Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Dev Cancel

ASecurity

Cleanly stop an active engineering layer flow (dev-autopilot, dev-deep-interview, dev-plan) and report what was completed. Use when the user says "cancel", "stop", "abort", "cancelomc", or wants to exit a multi-phase dev workflow.

529 stars
0 votes
0 copies
0 views
Added 5/29/2026
ai-agentsgogit

Works with

claude code

Security Analysis

A100/100

Scanned 5/29/2026

$npx -y skills add evolution-foundation/evo-nexus --skill dev-cancel --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dev Cancel?

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

Security grade badge for Dev Cancel
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/evolution-foundation-dev-cancel/badge)](https://www.skillsdirectory.com/skills/evolution-foundation-dev-cancel)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: dev-cancel
description: Cleanly stop an active engineering layer flow (dev-autopilot, dev-deep-interview, dev-plan) and report what was completed. Use when the user says "cancel", "stop", "abort", "cancelomc", or wants to exit a multi-phase dev workflow.
---

# Dev Cancel

Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer — simplified, runtime-free version.

## Use When
- User says "cancel", "stop", "abort", "cancelomc", "stopomc"
- Multi-phase workflow (dev-autopilot, dev-deep-interview, dev-plan, dev-ralplan) is active and the user wants to exit
- Context indicates a long-running dev orchestration that needs a clean stop

## Do Not Use When
- No engineering layer flow is active — just respond conversationally
- The user is canceling a single tool call (Claude Code already handles that)
- The user wants to pause/resume → use the workflow's own pause mechanism instead

## Goal
Stop the active flow cleanly and give the user a structured summary of:
1. **What was completed** before cancel
2. **What was in progress** at cancel time
3. **What was not started**
4. **Where the artifacts live** (spec, plan, code) so the user can resume manually
5. **Recommended next step**

## Workflow

### 1. Detect Active Flow
Look at recent context for signals:
- `dev-autopilot` was invoked → multi-phase pipeline active
- `dev-deep-interview` was invoked → interview loop active
- `dev-plan` was invoked → planning session active
- A `@compass-planner`, `@bolt-executor`, etc. agent was running

### 2. Stop the Flow
- Do NOT call any further agents
- Do NOT continue any in-progress phase
- Do NOT delete artifacts (specs, plans, partial code) — preserve for user inspection

### 3. Generate Cancel Report
Output this structure:

```markdown
## Engineering Layer Cancel Report

**Flow stopped:** {dev-autopilot | dev-deep-interview | dev-plan | other}
**Stopped at phase:** {phase name}
**Reason:** {user request / error / explicit abort}

### Completed
- [phase 1: spec written → workspace/projects/specs/...]
- [phase 2: plan approved → workspace/projects/plans/...]

### In Progress (at cancel time)
- [phase X: implementing Y in file Z]

### Not Started
- [remaining phases]

### Artifacts Preserved
- Spec: `workspace/projects/specs/[C]autopilot-spec-{name}.md`
- Plan: `workspace/projects/plans/[C]autopilot-plan-{name}.md`
- Code changes: see `git status`

### Recommended Next Step
- "Resume manually": pick up from {phase} using {agent} directly
- "Re-run from scratch": delete artifacts and re-invoke `dev-autopilot`
- "Investigate first": review the artifacts before deciding

### Open Questions
[any unresolved decisions the flow was waiting on]
```

## Rules
- **Always preserve artifacts.** Never delete spec/plan files on cancel — the user may want to resume.
- **Never cascade cancels into business layer.** Cancel only stops engineering flows; Clawdia/Flux/etc. routines keep running.
- **Be explicit about what's incomplete.** Don't claim partial work as done.
- **Suggest the cheapest resume path** — usually picking up from where the flow stopped, not restarting.

## Failure Modes To Avoid
- **Silent cancel**: stopping without a report. Always emit the structured summary.
- **Cleanup overreach**: deleting artifacts the user might want.
- **Continuing one more phase**: "let me just finish this last bit". No — stop means stop.
- **Vague status**: "I stopped the workflow." → useless. Always include phase, completed work, and next step.

Attribution

evolution-foundationevolution-foundation
View sourceSee grades on GitHubMore from evolution-foundation →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →