terraform.md · references/
- typescript.md · references/
SKILL.md (first lines)
# Language-Aware Planning Plan in the target language from the first sentence. Do not design in language-neutral pseudocode and translate afterwards: the error model, data modeling, abstraction mechanism and concurrency model ARE language decisions, and a neutral plan systematically produces lowest-common-denominator designs that then get transliterated badly. ## Procedure 1. **Name the target language** — detect from repo markers, never assume: `package.json`→JS/TS, `pyproject.toml`/`requirements.txt`→Python, `go.mod`→Go, `Cargo.toml`→Rust, `pom.xml`/`build.gradle`→Java/Kotlin, `Gemfile`→Ruby, `*.sln`/`*.csproj`→C#, `composer.json`→PHP, `*.tf`→Terraform, `Dockerfile`→ container build, `*.kt`/`build.gradle.kts`→Kotlin, `*.swift`/`Package.swift`→ Swift, `.ipynb`/a `train.py`-shaped script→data science/ML, a manifest under `k8s/`/`kubernetes/`/`manifests/`→Kubernetes, a `react-native`/`expo` dependency in `package.json`→React Native (load `react-native.md` alongside `javascript.md`/`typescript.md`, not instead of it). Then Grep for two or three modules that already solve a similar problem — **consistency with this codebase outranks textbook patterns.** 2. Make these five decisions explicit, in the language's own vocabulary: - Error model — one strategy, stated - Data model — make illegal states unrepresentable where the language allows - Public API — real signatures, not descriptions - Abstraction budget — list what you are NOT abstracting, and why - Test seams — how this is tested without mocking the world 3. Read `references/<language>.md` and verify the plan against it. **Load only the one language you need** — `python.md`, `typescript.md`, `javascript.md`, `go.md`, `rust.md`, `java.md`, `csharp.md`, `ruby.md`, `php.md`, `shell.md`, `cpp.md`, `terraform.md`, `dockerfile.md`, `swift.md`, `kotlin.md`, `data-science.md`, `kubernetes.md`, `react-native.md`, or `generic.md` for anything else. `react-native.md` supplements `javascript.md`/`typescript.md` rather than replacing it. The emitted plan follows `references/plan-template.md`. ## Universal constraints - Simplest design that satisfies the stated requirement. An abstraction needs a second concrete implementor or a stated extension requirement — otherwise omit it. Many classic patterns are workarounds for limitations the target language may not have. - One pattern per problem. Never mix error strategies within a module; never mix sync and async access to one resource without an explicit boundary. - Dependencies point inward: domain logic must not import I/O, framework, or transport concerns. - Validate external input at the boundary, parse into typed values, and let the interior assume validity.
From plantgreytrees/craftsman, MIT.
More from plantgreytrees/craftsman
- 0.553score
deep-research
plantgreytrees
Isolated repository research returning a concise summary with file references.
SkillAFreshness: AClaude Code +9 - 0.553score
verification-before-completion
plantgreytrees
Run the real checks and read their output before claiming done.
SkillAFreshness: AClaude Code +9 - 0.523score
test-driven-development
plantgreytrees
Write the failing test first, then the minimum code.
SkillAFreshness: AClaude Code +9 - 0.304score
design-review
plantgreytrees
No description from the publisher yet.
SkillAFreshness: AClaude Code +9 - 0.301score
systematic-debugging
plantgreytrees
No description from the publisher yet.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/plantgreytrees/craftsman
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from plantgreytrees
- 0.553score
deep-research
plantgreytrees
Isolated repository research returning a concise summary with file references.
SkillAFreshness: AClaude Code +9 - 0.553score
verification-before-completion
plantgreytrees
Run the real checks and read their output before claiming done.
SkillAFreshness: AClaude Code +9 - 0.523score
test-driven-development
plantgreytrees
Write the failing test first, then the minimum code.
SkillAFreshness: AClaude 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 language-aware-planning 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
language-aware-planning skill. Agent Mart. https://agentmart.dev/skills/plantgreytrees-language-aware-planning (last updated 2026-10-24)