load-context-bundle
Reload previous session context from a context bundle file. Use to resume work from a previous session.
What this skill does
# Load Context Bundle
Reload previous session context from a context bundle file.
## Arguments
- `$1`: Path to the context bundle JSONL file
## Instructions
You are reloading context from a previous agent session to continue work.
### Step 1: Read Bundle File
Read the JSONL bundle file at the path specified in `$1`.
Each line is a JSON object with one of these formats:
```json
{"operation": "read", "file_path": "path/to/file", "limit": 100, "offset": 0}
{"operation": "write", "file_path": "path/to/file", "content_length": 500}
{"operation": "prompt", "prompt": "truncated user prompt..."}
```
### Step 2: Analyze Bundle
Extract and analyze:
1. All unique file paths accessed
2. Read operations with their parameters
3. User prompts to understand work done
### Step 3: Deduplicate and Optimize
For each unique file, determine optimal read parameters:
**Deduplication Rules:**
1. If ANY entry for a file has no limit/offset -> Read entire file
2. If multiple entries with parameters -> Choose largest limit, prefer offset 0
3. If all have offset > 0 -> Choose entry reading furthest into file
4. If >3 entries for same file -> Read entire file (frequent access = important)
### Step 4: Load Context
Read each unique file ONLY ONCE with optimal parameters:
```text
For each file in deduplicated list:
- Read with determined parameters
- Note what was loaded
```
### Step 5: Understand Story
Based on user prompts and file operations, construct understanding of:
- What was the previous agent working on?
- What files were central to the work?
- What was the progression of changes?
- What might be next?
### Step 6: Report
## Output
Report context restoration:
```markdown
## Context Bundle Loaded
**Bundle:** [filename]
**Session:** [session_id if available]
### Previous Work Summary
Based on prompts and file operations, the previous agent was:
[Summary of work done]
### Files Restored
| File | Access Count | Loaded |
| --- | --- | --- |
| file1.ts | 5 | Full |
| file2.md | 2 | Full |
| file3.py | 1 | Partial (lines 1-100) |
### Context Restored
- **Files loaded:** [count]
- **Estimated tokens:** [estimate]
- **Work continuity:** [assessment]
### Ready to Continue
[What you're now prepared to do based on restored context]
### Gaps Identified
[Any context that couldn't be restored or may be stale]
```
## Notes
- Context bundles are created by hooks that track file operations
- This enables continuation of work across agent instances
- Bundle files use JSONL format (one JSON object per line)
- See @context-priming-patterns.md for priming vs bundles comparison
- See @rd-framework.md for context management strategies
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.