What makes wip notable?

2.4K downloads. Trust evidence available

How should wip be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

wip

Track in-session work progress. Register steps for 3+ step tasks, update status per step, handle completion/abort. On /wip invocation, when remaining tasks exist, AskUserQuestion is required for the per-item direction (proceed / split / merge / hold / defer-to-checklist / delete) — asking only about start priority is forbidden. After a compact, show prior-work summary then AskUserQuestion(multiSelect) for restore selection and re-register via TodoWrite. antigravity - task.md artifact-based checklist (Antigravity environment) [antigravity.md], claude - TodoWrite/TaskCreate API guide (Claude Code environment) [claude.md], resume - environment-agnostic task cleanup + remaining-work workflow [resume.md]. "wip", "track progress", "register tasks", "task register", "step tracking", "compact recovery", "task resume", "resume task", "cleanup + resume" triggers.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.4k

Updated

Oct 9, 2026

Version

0.7.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.4K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.4K downloadsadoption · observed Oct 9, 2026
Latest release: 0.7.4release · observed Sep 27, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17ay1v6v88r2m102pvvc44gz183qcrm:wip

Install using `clawhub skill install s17ay1v6v88r2m102pvvc44gz183qcrm:wip` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/drumrobot/wip before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-drumrobot-wip/snapshot"

Documentation

CLAWHUB

151,055 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: wip
depends-on: [next]
description: |
  Track in-session work progress. Register steps for 3+ step tasks, update status per step, handle completion/abort.
  On /wip invocation, when remaining tasks exist, AskUserQuestion is required for the per-item direction (proceed / split / merge / hold / defer-to-checklist / delete) — asking only about start priority is forbidden.
  After a compact, show prior-work summary then AskUserQuestion(multiSelect) for restore selection and re-register via TodoWrite.
  antigravity - task.md artifact-based checklist (Antigravity environment) [antigravity.md],
  claude - TodoWrite/TaskCreate API guide (Claude Code environment) [claude.md],
  resume - environment-agnostic task cleanup + remaining-work workflow [resume.md].
  "wip", "track progress", "register tasks", "task register", "step tracking", "compact recovery", "task resume", "resume task", "cleanup + resume" triggers.
metadata:
  author: es6kr
  version: "0.1.1"
---

# WIP (Work In Progress)

Track current session work as a checklist.

## Topics

| Topic | Description | Guide |
|-------|-------------|-------|
| antigravity | task.md artifact-based checklist for Antigravity sessions | [antigravity.md](./antigravity.md) |
| claude | TodoWrite/TaskCreate API for Claude Code sessions | [claude.md](./claude.md) |
| resume | Environment-agnostic task cleanup + remaining-work workflow | [resume.md](./resume.md) |

## Topic Dependencies

```text
wip (entry — /wip or "task cleanup + remaining work")
  └─→ resume (environment-agnostic workflow)
        ├─→ claude (Claude Code: TaskList/TaskCreate/TaskUpdate/AskUserQuestion)
        └─→ antigravity (Antigravity: task.md artifact + ask.md emulation)
```

- **resume**: workflow procedure (cleanup → per-item direction ask → execute). Environment-agnostic.
- **claude / antigravity**: per-environment tooling. Defines how resume Step 1–3 is implemented in each environment.

## Purpose

Record in-progress work via **at least one** of:
1. **TodoWrite / TaskCreate** — in-session tracking
2. `checklist.md`, `fix_plan.md` and similar markdown files — persists across sessions
3. **Commit** — preserve incomplete code with a `WIP:` tag for later amend/squash

Emitting only a text summary without persistent recording does not satisfy `/wip`.

## When to Use

- Starting a multi-step task (3+ steps)
- User gives a large task instruction
- Need to show progress to the user
- When you want to record/preserve the current state mid-session
- "task cleanup + remaining work", "task cleanup", "remaining work", "resume" invocations

## /wip Entry Procedure (CRITICAL)

### Step 0 — args classification (HARD STOP, MANDATORY before Step 1)

**Before dispatching to any topic, classify the args intent.** The `/wip` skill has two mutually-exclusive dispatch paths — resume workflow vs new-task registration — and the wrong choice wastes user time and misapplies the resume gate.

Read args + call `TaskList` (Claude Code) or read `task.md` (Anti

_meta.json

{
  "ownerId": "kn74k8yfvftx6f062qa8fzyd8h8373jd",
  "slug": "wip",
  "version": "0.7.4",
  "publishedAt": 1790524327521
}

antigravity.md

# Antigravity WIP Tracking

> ⚠️ **STALE — needs verification (flagged 2026-07-06).** The "AskUserQuestion emulation via `ask.md`" guidance below was written when the Antigravity agent had **no** native `AskUserQuestion` tool. Per the user, Antigravity **later added a native `AskUserQuestion` tool** (distinct from the Gemini CLI, which still lacks it). Before relying on the `ask.md` emulation, **verify the current Antigravity toolset** — if a native `AskUserQuestion` exists, prefer it and update this doc via `/skill-kit upgrade`. Do not treat the emulation steps below as authoritative until re-verified.

