core-dynamic-skills
Internal command support for dynamic Rust crate skill management. Use only when explicitly invoked by /sync-crate-skills, /clean-crate-skills, or /update-crate-skill.
What this skill does
# Dynamic Skills Manager
> **Version:** 2.1.0 | **Last Updated:** 2025-01-27
Orchestrates on-demand generation of crate-specific skills based on project dependencies.
## Concept
Dynamic skills are:
- Generated locally at `~/.claude/skills/`
- Based on Cargo.toml dependencies
- Created using llms.txt from docs.rs
- Versioned and updatable
- Not committed to the rust-skills repository
## Trigger Scenarios
### Prompt-on-Open
When entering a directory with Cargo.toml:
1. Detect Cargo.toml (single or workspace)
2. Parse dependencies list
3. Check which crates are missing skills
4. If missing: "Found X dependencies without skills. Sync now?"
5. If confirmed: run `/sync-crate-skills`
### Manual Commands
- `/sync-crate-skills` - Sync all dependencies
- `/clean-crate-skills [crate]` - Remove skills
- `/update-crate-skill <crate>` - Update specific skill
## Execution Mode Detection
**CRITICAL: Check if agent and command infrastructure is available.**
Try to read: `../../agents/` directory
Check if `/create-llms-for-skills` and `/create-skills-via-llms` commands work.
---
## Agent Mode (Plugin Install)
**When full plugin infrastructure is available:**
### Architecture
```
Cargo.toml
↓
Parse dependencies
↓
For each crate:
├─ Check ~/.claude/skills/{crate}/
├─ If missing: Check actionbook for llms.txt
│ ├─ Found: /create-skills-via-llms
│ └─ Not found: /create-llms-for-skills first
└─ Load skill
```
### Workflow Priority
1. **actionbook MCP** - Check for pre-generated llms.txt
2. **/create-llms-for-skills** - Generate llms.txt from docs.rs
3. **/create-skills-via-llms** - Create skills from llms.txt
### Sync Command
```bash
/sync-crate-skills [--force]
```
1. Parse Cargo.toml for dependencies
2. For each dependency:
- Check if skill exists at `~/.claude/skills/{crate}/`
- If missing (or --force): generate skill
3. Report results
---
## Inline Mode (Skills-only Install)
**When agent/command infrastructure is NOT available, execute manually:**
### Step 1: Parse Cargo.toml
```bash
# Read dependencies
cat Cargo.toml | grep -A 100 '\[dependencies\]' | grep -E '^[a-zA-Z]'
```
Or use Read tool to parse Cargo.toml and extract:
- `[dependencies]` section
- `[dev-dependencies]` section (optional)
- Workspace members (if workspace project)
### Step 2: Check Existing Skills
```bash
# List existing skills
ls ~/.claude/skills/
```
Compare with dependencies to find missing skills.
### Step 3: Generate Missing Skills
For each missing crate:
```bash
# 1. Fetch crate documentation
agent-browser open "https://docs.rs/{crate}/latest/{crate}/"
agent-browser get text ".docblock"
# Save content
# 2. Create skill directory
mkdir -p ~/.claude/skills/{crate}
mkdir -p ~/.claude/skills/{crate}/references
# 3. Create SKILL.md
# Use template from rust-skill-creator inline mode
# 4. Create reference files for key modules
agent-browser open "https://docs.rs/{crate}/latest/{crate}/{module}/"
agent-browser get text ".docblock"
# Save to ~/.claude/skills/{crate}/references/{module}.md
agent-browser close
```
**WebFetch fallback:**
```
WebFetch("https://docs.rs/{crate}/latest/{crate}/", "Extract API documentation overview, key types, and usage examples")
```
### Step 4: Workspace Support
For Cargo workspace projects:
```bash
# 1. Parse root Cargo.toml for workspace members
cat Cargo.toml | grep -A 10 '\[workspace\]'
# 2. For each member, parse their Cargo.toml
for member in members; do
cat ${member}/Cargo.toml | grep -A 100 '\[dependencies\]'
done
# 3. Aggregate and deduplicate dependencies
# 4. Generate skills for missing crates
```
### Clean Command (Inline)
```bash
# Clean specific crate
rm -rf ~/.claude/skills/{crate_name}
# Clean all generated skills
rm -rf ~/.claude/skills/*
```
### Update Command (Inline)
```bash
# Remove old skill
rm -rf ~/.claude/skills/{crate_name}
# Re-generate (same as sync for single crate)
# Follow Step 3 above for the specific crate
```
---
## Local Skills Directory
```
~/.claude/skills/
├── tokio/
│ ├── SKILL.md
│ └── references/
├── serde/
│ ├── SKILL.md
│ └── references/
└── axum/
├── SKILL.md
└── references/
```
---
## Related Commands
- `/sync-crate-skills` - Main sync command
- `/clean-crate-skills` - Cleanup command
- `/update-crate-skill` - Update command
- `/create-llms-for-skills` - Generate llms.txt (Agent Mode only)
- `/create-skills-via-llms` - Create skills from llms.txt (Agent Mode only)
## Error Handling
| Error | Cause | Solution |
|-------|-------|----------|
| Commands not found | Skills-only install | Use inline mode |
| Cargo.toml not found | Not in Rust project | Navigate to project root |
| docs.rs unavailable | Network issue | Retry or skip crate |
| Permission denied | Directory issue | Check ~/.claude/skills/ permissions |
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 — 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.