nijaru/second-pass
dot_claude/skills/second-pass/SKILL.md
Use after completing a bug fix, feature, refactor, or tk task when the first implementation taught enough context to replace it with a simpler, cleaner, or more coherent version before finalizing.
development
Updated Apr 25, 2026
$ install --global
skillsauthnpx skillsauth add nijaru/dotfiles second-passInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 9:12 AM22.7s1 file scanned
SKILL.md
- name:
- second-pass
- description:
- Use after completing a bug fix, feature, refactor, or tk task when the first implementation taught enough context to replace it with a simpler, cleaner, or more coherent version before finalizing.
- allowed-tools:
- Bash, Read, Grep, Glob, Edit, Task
Second Pass
Boundary
Second pass is a post-completion rewrite of the just-finished change set. It uses what the first pass revealed, but it does not broaden scope. If the goal is routine behavior-preserving cleanup, use refactor. If the goal is to evaluate a ground-up replacement before implementation, use rewrite.
Iron Law
Do not polish the first pass. Re-derive the minimal final implementation from the now-known problem, then replace any discovery-shaped code that no longer earns its complexity.
Workflow
- Re-read the task, tests, changed files, and any tk logs.
- State what the first pass taught: true constraints, false starts, edge cases, and accidental complexity.
- Define the simpler target shape in one paragraph.
- Remove or reshape the first-pass code that exists only because the problem was still being discovered.
- Reimplement the smallest correct version.
- Run the same verification as the first pass, plus any focused checks for the simplified path.
Rules
- Keep the public behavior and accepted scope fixed unless the user explicitly changes them.
- Prefer one coherent replacement over incremental cleanup.
- Delete fallback branches, temporary names, compatibility shims, and duplicated paths introduced during discovery.
- Preserve useful tests; update tests only when they were coupled to the first-pass structure rather than behavior.
- Stop if the second pass would require an architectural decision outside the completed task.
Output
Report what changed between first pass and second pass, why it is simpler, and the verification result. If the first pass is already the cleanest implementation, say so and leave it unchanged.
Anti-Rationalization
| Excuse | Reality | | :--- | :--- | | "The first pass works." | Correctness is the floor; second pass removes discovery artifacts before they become design. | | "I'll just rename a few things." | Cosmetic edits are refactoring, not second pass. Reconsider the implementation shape. | | "This is a chance to improve nearby code." | Do not expand scope. Use the learned context only for the completed change set. |
Related Skills
nijaru/zig-expert
development
VerifiedTrustedCommunity
Use when writing, migrating, or reviewing Zig code across recent stable versions (0.14-0.16), especially to correct stale syntax or stdlib, build.zig, allocator, formatting, or runtime API knowledge.
SKILL.mdUpdated Apr 22, 2026
nijaru/writer
documentation
VerifiedTrustedCommunity
Use when reviewing or revising text (prose, docs, commits) to remove AI patterns and improve voice/clarity.
SKILL.mdUpdated Apr 22, 2026
nijaru/twitter
content-media
VerifiedTrustedCommunity
Use when fetching X/Twitter post content by URL, or searching for recent X posts.
SKILL.mdUpdated Apr 22, 2026
nijaru/transformers-js
development
VerifiedTrustedCommunity
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.
SKILL.mdUpdated Apr 22, 2026