Track in-session work progress using the `task.md` artifact file.

## Role & Principle

- **Task Registration**: When user feedback or a decision is needed before registering, **ask first and only then register in `task.md`** — do not register immediately when the situation is ambiguous.
- **AskUserQuestion emulation**: The Antigravity (Gemini) agent has no `AskUserQuestion` tool. Emulate it by writing the question and options to `<appDataDir>/brain/<conversation-id>/ask.md` (`ArtifactType: "other"`, `RequestFeedback: true`).

## Storage

- **Path**: `<appDataDir>/brain/<conversation-id>/task.md`
- **Type**: Artifact (`ArtifactType: "task"`)

## Status Notation

| Notation | Meaning | Description |
|----------|---------|-------------|
| `- [ ]` | **Pending** | Not yet started |
| `- [/]` (IDE) / `- [ ] 🔄` (CLI) | **In Progress** | Currently working (only one at a time). In CLI environment, use `🔄` instead of `⏳` |
| `- [x]` | **Completed** | Finished |

> **`[/]` vs `🔄` scope**: In Antigravity IDE `task.md`, use `- [/]`. In `antigravity-cli` (terminal CLI) where `[/]` is unsupported, use `- [ ] 🔄`. Always use `🔄` as the standard in-progress indicator instead of `⏳`.

## Rendering Rules

> [!IMPORTANT]
> **Do NOT wrap checkboxes in backticks.**
> Some artifact renderers treat backtick-wrapped `[ ]` as inline code, preventing checkbox interactivity. Always use plain markdown checkbox format.

**Correct:**
```markdown
- [ ] Task item
- [/] In progress item
- [x] Completed item
```

**Wrong:**
```markdown
- `[ ]` Task item
- `[/]` In progress item
- `[x]` Completed item
```

## Called from resume.md

When invoked via `/wip` or "task cleanup + remaining work" (see [resume.md](./resume.md)), this topic provides the **Antigravity environment implementation** of resume's 3 steps:

| resume Step | Antigravity implementation |
|------------|----------------------------|
| Step 1: Cleanup (remove stale items) | Read `task.md` → identify lines to delete → remove them via `replace_file_content` |
| Step 2: Per-item direction ask | Emulate via `ask.md` (`ArtifactType: "other"`, `RequestFeedback: true`) — for each remaining item, offer proceed/split/merge/hold/delete options with Pros/Cons |
| Step 3: Start + execute | Use `replace_file_content` to flip the target line `[ ]` → `[/]` → do the work → `[x]` |

