diff
/diff
Compare a local routine .md file against its cloud state field by field. Read-only, no API writes. Invoke when the user says "diff <file>", "what's changed in <file>", or wants to preview drift between local and cloud before deploying.
- Author
- hamzafer ↗
- Repository
- claude-routines ↗
- Licence
- MIT
- Last repository change
- 18.05.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 18.05.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Compare a local routine .md file against its cloud state field by field. Read-only, no API writes. Invoke when the user says "diff <file>", "what's changed in <file>", or wants to preview drift between local and cloud before deploying.
Triggers from the description
Original author description
Compare a local routine .md file against its cloud state field by field. Read-only, no API writes. Invoke when the user says "diff <file>", "what's changed in <file>", or wants to preview drift between local and cloud before deploying.
How it works
- Procedure
- Tracked fields (compare and report differences)
- Read-only fields to skip
- Output format
- Whitespace handling
- Note on the model field
- Bulk diff
- See also
SKILL.md preview
---
name: diff
description: Compare a local routine .md file against its cloud state field by field. Read-only, no API writes. Invoke when the user says "diff <file>", "what's changed in <file>", or wants to preview drift between local and cloud before deploying.
---
# claude-routines:diff
Compare local vs cloud. Useful before `deploy` to see exactly what would change.
## Procedure
1. Parse the file's frontmatter and body. Expand `{{include}}` directives in the body (same as deploy does).
2. Read the file's `trigger_id`. If absent, abort with: `"no trigger_id in frontmatter; use create first"`.
3. Call `RemoteTrigger` with `action: "get"` and `trigger_id: <id>`.
4. Compare each tracked field. Skip read-only fields entirely.
## Tracked fields (compare and report differences)
- `name` (string equality)
- `cron_expression` or `run_once_at` (string equality on whichever is populated)
- `enabled` (bool equality)
- `job_config.ccr.environment_id` (string equality)
- `job_config.ccr.session_context.model` (string equality; treat absent on either side as equal)
- `job_config.ccr.session_context.allowed_tools` (set comparison; report added/removed individually)
- `job_config.ccr.session_context.sources` (list of objects; compare by `url`)
- `mcp_connections` (list of objects; compare by `connector_uuid`)
- Prompt body (compare file's expanded body against `job_config.ccr.events[0].data.message.content`)
## Read-only fields to skip
`created_at`, `updated_at`, `next_run_at`, `creator`, `ended_reason`, `api_token_hint`, `persist_session`, `enabled_plugins`, `extra_marketplaces`, `outcomes`, `last_fired_at`.
## Output format
```
trig_01ABC... Norway News Digest
cron: "0 7 * * *" -> "0 8 * * *"
allowed_tools: +Bash -KillBash
prompt: 3 lines changed (+42 chars)
--- Send a Norway news digest with ONLY NEW stories...
+++ Send a Norway news digest from the last 24 hours...
3 fields differ.
```
If everything matches:
```
trig_01ABC... Norway News Digest
in sync.
```
## Whitespace handling
Trailing whitespace and trailing newlines are sometimes added or stripped by Anthropic's normalization. Report these as a special note: `prompt: trailing whitespace differs (semantically identical)`. Don't show this as a hard difference.
## Note on the model field
The API GET response does NOT echo the `model` field even when it's set. If your local file has `model: claude-opus-4-7` but the cloud response shows no model, treat this as `unknown - cannot verify`. Don't report it as a diff. (Verified 2026-05-14.)
## Bulk diff
For `diff all`, see the `bulk` skill.
## See also
- `dry-run deploy <file>` to see the exact body that would be sent on deploy
- `deploy <file>` to apply the changes after reviewing the diff
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · hamzafer/claude-routines | 100 | MIT |
| Alejo2075/claude-code-aws | 90 | MIT |
| mmurakaru/cueloop | 81 | Apache-2.0 |
Database snapshot: 13.11.2026 · package version 1b9ecf06f67a (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90deploy
Deploy a Claude Code routine from a local .md file. Routes to create or update based on whether the file's frontmatter has a trigger_id. Invoke when the user says "deploy <file>", "push <file>", "ship <file>", or asks to publish a routine to the cloud. - 100drift-detector
Detect infrastructure drift between Terraform state and actual cloud resources. Identifies unmanaged resources, manual changes, and configuration drift. Use when: - User asks to check for infrastructure drift - User wants to find unmanaged cloud resources - User mentions "drift… - 100deploying
Guides deployment of Race Condition to a GCP project. Use when deploying to the cloud, setting up infrastructure with Terraform, or troubleshooting a deployment. This is for cloud deployment -- for local development, use the getting-started skill instead. - 100get
Fetch a single Claude Code routine by its trigger_id and write it to a local .md file. Invoke when the user says "get <trigger_id>" or asks to download/inspect one specific routine from the cloud. - 100diff-files
This skill should be used when the user asks to "compare files", "diff these files", "what changed between", "show differences between", "compare versions", or mentions keywords related to file comparison and difference analysis. - 90review
Compare an API contract with the routes the templates declare, and report the differences. Use to find drift between documentation and infrastructure code.