Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt How does Dijkstra's algorithm find the shortest path in a weighted graph with non-negative edge weights step by step?
What was checked, without and with the skill Checked Without skill With skill Explains priority queue usage in Dijkstra's algorithm Describes updating tentative distances to adjacent vertices
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 25 lines single file
Coding Agent Standards
Purpose
Use this skill to keep code changes predictable, reviewable, and safe.
Default Behavior
Clarify the requested outcome and constraints before editing.
Prefer small, focused changes over broad refactors.
Preserve existing behavior unless a behavior change is requested.
Keep naming, structure, and style consistent with nearby code.
Add or update tests when behavior changes.
Implementation Checklist
Confirm the smallest viable file set to edit.
Handle edge cases and explicit failure paths.
Avoid speculative abstractions and dead code.
Add concise comments only where intent is not obvious.
Run available validation steps before finalizing.
Delivery Format
When reporting completion:
What changed (files and intent).
Why it changed (problem solved or risk reduced).
How it was verified (tests, checks, or manual validation).
Remaining risks, assumptions, or follow-ups.
When it activates Automatically, when a task matches.
Use when creating or editing code, especially when reliability, clarity, and low-risk delivery are required.
Track record Benchmark 13 / 18
test cases passed, vs 16 / 18 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported repowise-dev / claude-code-prompts
skills/coding-agent-standards/SKILL.md
View on GitHub ↗ License MITImported 8/3/2026Version v1