Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ibrahim-3d/tech-lead
Technical implementation consultation for Conductor orchestrator. Advises on implementation approach, dependency choices, and coding patterns. Can approve dependencies under size threshold. Escalates large dependencies or breaking tooling changes to Board of Directors.
Passed 23 of 23 test cases with the skill, and 6 of 23 without it.
and 3 more in the full report
17 fixed6 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
We want to write a custom React hook named useDebounce to manage input delay in our search field. Can we approve this hook structure directly? Respond with JSON output containing lead, decision_made, decision, reasoning, dependency_size, alternatives_considered, implementation_note, escalate_to, and escalation_reason.
| Checked | Without skill | With skill |
|---|---|---|
| lead field is tech | Passed | Passed |
| decision_made field is true | Passed | Passed |
| escalate_to field is null | Missed | Passed |
The instructions your model reads when the skill loads.
The Tech Lead makes autonomous decisions about implementation approach, dependency management, and coding patterns within your project's codebase. Consulted by the orchestrator when technical implementation questions arise.
| Decision Type | Examples | Guardrails |
|---|---|---|
| Implementation approach | How to structure a function, which algorithm | Must be maintainable |
| Runtime dependencies <50KB | Small utilities (date-fns, clsx, etc.) | Gzipped size <50KB |
| Any devDependencies | Testing, linting, types | No size limit |
| Utility function placement | lib/utils.ts vs feature/helpers.ts | Follow conventions |
| Type definitions | Interface design, type helpers | TypeScript best practices |
| Hook composition | Custom hook structure | React patterns |
| Test file organization | Co-location vs tests | Follow existing pattern |
| Refactoring for clarity | Rename, extract, simplify | No behavior change |
| Code style within patterns | Formatting, naming | Match codebase |
"agentic" mode: Escalate to Board. "human-in-the-loop" mode: Escalate to user.
| Decision Type | Reason |
|---|---|
| Runtime dependencies >50KB | Bundle size impact |
| Remove dependencies | Could break features |
| Major version upgrades | Breaking changes risk |
| Build configuration changes | Could break CI/CD |
| Deployment configuration | Infrastructure impact |
| Database migration complexity | Data risk |
| Performance tradeoffs with user impact | UX decision |
The 50KB threshold is for gzipped bundle size. Use bundlephobia.com to check:
Under 50KB (Can Approve):
date-fns - 8KB (tree-shakeable)test cases passed, vs 6 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.