tzachbon/srulik-toolkit / plugins/srulik-toolkit/skills/skill-creator
skill-creator
VerifiedCreate or edit a skill, improve its instructions or triggers, evaluate it on real tasks, or benchmark a revision. Every skill creation or edit uses create-plan and implement-plan, including small changes; evaluation compares actual outputs and includes human review.
| File | Kind | Size |
|---|---|---|
| LICENSE.txt | markdown | 11.1 KB |
| SKILL.md | skill md | 4.2 KB |
| agents/analyzer.md | markdown | 10.3 KB |
| agents/grader.md | markdown | 9.1 KB |
| agents/openai.yaml | config | 118 B |
| assets/eval_review.html | other | 6.8 KB |
| eval-viewer/generate_review.py | script | 7.2 KB |
| eval-viewer/viewer.html | other | 40.7 KB |
| references/authoring.md | markdown | 2.8 KB |
| references/claude-code.md | markdown | 3.9 KB |
| references/codex.md | markdown | 2.1 KB |
| references/evaluation.md | markdown | 3.9 KB |
| references/hosts.md | markdown | 861 B |
| references/oh-my-pi.md | markdown | 1.2 KB |
| references/schemas.md | markdown | 3.9 KB |
| references/t3-code.md | markdown | 2.2 KB |
| scripts/__init__.py | script | 0 B |
| scripts/aggregate_benchmark.py | script | 9.3 KB |
| scripts/generate_report.py | script | 12.5 KB |
| scripts/improve_description.py | script | 11.3 KB |
| scripts/run_eval.py | script | 12.6 KB |
| scripts/run_loop.py | script | 13.9 KB |
| scripts/utils.py | script | 3.0 KB |
references/t3-code.md
View on GitHub# T3 Code mapping
Use the provider's namespaced skill invocation and verify source identity.
T3's current thread can have an older installed plugin than the checkout; a
file path in a task does not change runtime installation or workspace binding.
Use native asynchronous question tools while work continues. Required answers
and implementation authority remain pending until actually received. A new
authoring request invokes `create-plan`; authorized execution invokes
`implement-plan` and consumes the references within its approved task.
Follow the current T3 orchestration instructions: discover capabilities with
`orchestrator_capabilities` before the first `delegate_task`; set model options
in `target.options`, and use `isolation: "worktree"` for separate writer
checkouts. Same-provider native children are appropriate when the active rules
allow them. Never create a top-level conversation as a substitute child.
Retain task IDs and obey each delegated task's `next`. If completion wakes the
parent, end the turn rather than polling. Use a new task for a new review
round, and cancel replaced tasks with `task_cancel`. Children do not inherit
publication or installation authority. Keep paired evaluation settings and
outputs explicit; serialize heavy runs when host capacity requires it.
Store only actual completion telemetry. A T3 receipt or native child result may
not contain the same timing/token fields as another transport; omit unavailable
measurements. A model's claim of success is not produced-artifact evidence.
For static HTML presentation use `html_preview` then `html_render` when those
tools are available under the active visual instructions. Pass the generated
file's HTML; never start a viewer server or claim an on-disk screenshot displays
the artifact. Otherwise return the supported clickable absolute file link and
state that in-app display is unverified. Import explicit completed feedback
through the host's supported file exchange; distinguish synthetic round trips
from actual human review.
This mapping documents tool contracts, not live verification of the user's
current conversation. Native CLI smoke results prove those exact isolated
runtimes, not automatic activation of a newly bundled skill here.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |