coding
/coding
Implements or changes application code in this repo, step by step with a self-check. Use when adding a feature, changing behaviour, or refactoring code under src/.
- Author
- sudheer554 ↗
- Repository
- claude-code-project-template ↗
- Licence
- MIT
- Last repository change
- 08.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 08.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Implements or changes application code in this repo, step by step with a self-check. Use when adding a feature, changing behaviour, or refactoring code under src/.
Original author description
Implements or changes application code in this repo, step by step with a self-check. Use when adding a feature, changing behaviour, or refactoring code under src/.
How it works
- Design defaults
- Self-check (step 5)
SKILL.md preview
--- name: coding description: Implements or changes application code in this repo, step by step with a self-check. Use when adding a feature, changing behaviour, or refactoring code under src/. --- # Coding Copy this checklist into your reply and tick it off: ``` - [ ] 1. Read the target file, its callers, and its existing tests - [ ] 2. Check docs/conventions.md and docs/decisions.md for anything that applies - [ ] 3. Search for an existing helper before writing a new one - [ ] 4. Make the smallest change that does the job - [ ] 5. Self-check (below) - [ ] 6. Run the tests for the touched area (testing skill) - [ ] 7. Summarise: files changed, why, anything left undone ``` ## Design defaults - New feature or project: plan a fully modular structure first (folders and one-job files), so code is split before it grows, not after. - Inputs and outputs explicit; prefer pure functions for logic. - Keep I/O (network, disk, database, clock) at the edges so core logic stays testable. - Validate external input at the boundary; trust it inside. - Fail loudly with a clear message; never swallow an exception silently. - Calls to outside services (AI providers, payment, email) get a timeout, and a fallback if `docs/architecture.md` lists one. ## Self-check (step 5) 1. Does the diff contain only what the task needs? Remove drive-by edits. 2. Does it break any rule in `CLAUDE.md`? Go through them one by one. 3. Did the format hook report lint errors? Fix them. If any answer fails, fix it and run the self-check again. Go to step 6 only when all three pass.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · sudheer554/claude-code-project-template | 100 | MIT |
| sorah/config | 100 | MIT |
| pssah4/digital-innovation-agents | 100 | MIT |
| vaayne/agent-kit | 90 | MIT |
| Reevias/Prometheus- | 90 | MIT |
| liustack/vibemaster | 90 | MIT |
| skhoroshavin/tandem-skills | 86 | MIT |
Database snapshot: 13.11.2026 · package version c7d9d629b8b7 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100test-first
Use when implementing a feature, fixing a bug, refactoring, or changing behaviour in any codebase, before writing the production code that does it. - 100cli-commands
Use when adding or modifying CLI command (`but` commands) under `crates/but/src`. - 100refactor
Analyze complexity and smells, draft a safe refactor plan, and execute step-by-step with tests. Use when refactoring code or invoking /refactor. - 100refactoring-guide
Fowler-based refactoring recommendations with specific techniques, risk assessment, and step-by-step plans. Use when code needs restructuring and you want a safe execution plan. To first locate structural issues use /architecture-review. - 100coding-standards
Detects code smells, anti-patterns, and readability issues. Use when implementing features, reviewing code, or refactoring. - 100tdd
Test-first implementation discipline. Use when adding a function or feature, fixing a bug, changing existing behavior, or when implementation code already exists with no test covering it.