Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
UiPath Action Center human-in-the-loop tasks via uip tasks: list, assign, complete, plus task catalogs, comments, labels, metadata, and task data (get/save).
$ npx skills add UiPath/skills --skill uipath-tasks -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install UiPath/skills uipath-tasks --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/UiPath/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/uipath-tasks .claude/skills/uipath-tasks && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "uipath-tasks" agent skill from https://github.com/UiPath/skills/tree/main/skills/uipath-tasks into .claude/skills/uipath-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uipath-tasks", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/UiPath/skills/tree/main/skills/uipath-tasksType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add UiPath/skills --skill uipath-tasks -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install UiPath/skills uipath-tasks --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/UiPath/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/uipath-tasks .agents/skills/uipath-tasks && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "uipath-tasks" agent skill from https://github.com/UiPath/skills/tree/main/skills/uipath-tasks into .agents/skills/uipath-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uipath-tasks", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add UiPath/skills --skill uipath-tasks -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install UiPath/skills uipath-tasks --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/UiPath/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/uipath-tasks .cursor/skills/uipath-tasks && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "uipath-tasks" agent skill from https://github.com/UiPath/skills/tree/main/skills/uipath-tasks into .cursor/skills/uipath-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uipath-tasks", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/UiPath/skills.git --path skills/uipath-tasks--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add UiPath/skills --skill uipath-tasks -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install UiPath/skills uipath-tasks --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/UiPath/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/uipath-tasks .gemini/skills/uipath-tasks && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "uipath-tasks" agent skill from https://github.com/UiPath/skills/tree/main/skills/uipath-tasks into .gemini/skills/uipath-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uipath-tasks", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install UiPath/skills uipath-tasksInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add UiPath/skills --skill uipath-tasks -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/UiPath/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/uipath-tasks .github/skills/uipath-tasks && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "uipath-tasks" agent skill from https://github.com/UiPath/skills/tree/main/skills/uipath-tasks into .github/skills/uipath-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uipath-tasks", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add UiPath/skills --skill uipath-tasks -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install UiPath/skills uipath-tasks --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/UiPath/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/uipath-tasks .opencode/skills/uipath-tasks && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "uipath-tasks" agent skill from https://github.com/UiPath/skills/tree/main/skills/uipath-tasks into .opencode/skills/uipath-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uipath-tasks", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
uipath-tasksUiPath Action Center human-in-the-loop tasks via uip tasks: list, assign, complete, plus task catalogs, comments, labels, metadata, and task data (get/save).
Uipath Tasks is an agent skill from UiPath/skills. UiPath Action Center human-in-the-loop tasks via uip tasks: list, assign, complete, plus task catalogs, comments, labels, metadata, and task data (get/save). For authoring HITL nodes in flows/agents→uipath-human-in-the-loop. For Orchestrator→uipath-platform, codedapp→uipath-coded-apps. Skip Document Understanding.
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/action-center-urls.md`, `references/task-assignment.md` and `references/task-catalogs.md`).
It sits in Agent Workflows, covering Human-in-the-loop approvals. The repository describes itself as: This is a repository of skills for interfacing UiPath capabilities to external developers. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit bc2e230. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
cloud.uipath.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Uipath Tasks loads about 2.9k tokens when it runs, and up to ~8.4k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 1,250 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from UiPath/skills at commit bc2e230, republished under its MIT licence (© UiPath). 1,250 words, ~2,943 tokens.
.claude/skills/uipath-tasks/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.Action Center is UiPath's human-in-the-loop platform. Tasks represent work items that require human input — form approvals, document validation, data labeling, and more.
All operations go through uip tasks <verb> --output json.
