Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

1b1

ASecurity

Walk through items 1-by-1 (findings, tasks, issues, TODOs). Triggers: "one by one" | "walk through" | "1b1" | "process each item" | "review one by one" | "go through each" | "handle them one at a time" | "step through".

9 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsgobashgit

Security Analysis

A100/100

Scanned 9/23/2026

Install to Claude Code

$npx -y skills add Roxabi/roxabi-plugins --skill 1b1 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of 1b1?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for 1b1
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/roxabi-1b1/badge)](https://www.skillsdirectory.com/skills/roxabi-1b1)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: 1b1
description: 'Walk through items 1-by-1 (findings, tasks, issues, TODOs). Triggers: "one by one" | "walk through" | "1b1" | "process each item" | "review one by one" | "go through each" | "handle them one at a time" | "step through".'
version: 0.2.0
argument-hint: '[items description]'
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, ToolSearch
---

# 1b1 — One by One

Let:
  ι := single item from the list
  Ι := full list of items to process
  D := [] — deferred items accumulator

Walk through Ι from conversation one at a time. ∀ ι: brief context → ask decision → execute.

## Instructions

### 1. Identify Ι

Scan conversation for most recent list (review findings, plan tasks, GitHub issues, TODOs, any enumerated list).

Argument ∃ (e.g. `/1b1 review findings`) → narrow to matching list.

| Condition | Action |
|-----------|--------|
| Ι ∄ | → ask user |
| Multiple lists ∃ | → present choice |

### 2. ∀ ι ∈ Ι (sequential)

#### 2a. Investigate

ι references file → read relevant lines + surrounding context. ι references issue → `gh issue view`. Trace root cause — ¬stop at symptom.

**Root cause first:** before presenting options, understand *why* ι exists. Read code, check history, follow references. Analysis must be grounded in evidence, ¬speculation.

#### 2b. Brief

```
── Item {N}/{|Ι|}: {title} ──

Summary:        {what the item is and its root cause — 2-3 lines}
Benefit:        {what improves if we act on it}
Tradeoff:       {cost, risk, or complexity of acting}
Recommendation: {Fix now | Defer | Skip | Reject} — {1-line rationale}
```

#### 2c. Ask Decision

→ present choice Options adapted to ι type. Always include **Skip**.

| Item type | Options |
|-----------|---------|
| Code findings | **Fix now** · **Reject** (invalid) · **Skip** · **Defer** (valid, not urgent) |
| Tasks / plan items | **Do it** · **Skip** · **Modify** · **Remove** |
| Issues / TODOs | **Act on it** · **Skip** · **Defer** |
| Generic | **Act** · **Skip** · **Defer** |

#### 2d. Execute

| Decision | Behavior |
|----------|----------|
| Fix / Do it / Act | Perform action, show brief confirmation |
| Reject | Acknowledge invalid, discard, continue |
| Skip | Next ι silently |
| Defer | Append to D, continue |
| Modify | → ask userfor changes → execute modified |
| Remove | Acknowledge, continue |

### 3. Summary

```
── 1b1 Complete ──

Processed: {|Ι|} items
  Acted on:  {count}
  Rejected:  {count}
  Skipped:   {count}
  Deferred:  {count}
  Removed:   {count}

Deferred items:
  1. {title}
  2. {title}
```

D ≠ ∅ → present choice **Process deferred now** | **Done**.

## Edge Cases

| Scenario | Behavior |
|----------|----------|
| Ι ∄ | → ask userwhat to walk through |
| Multiple lists ∃ | → present choice|
| User stops mid-way | End early, show summary of processed |
| ι references files | Read relevant sections before brief |
| ι already resolved | Note in brief, ask user to confirm skip |
| \|Ι\| = 1 | Still brief + ask — ¬skip flow |

## Safety Rules

1. Always investigate then brief before asking — ¬present decision without root cause analysis
2. One ι at a time — ¬batch multiple into one question
3. Track all decisions — maintain tally for summary
4. Respect user pace — ¬rush or skip ahead

$ARGUMENTS

Attribution

RoxabiRoxabi
View sourceMore from Roxabi →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →