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

Graph Save

ASecurity

Persist the most recent /graph run's workflow script to

2 stars
0 votes
0 copies
0 views
Added 9/3/2026
ai-agentsrustgoapi

Works with

cliapi

Security Analysis

A100/100

Scanned 9/3/2026

Install to Claude Code

$npx -y skills add ayaangazali/graph-engineering --skill graph-save --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Graph Save?

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

Security grade badge for Graph Save
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ayaangazali-graph-save/badge)](https://www.skillsdirectory.com/skills/ayaangazali-graph-save)

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

Download Zip
Files
SKILL.md
---
name: graph-save
description: Persist the most recent /graph run's workflow script to
  .claude/workflows/<name>.js so it becomes a reusable /command in this project.
argument-hint: "[name]"
disable-model-invocation: true
---

# Graph-save: keep a graph as a replayable command

Persist the most recently run graph so it can be replayed as `/<name>` — same DAG,
new inputs via `args`.

## Procedure

1. **Locate the script.** Every Workflow invocation persists its script and returns
   the path in the tool result (under the session directory). Use the most recent
   run from this conversation.
   - No graph has run this session → say so and suggest `/graph <goal>` first; do
     not reconstruct a script from memory.
   - The last run used the **fallback engine** (no Workflow script exists) → offer
     to author a fresh script from the recorded DAG and schemas, clearly labeled
     as untested, or decline — never present a reconstruction as the tested run.
2. **Name it.** Use `$ARGUMENTS` kebab-cased; if empty, propose a name derived from
   the graph's goal and ask. Validate the result is legal kebab-case (it becomes
   `meta.name` and the `/command`).
3. **Check for collisions** before writing: an existing file at
   `.claude/workflows/<name>.js`, or a known command/skill with the same name.
   On collision, require explicit confirmation to overwrite, else suggest a
   suffixed name.
4. **Read the script file**, then adjust for reuse:
   - `meta.name` → the chosen name; `meta.description` → one generic line;
     populate `meta.whenToUse`.
   - Generalize the input: the goal/targets come from `args`
     (`const GOAL = (typeof args === "string" && args.trim()) || ""` with a
     helpful error return) — hard-coded file lists or findings from the original
     run must not survive into the template.
   - Add a comment header with 2–3 realistic example invocations derived from the
     just-completed run: `// examples: /<name> "audit src/api", /<name> "src/auth"`.
5. **Write** to `<project-root>/.claude/workflows/<name>.js` (create the directory
   if needed).
6. **Confirm and offer a smoke test:**
   - Available as `/<name> <input>` from the next session (or immediately via
     `Workflow({name: '<name>', args})`).
   - Offer to replay it now with the smallest example to confirm the generalized
     `args` plumbing works before anyone trusts it as a team command.
   - Project workflows are shared with everyone who clones the repo; for
     cross-project personal use, offer to copy to `~/.claude/workflows/<name>.js`.

Attribution

ayaangazaliayaangazali
View sourceMore from ayaangazali →
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 →