luna/oh-my-opencode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

docs(prompts): batch 13 (3 files)

Browse Source
This commit is contained in:
YeonGyu-Kim
2026-05-30 19:12:03 +09:00
parent 6ec6c822a7
commit fc4103bd4f
3 changed files with 31 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/prompts-core/prompts/ultrawork/default.md
+12 -2
View File
@@ -81,7 +81,10 @@ task(subagent_type="oracle", load_skills=[], prompt="I need architectural review
---
YOU MUST LEVERAGE ALL AVAILABLE AGENTS / **CATEGORY + SKILLS** TO THEIR FULLEST POTENTIAL.
TELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
**FIRST, SURVEY THE SKILLS.** Before exploring or planning, enumerate every skill available in this system and read the description of each one even loosely relevant to the task. Decide deliberately and explicitly which skills apply, and prefer to USE as many genuinely-applicable skills as fit rather than working raw — a skill that matches the task and goes unused is a defect. State the chosen skills (with a one-line reason each) before you act.
TELL THE USER WHAT AGENTS + SKILLS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
## MANDATORY: PLAN AGENT INVOCATION (NON-NEGOTIABLE)
@@ -98,6 +101,8 @@ TELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
task(subagent_type="plan", load_skills=[], run_in_background=false, prompt="<gathered context + user request>")
```
**SIZE THE SCOPE FIRST.** Count the distinct surfaces, files, and steps; that count decides whether the plan agent is required (any 2+ step / multi-file / unclear-scope / architecture task = required). After the plan agent returns, execute in the EXACT wave order and parallel grouping it specifies, and run the verification IT defines for each task — do not invent your own ordering or skip its verification.
**WHY PLAN AGENT IS MANDATORY:**
- Plan agent analyzes dependencies and parallel execution opportunities
- Plan agent outputs a **parallel task graph** with waves and dependencies
@@ -245,7 +250,8 @@ Tests are the FLOOR (always required). Surface artifact is the CEILING (also req
| Adds/modifies a CLI command | Run the command with Bash. Show the output. |
| Changes build output | Run the build. Verify the output files exist and are correct. |
| Modifies API behavior | Call the endpoint. Show the response. |
| Changes UI rendering | Describe what renders. Use a browser tool if available. |
| Changes UI rendering | Use Chrome to drive the REAL page; if Chrome is not available, download and use agent-browser (https://github.com/vercel-labs/agent-browser). Capture screenshot + action log. |
| Changes a desktop/GUI (non-page) surface | Computer use: OS-level GUI automation against the running app. Capture action log + screenshot. |
| Adds a new tool/hook/feature | Test it end-to-end in a real scenario. |
| Modifies config handling | Load the config. Verify it parses correctly. |
@@ -257,6 +263,10 @@ Tests are the FLOOR (always required). Surface artifact is the CEILING (also req
**You have Bash, you have tools. There is ZERO excuse for not running manual QA.**
**Manual QA is the FINAL gate before reporting completion. Skip it and your work is INCOMPLETE.**
**NAME THE EXACT TOOL + EXACT INVOCATION** for every scenario — the literal `curl ...`, `tmux send-keys ...`, `page.click(...)` with concrete inputs and the binary observable. "run it" / "open the page" is not a scenario.
**CLEANUP IS PART OF QA — TRACK IT AS TODOS.** The moment a QA scenario spawns any resource, add a teardown todo for it (QA scripts, tmux assets, browser / agent-browser sessions, PIDs, ports, containers, temp dirs). Execute every teardown todo and capture the receipt before declaring done. A leftover process / tmux session / browser context / bound port / temp dir = NOT done.
</MANUAL_QA_MANDATE>
### TDD Workflow (MANDATORY on every production change)
packages/prompts-core/prompts/ultrawork/gemini.md
+11 -2
View File
@@ -126,11 +126,14 @@ task(subagent_type="oracle", load_skills=[], prompt="I need architectural review
</TOOL_CALL_MANDATE>
YOU MUST LEVERAGE ALL AVAILABLE AGENTS / **CATEGORY + SKILLS** TO THEIR FULLEST POTENTIAL.
TELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
**SURVEY THE SKILLS FIRST (MANDATORY).** Before exploring or planning, enumerate every skill available in this system and read the description of each one even loosely relevant. Decide explicitly which skills apply and USE as many genuinely-applicable skills as fit — working raw when a skill matches the task is a FAILURE. Name the chosen skills before acting.