Default to Production. Only switch environment/org/tenant when explicitly stated in the request.
cloud.uipath.com)uip login status and re-login if neededWhen switching is required:
uip login status --output json — verify UIPATH_URL, Organization, and Tenant--authority only if environment differs:uip login --authority "<AUTHORITY_URL>" --tenant <tenant>cloud.uipath.com: uip login --tenant <tenant> (default, no --authority needed)uip login tenant set <tenant-name># Check current environment, org, and tenant
uip login status --output json
# Login to a specific environment (production cloud is the default)
uip login --authority https://cloud.uipath.com --tenant MyTenant
# List all available tenants (after login)
uip login tenant list --output json
# Switch tenant within the same environment
uip login tenant set MyTenantCritical: The
--tenantflag ontaskscommands does NOT switch the active session tenant. The environment is determined byUIPATH_URLin the auth file — always confirm withlogin statusbefore runningtaskscommands.
Not in scope: Orchestrator queues or queue items (use
uip or), Document Understanding model training, or Action Center app development (useuip codedapp).
| Type | CLI value | Description |
|---|---|---|
| Form task | FormTask | Form-based approval/action task |
| External task | ExternalTask | Generic external task |
| App task | AppTask | Action Center app-based task |
| Document validation | DocumentValidationTask | Document Understanding validation |
| Document classification | DocumentClassificationTask | Document Understanding classification |
| Data labeling | DataLabelingTask | Data labeling task |
| Status | Meaning |
|---|---|
Unassigned | Created but not assigned to any user |
Pending | Assigned, awaiting completion |
Completed | Completed with an action/outcome |
| Priority | Level |
|---|---|
Low | Low |
Medium | Medium (default) |
High | High |
Critical | Critical |
# Check login and active tenant
uip login status --output json
# Switch tenant if needed
uip login tenant set <tenant-name>
# List all tasks across folders
uip tasks list --output json
# Get details of a specific task
uip tasks get <task-id> --output json
# Assign a task to a user
uip tasks assign <task-id> --user alice@company.com --output json
# Complete a task
uip tasks complete <task-id> --type ExternalTask --folder-id <folder-id> --output jsonAlways resolve org and tenant first. If the user specifies an org/environment and tenant, run uip login status to check the active tenant, then uip login tenant set <tenant> to switch if needed. Never assume the active tenant matches the user's intent.
Task IDs are numeric. Unlike other UiPath services that use GUIDs, Action Center uses numeric task IDs. Use tasks list to discover task IDs.
Folder scope comes in three interchangeable forms. Folder-scoped commands accept --folder-id <numeric-id>, --folder-path <path>, or --folder-key <guid> (mutually exclusive). Path and key are exactly what uip or folders list prints (it has no numeric ID column), so prefer them when the folder came from folder discovery; the numeric id still works when a task row gave you folderId.
Complete requires --type. The API routes to different endpoints per task type. Always include --type when completing a task. Use tasks get to check the task type first.
FormTask and AppTask require --action and --data for completion. Other task types allow optional action and data.
Assign accepts --user-id or --user (email). Use tasks users <folder-id> (or tasks users --folder-path <path> / --folder-key <guid>) to discover assignable users and their IDs.
Always discover before acting. Use tasks list or tasks get to inspect task state before performing assign/complete operations.
Do not complete already-completed tasks. Check the task status field — if it is Completed, inform the user.
Folder scope for complete/catalogs/comments/labels/metadata/data. These commands need a folder. Pass one of --folder-id/--folder-path/--folder-key, or omit all three on an interactive terminal to pick from a list. A folder option is required in non-interactive runs (agents, CI) — the command fails with A folder is required otherwise, so always pass one explicitly there.
Retention actions are Delete or Archive. Archive also needs --retention-bucket-id. --encrypted is create-only and cannot be changed on update.
