refactor(engineering-manager): extract implementation orchestration into a canonical skill#66
Open
IgorWnek wants to merge 6 commits into
Open
refactor(engineering-manager): extract implementation orchestration into a canonical skill#66IgorWnek wants to merge 6 commits into
IgorWnek wants to merge 6 commits into
Conversation
Contributor
Author
|
Everything up to date, added changelog entries, ready for review. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR refactors the lower-tier implementation orchestration flow so the
GPT-5.4 miniorchestrator can execute it more reliably.The main change is moving the canonical implementation workflow out of
tsh-engineering-manager.agent.mdandtsh-implement.prompt.mdinto a single non-user-invocable skill:tsh-orchestrating-implementation.As a result:
tsh-engineering-managerbecomes the WHO-only orchestrator/tsh-implementbecomes a thin triggerBehavior preservation
This refactor preserves the existing implementation-orchestration workflow branches and keeps the downstream specialist-agent routing model intact.
The only intentional behavior change is:
Why
Architecture overview
flowchart LR U[User / task input] --> P["tsh-implement.prompt.md\nthin trigger<br>GPT-5.4 mini"] P --> A["tsh-engineering-manager.agent.md\nWHO / persona / delegation roster / tool rules<br>GPT-5.4 mini"] A --> S["tsh-orchestrating-implementation\nSKILL.md<br>canonical workflow<br>Step 0 / Quick Flow / Full Flow<br>todo protocol / execution-plan step / quality gates"] S --> I1["Internal prompts<br>9 specialist agents + 12 routed prompts"] I1 --> I2["tsh-architect<br>`tsh-plan-reviewer`<br>`tsh-context-engineer`<br>`tsh-software-engineer`<br>`tsh-devops-engineer`<br>`tsh-code-reviewer`<br>`tsh-e2e-engineer`<br>`tsh-ui-reviewer`<br>`tsh-prompt-engineer`"]