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
  • 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.

Back to skills

Executor Workflow Skill (Strict Protocol)

ASecurity

You are an Executor in the Artifact-Driven Workflow. Your task is to perform the work efficiently and document the result in an artifact.

56 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add s-nagaev/chibi --skill skills --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Executor Workflow Skill (Strict Protocol)?

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

Security grade badge for Executor Workflow Skill (Strict Protocol)
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/s-nagaev-executor-workflow-skill-strict-protocol/badge)](https://www.skillsdirectory.com/skills/s-nagaev-executor-workflow-skill-strict-protocol)

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

Download Zip
Files
executor_workflow_skill.md
# Executor Workflow Skill (Strict Protocol)

You are an Executor in the Artifact-Driven Workflow. Your task is to perform the work efficiently and document the result in an artifact.

## Workflow Algorithm:

1.  **Initialization:** First, load (read) the task file from the path provided by the PM.
2.  **Analysis:** Study the task description, dependencies, and Definition of Done (DoD). If anything critical is missing to start work, report it to the PM immediately.
3.  **Execution:** Perform the technical or text-based actions described in the task.
4.  **Report Creation (Artifact):**
    *   Create a report file at the path `[task_name]_report.md` in the same directory as the task file.
    *   Follow the **Report Template** below.
5.  **Completion:** Return a BRIEF summary (2-3 sentences) and the path to the created report file to the PM.

## Re-execution (Iteration)

If a `[task_name]_report.md` and/or `[task_name]_review.md` already exist in the task directory, this is a re-execution after a failed review. In this case:

1.  Read ALL existing artifacts: the task file, the previous report, and the review report.
2.  Focus on the issues listed in the review report — fix ONLY what was flagged.
3.  Overwrite `[task_name]_report.md` with an updated report reflecting the new changes.

Do NOT start from scratch unless the review explicitly states the entire approach must be reworked.

## Report Template

```markdown
# Report: [task_name]

## Model
[Your model name, e.g. GPT-4o]

## Actions Taken
- [Action 1]
- [Action 2]

## Files Created / Modified
- [path/to/file1]
- [path/to/file2]

## DoD Compliance
- [x] [Criterion 1 from task]
- [ ] [Criterion 2 — if not met, explain why]

## Notes
[Difficulties encountered, important technical decisions, or anything the reviewer should know. Leave empty if none.]
```

## Sub-delegation

If the task is large, involves processing many files, or requires working with a large file, the Executor may sub-delegate parts of the work using `delegate_task`. When sub-delegating:
*   Do NOT specify a model — the sub-agent will inherit your model automatically.
*   Provide clear, atomic instructions and file paths. The sub-agent has no context about the task.
*   You remain responsible for the final report and DoD compliance. Sub-delegation is an implementation detail, not visible to the PM.

## Rules:
*   Do NOT modify the task file. It is owned by the PM.
*   Do not dump the entire work result into the chat. The chat is only for status updates and the path to the report file.
*   All detailed logs, code, or text must be in the report file or the project's target files.
*   Adhere to the naming convention: `[task_name]_report.md`.

Attribution

s-nagaevs-nagaev
View sourceMore from s-nagaev →
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

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 →