Labels replace the full set. tasks labels --labels overwrites all labels on the task — include every label to keep, and pass [] to clear them all.
data save takes no type flag. The command resolves the task type itself; pass the task ID, a folder option (--folder-id/--folder-path/--folder-key), and --data (a JSON object).
| Task | Commands to use |
|---|---|
| List all tasks | tasks list |
| List tasks in a folder | tasks list --folder-id <id> |
| List tasks in a folder by path/key | tasks list --folder-path "<path>" or tasks list --folder-key <guid> |
| List tasks as admin | tasks list --as-admin |
| Get task details | tasks get <task-id> |
| Get task with type hint | tasks get <task-id> --task-type FormTask --folder-id <id> |
| Assign a task | tasks assign <task-id> --user <email> |
| Assign by user ID | tasks assign <task-id> --user-id <id> |
| Reassign a task | tasks reassign <task-id> --user <email> |
| Unassign a task | tasks unassign <task-id> |
| Complete a task | tasks complete <task-id> --type <type> --folder-id <id> |
| Complete with action | tasks complete <task-id> --type FormTask --folder-id <id> --action "Approve" --data '{...}' |
| List assignable users | tasks users <folder-id>, tasks users --folder-path "<path>", or tasks users --folder-key <guid> |
| List task catalogs | tasks catalogs list --folder-id <id> |
| Get a catalog | tasks catalogs get <catalog-id> --folder-id <id> |
| Create a catalog | tasks catalogs create --name <name> --folder-id <id> |
| Update a catalog | tasks catalogs update <catalog-id> --folder-id <id> |
| List task comments | tasks comments list <task-id> --folder-id <id> |
| Add a comment | tasks comments add <task-id> --text <text> --folder-id <id> |
| Set task labels | tasks labels <task-id> --labels '[{"name":"region","displayName":"Region","displayValue":"EMEA"}]' --folder-id <id> |
| Edit task metadata | tasks metadata <task-id> --folder-id <id> [--title --priority --catalog-id] |
| Get task data | tasks data get <task-id> --folder-id <id> |
| Save task data | tasks data save <task-id> --data '{...}' --folder-id <id> |
Always follow this pattern:
# 0. Ensure correct tenant
uip login status --output json
uip login tenant set <tenant-name> # only if needed
# 1. Discover
uip tasks list --output json
uip tasks get <task-id> --output json
# 2. Plan — determine the task type, folder ID, and action needed
# 3. Act — assign a task
uip tasks assign <task-id> --user alice@company.com --output json
# 4. Verify
uip tasks get <task-id> --output json| Error | Cause | Fix |
|---|---|---|
Not logged in | Auth expired | uip login |
HTTP 401 | Invalid token | Re-login |
HTTP 403 | Permission denied | Ensure account has Action Center permissions in the folder |
Missing assignee | Neither --user-id nor --user provided | Add --user <email> or --user-id <id> |
Task not found | Wrong task ID | Run tasks list to get correct ID |
| Completion fails | Wrong --type | Use tasks get to check the actual task type |
| Completion fails for FormTask | Missing --action or --data | FormTask and AppTask require both --action and --data |
| Cannot assign | User lacks permissions in folder | Run tasks users <folder-id> to list eligible users |
A folder is required | Non-interactive run without a folder option | Pass --folder-id, --folder-path, or --folder-key |
Folder not found: '<value>'. | The path/key doesn't match a folder this login can access | Run uip or folders list and use a listed Path or Key |
Invalid --folder-key: <value> | The key is not a UUID | Use the GUID from the Key column of uip or folders list |
Error resolving folder path/key '<value>' | The folder lookup itself failed (permissions or network) | Check the error detail in Instructions; verify access with uip or folders list |
For deeper guidance, read these files only when needed:
references/task-lifecycle.md — Listing and getting tasks, type-hint endpoint routing, and the full discover→assign→complete workflowreferences/task-completion.md — Completion endpoint routing, required fields per task typereferences/task-assignment.md — Assign, reassign, unassign patterns and user discoveryreferences/task-catalogs.md — Task catalog list/get/create/update and retention policyreferences/task-metadata.md — Editing task metadata, plus task comments and labelsreferences/task-data.md — Getting and saving task data, and save type routingreferences/action-center-urls.md — Canonical Action Center URL patterns; read this before constructing or sharing any task deep-link (the portal-UI misclassifies tenant-less URLs as "Orchestrator not enabled")© UiPath, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 7 other files (references) in skills/uipath-tasks of UiPath/skills.
Open the folder on GitHubat commit bc2e230
Uipath Tasks next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Uipath Tasks this skillUiPath/skills | 168 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Show Me Your Work Decision Logcursor/plugins | 10k | 8 repos | ~1.6k | Automated safety check: Pass | None | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Loop Constraints Enforcercobusgreyling/loop-engineering | 11k | 1 repos | ~475 | Automated safety check: Notes | MIT | |
| Ask User QuestionMemTensor/MemOS | 12k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| PUA High-Agency Governancetanweai/pua | 20k | — | ~502 | Automated safety check: Pass | MIT |
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
cobusgreyling/loop-engineering
Loads a project's loop-constraints.md before any other action and blocks pushes, edits or merges that violate the rules it defines.
MemTensor/MemOS
Shows a question as a modal in the interface to clarify a task, collect a preference or get approval, since the user cannot see terminal output.
tanweai/pua
Pushes an agent to keep verifying and changing approach after repeated failures, using a diagnosis line, evidence-based completion and confirmation before risky edits.
rohitg00/agentmemory
Deletes chosen memories from agentmemory only after showing the matches and getting an explicit yes, for privacy requests and cleanup of outdated notes.
UiPath/skills
UiPath automation discovery — mines Slack/email/wikis/CRM/HRIS/ERP for repetitive work, SPOFs, and replicable models; produces a 4-tier prioritized opportunity report with UiPath implementation…
UiPath/skills
Maintain build-time skill flavors in the UiPath skills repository.
UiPath/skills
UiPath Coded Functions — deterministic Python or TypeScript/JavaScript units built with the uip function CLI (new -l py|ts|js, init, serve, run, pack, publish); the functions map in uipath.json…
UiPath/skills
TRIGGER for authoring, operating or diagnosing UiPath Maestro BPMN.
UiPath/skills
TRIGGER for authoring UiPath Maestro Case plans as <Name.case.ts with the reference-mode TypeScript builder SDK (@uipath/maestro-builder-sdk/case), compiling to caseplan.json, and running the uip…
UiPath/skills
UiPath causal investigation across every product, runtime, and activity package.
Categories
UiPath Action Center human-in-the-loop tasks via uip tasks: list, assign, complete, plus task catalogs, comments, labels, metadata, and task data (get/save). Uipath Tasks is an agent skill from UiPath/skills. UiPath Action Center human-in-the-loop tasks via uip tasks: list, assign, complete, plus task catalogs, comments, labels, metadata, and task data (get/save).
Uipath Tasks fits situations like: tasks that involve Human-in-the-loop approvals.
Run `npx skills add UiPath/skills --skill uipath-tasks -a claude-code`. Or copy the skill folder (skills/uipath-tasks in UiPath/skills) into .claude/skills/uipath-tasks in your project. Claude Code loads it when a task matches its description.
Run `npx skills add UiPath/skills --skill uipath-tasks -a codex`. Or copy the skill folder (skills/uipath-tasks in UiPath/skills) into .agents/skills/uipath-tasks in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add UiPath/skills --skill uipath-tasks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/uipath-tasks, .gemini/skills/uipath-tasks, .github/skills/uipath-tasks and .opencode/skills/uipath-tasks in your project.
SKILL.md names no scripts, command-line tools or credentials: Uipath Tasks is instructions for the agent only.
SKILL.md names 1 domain. In commands or code: cloud.uipath.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Uipath Tasks is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Uipath Tasks: Show Me Your Work Decision Log (cursor/plugins, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), Loop Constraints Enforcer (cobusgreyling/loop-engineering, 11k stars) and Ask User Question (MemTensor/MemOS, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
UiPath (a GitHub organization) maintains it in UiPath/skills, which has 168 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 9, 2026.
Source: UiPath/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.