1password
Use when needing to fetch, read, store, or manage secrets and credentials. Triggers on "get secret", "fetch password", "store credential", "1password", "op read", "vault", or when a task requires API keys, tokens, or passwords that might be in 1Password.
What this skill does
# Secret & Credential Management
## ๐ซ SCOPE โ READ THIS FIRST ๐ซ
**1Password (`op` CLI) is STRICTLY for Claude Code's use during coding.** It is for fetching a secret value you need **right now, in this session**, to inject into a config file, paste into a dashboard, run a one-off curl, call an API during investigation, or similar **development-time** work.
**NEVER write `op read` / `op item get` into code or scripts that will be run later by:**
- A user (operator shell)
- CI/CD pipelines (GitHub Actions, etc.)
- Production services
- Other automated systems
- A cron job
**Why:** production scripts must receive secrets via environment variables injected by the caller (operator, CI, secret manager sidecar). Baking `op` calls into a script creates a brittle dependency on a specific developer's laptop + biometric auth, leaks the choice of secret store into every user of the script, and silently breaks in any environment where `op` isn't signed in.
**Correct pattern for scripts that need secrets:**
```bash
# In the script โ require env vars, never fetch
if [[ -z "${API_KEY:-}" ]]; then
echo "Error: API_KEY not set. Export it before running." >&2
exit 1
fi
curl -H "Authorization: Bearer $API_KEY" ...
# Operator invokes manually (pulls from 1Password once, in their shell):
export API_KEY=$(op read "op://Vault/Item/field" --account my.1password.eu)
./scripts/do-thing.sh
# Or in CI/CD:
# - GitHub Actions secrets โ job env
# - Set once via `gh secret set API_KEY`
```
**If you catch yourself writing `op read` inside a `.sh` file, STOP.** Change it to read from an env var and document in the script header that the caller must set the var.
---
## Lookup Priority
**Always try sources in this order โ only escalate to the next if the previous doesn't have what you need:**
1. **Project `.env` files** โ most project secrets live here (API keys, Supabase keys, database URLs)
2. **CLI tools** โ use the service's own CLI when available (e.g., `npx supabase` for Supabase credentials)
3. **Shell environment / `.zshrc`** โ tokens exported globally (e.g., `$GITHUB_PERSONAL_ACCESS_TOKEN`)
4. **1Password (`op` CLI)** โ last resort, only for secrets that don't exist in `.env` or `.zshrc`
### Project .env Files
```bash
# Read directly โ no biometric prompt needed
grep SUPABASE_SERVICE_ROLE_KEY backend/.env
```
### Supabase Credentials (Preferred Method)
```bash
# Local Supabase โ use the CLI, never 1Password
npx supabase status # Shows all URLs, keys, connection strings
npx supabase status -o env # Machine-readable key=value format
```
### Shell Environment
```bash
# Tokens already exported in .zshrc
echo $GITHUB_PERSONAL_ACCESS_TOKEN
echo $RENDER_TOKEN
```
## 1Password (Last Resort)
Only use `op` for secrets that live exclusively in 1Password and aren't available via `.env`, CLI tools, or shell environment. Examples: Apple ASC credentials, tokens not exported anywhere else.
