ed/manual_slop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

skill fixes

Browse Source
This commit is contained in:
Edward R. Gonzalez
2026-02-25 22:14:13 -05:00
parent 8abf5e07b9
commit d82c7686f7
2 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.gemini/skills/mma-tier2-tech-lead/SKILL.md
View File

@@ -15,5 +15,5 @@ You are the Tier 2 Tech Lead. Your role is to ensure architectural integrity, al
## Limitations
- Do not write boilerplate or exhaustive feature code yourself.
- Delegate implementation tasks to Tier 3 Workers using `uv python scripts/mma_exec.py --role tier3-worker "[PROMPT]"`.
- For error analysis of large logs, use `uv python scripts/mma_exec.py --role tier4-qa "[PROMPT]"`.
- Delegate implementation tasks to Tier 3 Workers using `uv run python scripts/mma_exec.py --role tier3-worker "[PROMPT]"`.
- For error analysis of large logs, use `uv run python scripts/mma_exec.py --role tier4-qa "[PROMPT]"`.

6
mma-orchestrator/SKILL.md
View File

@@ -11,21 +11,21 @@ To accomplish this, you MUST delegate token-heavy or stateless tasks to "Tier 3
**CRITICAL Prerequisite:**
To avoid hanging the CLI and ensure proper environment authentication, you MUST NOT call the `gemini` command directly. Instead, you MUST use the wrapper script:
`uv python scripts/mma_exec.py --role <Role> "..."`
`uv run python scripts/mma_exec.py --role <Role> "..."`
## 1. The Tier 3 Worker (Heads-Down Coding)
When you need to perform a significant code modification (e.g., refactoring a 50-line+ script, writing a massive class, or implementing a predefined spec):
1. **DO NOT** attempt to write or use `replace`/`write_file` yourself. Your history will bloat.
2. **DO** construct a single, highly specific prompt.
3. **DO** spawn a sub-agent using `run_shell_command` pointing to the target file.
*Command:* `uv python scripts/mma_exec.py --role tier3-worker "Read [FILE_PATH] and modify it to implement [SPECIFIC_INSTRUCTION]. Only write the code, no pleasantries."`
*Command:* `uv run python scripts/mma_exec.py --role tier3-worker "Read [FILE_PATH] and modify it to implement [SPECIFIC_INSTRUCTION]. Only write the code, no pleasantries."`
4. The Tier 3 Worker is stateless and has no tool access. You must take the clean code it returns and apply it to the file system using your own `replace` or `write_file` tools.
## 2. The Tier 4 QA Agent (Error Translation)
If you run a local test (e.g., `npm test`, `pytest`, `go run`) via `run_shell_command` and it fails with a massive traceback (e.g., 100+ lines of `stderr`):
1. **DO NOT** analyze the raw `stderr` in your own context window.
2. **DO** immediately spawn a stateless Tier 4 agent to compress the error.
3. *Command:* `uv python scripts/mma_exec.py --role tier4-qa "Summarize this stack trace into a 20-word fix: [PASTE_SNIPPET_OF_STDERR_HERE]"`
3. *Command:* `uv run python scripts/mma_exec.py --role tier4-qa "Summarize this stack trace into a 20-word fix: [PASTE_SNIPPET_OF_STDERR_HERE]"`
4. Use the 20-word fix returned by the Tier 4 agent to inform your next architectural decision or pass it to the Tier 3 worker.
## 3. Context Amnesia (Phase Checkpoints)