### Step 1 — task.md cleanup commands

```python

CHANGELOG.md

# Changelog

## [0.7.4](https://github.com/es6kr/skills/compare/wip-v0.7.3...wip-v0.7.4) (2026-09-27)


### Bug Fixes

* **wip:** import-safe main() wrapping for block-wip-register hook ([26017da](https://github.com/es6kr/skills/commit/26017daacece6fc517d1948aa0b136393d61a589))

## [0.7.3](https://github.com/es6kr/skills/compare/wip-v0.7.2...wip-v0.7.3) (2026-09-24)


### Bug Fixes

* **todowrite,wip:** clarify session-medium delegation boundary (S6/S7) ([806dcad](https://github.com/es6kr/skills/commit/806dcad0c92a027b9fc89617957510cb52f580ea))
* **wip:** document defer-to-checklist follows todowrite file-medium convention ([8198e5d](https://github.com/es6kr/skills/commit/8198e5d888fe79bab1c563f319bbe6b98c1c873b))

## [0.7.2](https://github.com/es6kr/skills/compare/wip-v0.7.1...wip-v0.7.2) (2026-09-18)


### Bug Fixes

* **cleanup:** make the session-end report table self-sufficient ([#487](https://github.com/es6kr/skills/issues/487)) ([c4a0255](https://github.com/es6kr/skills/commit/c4a02557fb8de3b32cf337c549f62535dabf824b))

## [0.7.1](https://github.com/es6kr/skills/compare/wip-v0.7.0...wip-v0.7.1) (2026-09-08)


### Bug Fixes

* **tdd:** scope the Red-only commit ban to shared branches ([fc2e6ec](https://github.com/es6kr/skills/commit/fc2e6ecdd1906c41d47955226e247aeb03a6f367))

## [0.7.0](https://github.com/es6kr/skills/compare/wip-v0.6.0...wip-v0.7.0) (2026-09-05)


### Features

* promote develop (schema, hook-kit, cleanup, wip, todowrite) ([5938cea](https://github.com/es6kr/skills/commit/5938cea0a20eaf93aec4d373298e58ccc3f2a682))


### Bug Fixes

* **wip:** standardize in-progress markers to 🔄 in antigravity tracking ([f9f4c97](https://github.com/es6kr/skills/commit/f9f4c97ae57bf7249b92c591c807c590fe8ffe73))

## [0.6.0](https://github.com/es6kr/skills/compare/wip-v0.5.1...wip-v0.6.0) (2026-08-29)


### Features

* promote next-feat batch (backlog skill, hooks JS port, git-repo doctor, pre-push guard) ([0d76a4c](https://github.com/es6kr/skills/commit/0d76a4c01180fbdc78bfeec8dea91373b4912470))


### Bug Fixes

* address CodeRabbit and Copilot review feedback on PR [#385](https://github.com/es6kr/skills/issues/385) ([e94de34](https://github.com/es6kr/skills/commit/e94de34ce5e075c79b7edc5d672813cea94a0acc))
* **hook-kit:** document --json mode and scope WSCFG_* to hook scripts ([373634c](https://github.com/es6kr/skills/commit/373634c022b0e2b114a3bbb799bb9a8934c9fbb2))


### Refactor

* **hooks:** port check-completed-bloat and wip-task-complete-detect to Node.js ([7097526](https://github.com/es6kr/skills/commit/7097526ca208c3106b38a3ac5c317d0eb49eff30))

## [0.5.1](https://github.com/es6kr/skills/compare/wip-v0.5.0...wip-v0.5.1) (2026-08-26)


### Bug Fixes

* accumulate 16 patch-level bug fixes and guard enhancements across skills ([d214e5d](https://github.com/es6kr/skills/commit/d214e5dcc7fac1bc07baf3b6cec62999aea732f0))
* promote accumulated skill fixes from the working checkout ([770bed2](https://github.com/es6kr/skills/commit/770bed23862

claude.md

# Claude Code WIP — TaskCreate/TodoWrite API guide

Tool usage for registering / updating / deleting tasks in the Claude Code environment.

For the workflow procedure (cleanup → per-item direction ask → execute), see [resume.md](./resume.md).

## Tool unavailability — verify before falling back (HARD STOP)

**A `ToolSearch` miss or a system-reminder saying `TaskCreate`/`TaskList` is "disconnected" is NOT sufficient evidence to skip task tracking entirely.** `ToolSearch` only reports whether a tool's schema is currently loaded — it cannot distinguish "temporarily disconnected (will reconnect)" from "disabled in this context (won't reconnect this session)". Before falling through to a file-only medium (`fix_plan.md`/`checklist.md`), attempt an actual `TaskCreate` call once per session (and again after any subsequent disconnect signal) and branch on the real error:

| Actual `TaskCreate` call result | Meaning | Action |
|---|---|---|
| Succeeds | Available now | Use it normally |
| Error mentions disconnect / MCP unreachable | Recoverable — connectivity flickers | Retry at the start of the next `/wip` invocation this session; use the `claude-task` CLI fallback below in the meantime |
| Error says "exists but is not enabled in this context" | Context/settings gap, not connectivity | **Report this to the user in plain text this turn** — do not silently normalize the workaround. Use the `claude-task` CLI fallback below for the rest of the session |

**`claude-task` CLI fallback (when no Task tool is usable this turn)**: use the `claude-task` CLI (`todowrite` skill's `claude-task` topic) — `claude-task --env agent add -s "<subject>"` / `claude-task --env agent list` / `claude-task --env agent update <id> --status <status>`. It persists to a fixed directory (`~/.agents/tasks/default/`) that survives session/scratchpad-path changes — **do NOT use the session scratchpad directory** for this tracking; the scratchpad path changes across sessions/compacts and silently drops its contents with no recovery (case history: failed-attempts.md "scratchpad ephemeral task loss"). Run `claude-task --env agent list` first — a prior `/wip` or `/fix` call in the same session may have already registered unrelated in-flight items; add to the ledger rather than treating it as empty.

### Don't / Do

| # | Don't | Do |
|---|-------|-----|
| 1 | Conclude "Task API unavailable" from `ToolSearch` alone and skip straight to reading `fix_plan.md` with no task tracking at all | Attempt a real `TaskCreate` call first; only after seeing its actual error, decide the fallback medium |
| 2 | Treat "exists but not enabled in this context" the same as a transient disconnect (silently retry every turn) | It's a settings-level gap — surface it to the user once, then use the `claude-task` CLI for the rest of the session without re-attempting every turn |
| 3 | Write fix/wip tracking state to a file in the session scratchpad directory (`<scratchpad>/*.md`) | Use `claude-task --env agent add/l

Github ReposUpdated 3h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.