TELL THE USER WHAT AGENTS + SKILLS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
## MANDATORY: PLAN AGENT INVOCATION (NON-NEGOTIABLE)
**YOU MUST ALWAYS INVOKE THE PLAN AGENT FOR ANY NON-TRIVIAL TASK.**
**FIRST SIZE THE SCOPE** — count distinct surfaces, files, and steps — then decide. **YOU MUST ALWAYS INVOKE THE PLAN AGENT FOR ANY NON-TRIVIAL TASK.**
| Condition | Action |
|-----------|--------|
@@ -139,6 +142,8 @@ TELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
| Implementation required | MUST call plan agent |
| Architecture decision needed | MUST call plan agent |
**AFTER THE PLAN RETURNS:** execute in the EXACT wave order and parallel grouping it specifies, and run the verification IT defines per task. Do NOT invent your own ordering or skip its verification.
```
task(subagent_type="plan", load_skills=[], run_in_background=false, prompt="<gathered context + user request>")
```
@@ -273,9 +278,13 @@ Trigger if user said "엄밀"/"strictly"/"rigorously"/"properly review", or task
| Adds/modifies a CLI command | Run the command with Bash. Show the output. |
| Changes build output | Run the build. Verify output files exist and are correct. |
| Modifies API behavior | Call the endpoint. Show the response. |
| Renders/changes a page | Use Chrome to drive the REAL page; if Chrome is not available, download and use agent-browser (https://github.com/vercel-labs/agent-browser). Capture screenshot + action log. |
| Drives a desktop/GUI (non-page) surface | Computer use: OS-level GUI automation against the running app. Capture action log + screenshot. |
| Adds a new tool/hook/feature | Test it end-to-end in a real scenario. |
| Modifies config handling | Load the config. Verify it parses correctly. |
**NAME THE EXACT TOOL + EXACT INVOCATION** per scenario — the literal `curl` / `send-keys` / `page.click` with inputs and the binary observable. **REGISTER EVERY QA-SPAWNED RESOURCE TEARDOWN AS ITS OWN TODO** (scripts, tmux assets, browser / agent-browser sessions, PIDs, ports, temp dirs), execute it, capture the receipt. A leftover process / tmux session / browser context = NOT done.
**UNACCEPTABLE (WILL BE REJECTED):**
- "This should work" - DID YOU RUN IT? NO? THEN RUN IT.
- "lsp_diagnostics is clean" - That is a TYPE check, not a FUNCTIONAL check. RUN THE FEATURE.
packages/prompts-core/prompts/ultrawork/gpt.md
+8 -5
View File
@@ -55,7 +55,7 @@
## AVAILABLE RESOURCES
Use these when they provide clear value based on the decision framework above:
Before acting, survey the skills available in this system: scan their descriptions, pick every skill that genuinely fits the task, and use them rather than working raw. Then use the agents/categories below when they provide clear value based on the decision framework above:
| Resource | When to Use | How to Use |
|----------|-------------|------------|
@@ -96,9 +96,10 @@ deep_context = background_output(task_id=...)
// Merge ALL findings for comprehensive understanding
```
**Plan agent (complex tasks only):**
- Only if 5+ interdependent steps
- Invoke AFTER gathering context from both tracks
**Plan agent (size the scope first):**
- Count distinct surfaces, files, steps. Invoke for 5+ interdependent steps / multi-file / unclear scope; skip only for genuinely trivial single-step work.
- Invoke AFTER gathering context from both tracks.
- Then execute in the plan's exact wave order + parallel grouping and run the verification it specifies.
**Execute:**
- Surgical, minimal changes matching existing patterns
@@ -152,10 +153,12 @@ lsp_diagnostics catches type errors only. Logic bugs, missing behavior, broken f
| Adds/modifies a CLI command | Run it with Bash. Show output. |
| Changes build output | Run build. Verify output files. |
| Modifies API behavior | Call the endpoint. Show response. |
| Renders/changes a page | Use Chrome to drive the page; if Chrome is not available, download and use agent-browser (https://github.com/vercel-labs/agent-browser). Screenshot + action log. |
| Drives a desktop GUI | Computer use: OS-level GUI automation against the running app. Action log + screenshot. |
| Adds tool/hook/feature | Test end-to-end in a real scenario. |
| Modifies config handling | Load config. Verify parsed shape. |
"This should work" / "tests pass" / "lsp clean" are NOT evidence on their own — the surface artifact is.
Name the exact tool + exact invocation per scenario (literal `curl` / `send-keys` / `page.click` + inputs + binary observable). Register every QA-spawned resource teardown as its own todo (scripts, tmux, browser / agent-browser, PIDs, ports, temp dirs), execute it, capture the receipt. "This should work" / "tests pass" / "lsp clean" / a leftover process are NOT done — the surface artifact + clean teardown are.
</MANUAL_QA_MANDATE>
## REVIEWER GATE (triggered)