See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptYou are acting as the primary agent in Plugin mode after completing bootstrap prep steps. What action must be taken regarding workflows?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Identifies and loads the matching workflow | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md35 linessingle file
Mode detection:
- If
RUNNING AS A PLUGIN is in context → Plugin mode
- Else if
get_context_instructions tool is available → MCP mode
- Else → Adhoc mode
Plugin mode:
- Bootstrap rules are loaded via startup hook — do NOT assume prep steps are done
- Create todo tasks (search/discover the tool if needed)
- Locate and execute ALL prep steps defined in the loaded bootstrap rules in full
- DO NOT proceed to any action until all prep steps are confirmed complete
- Identify and load the most matching workflow — a must if you are not subagent
- Create and update all todo tasks per workflow
MCP mode:
- Call
get_context_instructions (blocking gate — do not proceed until complete)
- If output truncated and file path provided — read entire file, preview is NOT enough
- Create todo tasks (search/discover the tool if needed)
- Execute ALL prep steps returned — no skipping, no partial execution
- DO NOT proceed to any action until all prep steps are confirmed complete
- Identify and load the most matching workflow — a must if you are not subagent
- Create and update all todo tasks per workflow
Adhoc mode:
- Read
docs/CONTEXT.md and docs/ARCHITECTURE.md in full
- List
docs/*.md and workspace root *.md files to gather context
All modes:
- Treat context loading as a hard blocking gate, not a background task
- Explicitly confirm all prep steps complete before responding, planning, or executing anything
- If anything fails or is unclear — stop and ask user
Track record
Benchmark
10 / 18
test cases passed, vs 5 / 18 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedgriddynamics / rosetta
instructions/r2/core/skills/load-context/SKILL.md
View on GitHub ↗License Apache-2.0Imported 8/3/2026Version v1