start
/start
Use when the user asks how to use RELAI, where to start, what it can do for their agent, or what the status of their evals is and what to do next ("how do I use RELAI", "where do I start", "what's the status of my evals"); also to set up RELAI records when a selected workflow needs them. Routes an already clear request directly to the appropriate skill, reusing existing project infrastructure.
- Author
- relai-ai ↗
- Repository
- agent-eval-loop ↗
- Licence
- Apache-2.0
- Last repository change
- 12.11.2026
Assessment and security
- Files in this package
- 15
- Scripts
- 7
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 12.11.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
- 7 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: template/bin/_common.py, template/bin/benchmark.py, template/bin/check_task.py, template/bin/check_trajectory.py, template/bin/check_wiki.py, template/bin/freeze.py, template/bin/summarize.py
What it does and when to use it
Use when the user asks how to use RELAI, where to start, what it can do for their agent, or what the status of their evals is and what to do next ("how do I use RELAI", "where do I start", "what's the status of my evals"); also to set up RELAI records when a selected workflow needs them. Routes an already clear request directly to the appropriate skill, reusing existing project infrastructure.
Triggers from the description
Original author description
Use when the user asks how to use RELAI, where to start, what it can do for their agent, or what the status of their evals is and what to do next ("how do I use RELAI", "where do I start", "what's the status of my evals"); also to set up RELAI records when a selected workflow needs them. Routes an already clear request directly to the appropriate skill, reusing existing project infrastructure.
How it works
- Route before setting up
- Initialize or recover managed state when needed
- Orient and hand off
SKILL.md preview
---
name: start
description: Use when the user asks how to use RELAI, where to start, what it can do for their agent, or what the status of their evals is and what to do next ("how do I use RELAI", "where do I start", "what's the status of my evals"); also to set up RELAI records when a selected workflow needs them. Routes an already clear request directly to the appropriate skill, reusing existing project infrastructure.
---
# Start here
RELAI helps teams understand and improve agent behavior. Choose the smallest useful workflow:
- [discover](../discover/SKILL.md): requirements, risks and open questions from code, docs or traces.
- [trace-review](../trace-review/SKILL.md): build or adapt a UI for full traces, fast navigation and human feedback.
- [eval](../eval/SKILL.md): build missing evaluations, reuse a benchmark, or measure current behavior.
- [improve](../improve/SKILL.md): a direct fix, regression check, or measured behavioral, cost or latency improvement.
- [loop](../loop/SKILL.md): coordinate ongoing learning and experiments under one agreement.
- [coding-evals](../coding-evals/SKILL.md): agent-neutral coding tasks from sessions, pull requests
and history, including for a custom coding agent developed here.
## Route before setting up
Inspect the request and existing project tests, runners and results. A deterministic fix or a
regression check using project tests goes directly to `improve`; that handoff completes this skill
without requiring evaluation setup or a board. Maintain durable knowledge when useful as the
[knowledge policy](template/README.md#maintain-useful-knowledge) describes; a small task may yield
a valuable constraint or lesson. Do not ask the user to choose a step they already requested.
Other workflows reuse working infrastructure and initialize only the RELAI artifacts they need.
For shared terms, knowledge maintenance and user interaction, read the relevant sections of the
project's `relai/README.md`, otherwise the bundled [terms](template/README.md#terms),
[knowledge policy](template/README.md#maintain-useful-knowledge) and
[user interaction guidance](template/README.md#working-with-the-user). Plugin methods are linked from each skill; `relai/`
paths refer to project artifacts, not files inside the plugin.
## Initialize or recover managed state when needed
- A README beginning `<!-- relai` identifies RELAI state. If an unrelated folder occupies `relai/`,
explain the collision and ask how to resolve it. Do not move or overwrite it; another state root
is not currently supported by these workflows.
- When initialization is needed and authorized, copy only the parts of [template/](template/)
needed for the selected workflow into the repository's `relai/`, including supporting contracts
and checker dependencies. Keep needed local references usable; references to optional stages
do not require initializing those stages. Skip caches and rename `gitignore` to `.gitignore`
when copied. Explain material additions; ask only when existing instructions do not authorize
them. Add other template assets when a concrete workflow needs them, rather than copying
unused harness or reporting infrastructure in advance.
- Record the source of copied files in `relai/UPSTREAM.md` or existing project provenance,
following the [project-copy upgrade policy](template/docs/upgrades.md). Apply that policy
when upgrading existing copies; an installed plugin update does not replace project files.
- If setup was interrupted, restore missing template files needed for the selected work. Preserve
project modifications. If an existing file is incompatible with the needed operation, explain
the difference and resolve that file rather than silently replacing the project copy.
- This is orientation and setup: do not run a model or container here. Name a credential only
when a later step needs it, using the project's existing credential mechanism where suitable.
## Orient and hand off
When using managed state, read its contract and update `relai/STATUS.md` using the
[board contract](template/docs/board.md). Show the current request, relevant progress, pending
decisions and the useful next action. Missing optional stages are not prerequisites.
Start the already requested skill. If the goal remains unclear, offer the relevant choices with
a recommendation. This skill is complete when the request has been routed, or the user understands
the project's relevant state and next action; setup and a board are required only on the managed-state path.
Files in this package (15)
- SKILL.md 4 KB
- template/README.md 23 KB
- template/gitignore 1 KB
- template/bin/_common.py 11 KB
- template/bin/benchmark.py 19 KB
- template/bin/check_task.py 59 KB
- template/bin/check_trajectory.py 8 KB
- template/bin/check_wiki.py 7 KB
- template/bin/freeze.py 5 KB
- template/bin/summarize.py 35 KB
- template/docs/board.md 4 KB
- template/docs/files.md 22 KB
- template/docs/harbor.md 6 KB
- template/docs/native.md 3 KB
- template/docs/upgrades.md 2 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · relai-ai/agent-eval-loop | 90 | Apache-2.0 |
| tilnoteio/tilnote-blog | 100 | MIT |
| dedujeong/gemba | 100 | Apache-2.0 |
| nextwork-projects/ai-video-editor-cooked | 100 | MIT |
| wrg32786/aigent-os | 100 | MIT |
| T-X-R/codex-game-studio | 100 | MIT |
| alienfast/claude | 100 | MIT |
| ratomirjovanovic/pandaward | 100 | AGPL-3.0 |
| darioabc/massimo | 100 | MIT |
Database snapshot: 13.11.2026 · package version d7e6e7e6341e (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 81evals-start
Entry point for evals. Use when the user asks for help with evals, does not know where to begin, or asks for something no other skill in this plugin matches. Do NOT use when a more specific skill in this plugin already matches; load that skill directly. - 100ask-pmai
Entry point for a PM who wants evals for an AI agent. Sets up the evals/ folder, finds the agent and its conversation logs, and routes to the next skill. Use when the user says they want to evaluate, test, measure or improve an agent, asks "where do I start with evals", or has… - 90eval-guide
Entry point for eval work. Use when someone asks for help with evals in general, does not know where to start, asks "what should I do next", or asks for something no other skill in this plugin matches. Do NOT use when a more specific skill in this plugin already matches the… - 100evals-context
Provides context about the Roo Code evals system structure in this monorepo. Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", or working with the evals infrastructure. Helps distinguish between the evals execution system (packages/evals,… - 100evals-context
Provides context about the CoStrict evals system structure in this monorepo. Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", or working with the evals infrastructure. Helps distinguish between the evals execution system (packages/evals,… - 100huggingface-community-evals
Curated upstream guidance for Huggingface Community Evals; use when the workflow matches the user goal.