generate-task

A generator for coder-eval task YAML files, which define scenarios used to test an AI coding agent. Given a plain-language scenario, it creates one task and may also create a checking script for end-to-end tests.

In plain words
What is it for?
Use it to turn a described scenario into one smoke, integration, or end-to-end evaluation task, with the target skill inferred from the description.
Why use it?
It removes the need to write the initial test structure by hand, while making clear that the generated task is only an unverified starting point. You still need to run and confirm the task before merging it.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/uipath/skills/generate-task
Clone the repo
git clone --depth 1 https://github.com/UiPath/skills

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,450 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.03450
Opus 5 $0.00000 $0.01725
Sonnet 5 $0.00000 $0.00690
Haiku 4.5 $0.00000 $0.00345

Measured 2d ago against content hash 354c2b179853, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/generate-task.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Test Task

Generate one coder-eval task YAML (and an optional check script) for the scenario described in $ARGUMENTS.

Input: $ARGUMENTS — a free-form description of the scenario the task should cover. The target skill is always inferred from the description (Phase 1a). Do not require or accept a skill name as a separate argument.

Optional tier filter. If the description contains a bare smoke / integration / e2e token (whitespace-separated), use it as the tier hint. Otherwise pick the tier from the scenario itself per the Phase 2a table.

Output: ONE task YAML at tests/tasks/<skill-name>/... plus an optional check_*.py for e2e tasks. Always one task per invocation — re-run the command for additional scenarios.

⚠ Generated tasks are unverified scaffolds

The author MUST before merging:

  1. Run the task end-to-end with coder-eval (command in the Phase 4 summary).
  2. Confirm it passes.
  3. State that explicitly in the PR description (e.g. Ran <task-id> locally and it passed.).

The lint workflow at .github/workflows/lint-tasks.yml raises a High issue when the PR description doesn't claim a passing run. Pushing the YAML alone is not enough.


Phase 1 — Context Gathering

1a. Infer the target skill from the description

  1. List candidates via ls skills/uipath-*/SKILL.md.
  2. Read every SKILL.md frontmatter (name + description) — that is what the runtime uses to decide which skill activates on a given prompt.
  3. Match the input description to the skill whose frontmatter best covers it. Tiebreak by inspecting the candidates' references/ and assets/ filenames.
  4. If two or more skills are plausible, ask the user to disambiguate before proceeding. Do not guess.

Once resolved, <skill-name> is fixed for the rest of the run.

1b. Read context (parallel Explore agents or parallel tool calls)

  1. skills/<skill-name>/SKILL.md plus everything under skills/<skill-name>/references/ and skills/<skill-name>/assets/.
  2. tests/README.md — authoritative source for the Tag Taxonomy, Weight scale, and experiment defaults (smoke.yaml for PR-gate, default.yaml for nightly e2e and ad-hoc, smoke-windows.yaml for Windows RPA). Do not duplicate that material here; reference it.
  3. .claude/commands/lint-task.md — the quality rubric (six axes, four severities). Generated tasks must not trip a Medium-or-above issue on any axis.
  4. tests/reports/<skill-name>.md if it exists — use it to detect that the scenario in the description is already a known gap with prior recommendations.
  5. Every existing *.yaml task under tests/tasks/ — collect all task_id values (collision check), study conventions for the target skill (or a peer skill if the target has none yet), and confirm the described scenario is not already covered.

Read the full file on GitHub · 236 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 236 lines · 0 tokens per session scan A 354c2b179853

Subscribe to this mod's changes

generate-task is a command published in the GitHub repository UiPath/skills (150 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,450 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.