### Vaults
| Vault | Account | Contents |
|-------|---------|----------|
| **What-If** | my.1password.eu | Linear, Cloudflare, Supabase, Grafana, Render, Sentry, Codacy, Chatbot, Admin |
| **Hyperglot** | my.1password.eu | Apple/ASC, Supabase, Google |
| **Dev Tools** | my.1password.eu | GitHub, Claude Code, Gemini, Jira, Postman, Google Stitch, 21st Dev |
### Fetch a Secret
```bash
# Single field from an item
op read "op://What-If/Linear/WHATIF_LINEAR_TOKEN" --account my.1password.eu
# All fields from an item
op item get "Linear" --vault "What-If" --account my.1password.eu
# List items in a vault
op item list --vault "What-If" --account my.1password.eu
```
### Store a New Secret
```bash
# Add to existing item
op item edit "Linear" --vault "What-If" --account my.1password.eu "NEW_FIELD[password]=secret_value"
# Create new item
op item create --category="API Credential" --title="Service Name" --vault="What-If" --account my.1password.eu "FIELD_NAME[password]=secret_value"
```
### Inject Into Environment
```bash
# Single export
export WHATIF_LINEAR_TOKEN=$(op read "op://What-If/Linear/WHATIF_LINEAR_TOKEN" --account my.1password.eu)
# Run command with injected secrets
op run --env-file=.env.tpl -- python script.py
```
### Multi-Account Access
The CLI can access both accounts โ always pass `--account`:
- `my.1password.eu` โ personal vaults (What-If, Hyperglot, Dev Tools)
- `whatifspaces.1password.eu` โ team vaults (Employee, Shared)
### Caching Fetched Secrets โ REQUIRED PATTERN
**Every `op read` / `op item get` triggers a biometric prompt (Touch ID).** Each Claude Code Bash tool call runs in a **brand new shell session** โ shell variables DO NOT persist between Bash calls. So `MY_KEY=$(op read ...)` in one call is GONE in the next.
**You MUST use this pattern from now on for any secret you'll need more than once:**
**Step 1 (first call only) โ write secret to a chmod-600 temp file:**
```bash
umask 077 && op read "op://Vault/Item/field" --account my.1password.eu > /tmp/.my_secret && chmod 600 /tmp/.my_secret
```
For multiple secrets from one item, write `export` lines:
```bash
umask 077 && op item get "Cloudflare" --vault What-If --account my.1password.eu --format json \
| python3 -c "
import json, sys
item = json.load(sys.stdin)
fields = {f.get('label'): f.get('value') for f in item.get('fields', []) if f.get('label')}
print(f'export CF_TOKEN={fields[\"CLOUDFLARE_API_TOKEN\"]}')
print(f'export CF_ACCOUNT={fields[\"CLOUDFLARE_ACCOUNT_ID\"]}')
" > /tmp/.cf_creds && chmod 600 /tmp/.cf_creds
```
**Step 2 (every subsequent call) โ source the file, NEVER re-call op:**
```bash
source /tmp/.cf_creds && curl -H "Authorization: Bearer $CF_TOKEN" "https://api.cloudflare.com/..."
```
**Step 3 (end of work) โ clean up:**
```bash
rm -f /tmp/.cf_creds /tmp/.my_secret
```
**ANTI-PATTERNS โ never do these:**
```bash
# โ BAD โ biometric prompt in every call
curl -H "Bearer $(op read '...' --account my.1password.eu)" ...
curl -H "Bearer $(op read '...' --account my.1password.eu)" ...
# โ BAD โ variables don't survive across Bash tool calls
# Call 1:
TOKEN=$(op read "..." --account my.1password.eu) && curl -H "Bearer $TOKEN" ...
# Call 2:
curl -H "Bearer $TOKEN" ... # $TOKEN is undefined here, will fail or send empty
```
**Acceptable shortcut โ single Bash call with everything:**
If ALL your work fits in one bash invocation, you can fetch and reuse without temp files:
```bash
KEY=$(op read "..." --account my.1password.eu) && \
curl ... -H "Authorization: Bearer $KEY" && \
curl ... -H "Authorization: Bearer $KEY"
```
But the moment you need a follow-up Bash call, switch to the temp-file pattern.
## Important Notes
- **Prefer `.env` and CLI tools over 1Password** โ faster, no biometric prompt
- **Always use `--account` flag** with `op` โ multiple accounts require explicit selection
- **Always cache fetched secrets** โ `op` requires biometric auth on every call; fetch once and store in a shell variable
- **Never print secrets to stdout** unless the user explicitly asks
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only โ no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.