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

Sync

ASecurity

Regenerate every AI tool's config from the agnostic-ai specs, or check for drift without writing. Use after editing anything under .agnostic-ai/, when a generated file looks stale, or when CI reports a drift failure.

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

Works with

cli

Security Analysis

A100/100

Scanned 9/30/2026

$npx -y skills add Chemaclass/agnostic-ai --skill sync --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sync?

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

Security grade badge for Sync
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/chemaclass-sync/badge)](https://www.skillsdirectory.com/skills/chemaclass-sync)

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: sync
description: Regenerate every AI tool's config from the agnostic-ai specs, or check for drift without writing. Use after editing anything under .agnostic-ai/, when a generated file looks stale, or when CI reports a drift failure.
---

# sync

Emits one set of specs to every configured target in its native format.

## Steps

1. Run `agnostic-ai sync`. It writes only the files whose content changed, so `git status` after a no-op run is empty.
2. Read the summary. Each line names a target and the paths it wrote.
3. Show the user the diff: `git diff --stat` (or `git status --short` when generated files are gitignored).

## Checking instead of writing

`agnostic-ai sync --check` compares planned output against what is on disk and writes nothing. Exit 0 means no drift; non-zero lists the stale files with counts. Add `--diff` to print the change per file. That is the CI gate:

```yaml
- run: agnostic-ai sync --check --diff
```

The CLI must be installed on the runner first. The CI page (https://agnostic-ai.org/docs/ci/) shows the npm dev dependency and the pinned `scripts/install.sh` setups.

When `--check` fails, decide by what changed:

- A spec was edited and the generated file lags (listed as out of date): run `agnostic-ai sync` and commit both.
- The CLI was upgraded and output shifted: run `sync`, review the diff, and commit it as a regeneration with no semantic change.
- Someone hand-edited a generated file (listed as edited locally): their edit is about to be lost. Move the change into the matching spec under `.agnostic-ai/`, then `sync`.

## Notes

- `agnostic-ai sync --watch` re-emits on every save, touching only affected targets. Useful while authoring several specs.
- `agnostic-ai sync --backup` keeps a `.bak` beside each overwritten file; `agnostic-ai revert` restores them. Without `--backup`, `revert` deletes generated files.
- `agnostic-ai status` reports spec counts, configured targets, the last sync time, and whether output is stale. `agnostic-ai doctor` is the stricter pre-merge check.
- A warning about an unsupported kind means the target has no surface for it (for example hooks on a target with no hook system). Silence it per project with `on-unsupported: silent`.
- Never resolve drift by editing generated files. The spec is the source of truth.

Attribution

ChemaclassChemaclass
View sourceSee grades on GitHubMore from Chemaclass →
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', ...

698431 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 →