suyoumo/ClawProBench

ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

823Stars on the repository
39Mods indexed here, across every type
8d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

ceo-setup

01

suyoumo/ClawProBench

Skill Claude CodeCodex

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

823 8d ago A 60 tokens original Apache-2.0

code-review

02

suyoumo/ClawProBench

Skill Claude CodeCodex

Paranoid architect review of code changes for bugs, security, missing tests, and undocumented assumptions. Works on local git diffs OR a GitHub pull request (e.g. owner/repo N). For PRs, can post findings as line-level review comments.

823 8d ago A 57 tokens original Apache-2.0

coding

03

suyoumo/ClawProBench

Skill Claude CodeCodex

Best practices for code editing, search, and file operations.

823 8d ago A 13 tokens original Apache-2.0

commit

04

suyoumo/ClawProBench

Skill Claude CodeCodex

Generate git commit messages from staged changes.

823 8d ago A 9 tokens original Apache-2.0

commitment-digest

05

suyoumo/ClawProBench

Skill Claude CodeCodex

Compose and deliver summaries of open commitments, deadlines, pending signals, and resolution suggestions.

823 8d ago A 22 tokens original Apache-2.0

commitment-setup

06

suyoumo/ClawProBench

Skill Claude CodeCodex

One-time setup for the commitments tracking system. Creates workspace structure, schema docs, and installs triage and digest missions. Excluded from activation once projects/commitments/README.md exists in the workspace (the file this skill writes as its first step).

823 8d ago A 58 tokens original Apache-2.0

commitment-triage

07

suyoumo/ClawProBench

Skill Claude CodeCodex

Recognize obligations in conversation, extract signals with immediacy and expiration, create and manage commitments in the workspace.

823 8d ago A 29 tokens original Apache-2.0

suyoumo/ClawProBench

Skill Claude CodeCodex

One-time onboarding for the content creator workflow — content pipeline stages, trend expiration, cross-platform cascades, heavy idea parking. After successful setup this skill is excluded from selection until the marker file is deleted.

823 8d ago A 47 tokens original Apache-2.0

decision-capture

09

suyoumo/ClawProBench

Skill Claude CodeCodex

Detect decisions in conversation and record them with rationale, alternatives, and outcome tracking.

823 8d ago A 20 tokens original Apache-2.0

delegation-tracker

10

suyoumo/ClawProBench

Skill Claude CodeCodex

Track delegated commitments, set follow-up timers, and generate nudge reminders when updates are overdue.

823 8d ago A 24 tokens original Apache-2.0

delegation

11

suyoumo/ClawProBench

Skill Claude CodeCodex

Helps users delegate tasks, break them into steps, set deadlines, and track progress via routines and memory.

823 8d ago A 25 tokens original Apache-2.0

developer-setup

12

suyoumo/ClawProBench

Skill Claude CodeCodex

One-time onboarding for the developer workflow — installs github-workflow missions, creates the commitments workspace, registers per-repo projects, writes calibration memories. After successful setup this skill is excluded from selection until the marker file is deleted.

823 8d ago A 49 tokens original Apache-2.0

github-workflow

13

suyoumo/ClawProBench

Skill Claude CodeCodex

Install and operate a full GitHub issue-to-merge workflow for any repository using event-driven and cron missions. Handles issue planning, PR monitoring, CI fixing, staging review, and post-merge learning.

823 8d ago A 45 tokens original Apache-2.0

github

14

suyoumo/ClawProBench

Skill Claude CodeCodex

GitHub API integration via HTTP tool with automatic credential injection.

823 8d ago A 13 tokens original Apache-2.0

idea-parking

15

suyoumo/ClawProBench

Skill Claude CodeCodex

Park interesting ideas for later consideration, resurface them periodically, and promote to commitments when ready.

823 8d ago A 23 tokens original Apache-2.0

linear

16

suyoumo/ClawProBench

Skill Claude CodeCodex

Linear issue tracker API integration. Covers first-use identity bootstrap (viewer + teams cached), raw GraphQL for list/search/create/update, and the rules for handling "my issues" / "assigned to me" requests.

823 8d ago A 45 tokens original Apache-2.0

llm-council

17

suyoumo/ClawProBench

Skill Claude CodeCodex

Query multiple LLM models in parallel from CodeAct and cross-reference their responses.

823 8d ago A 21 tokens original Apache-2.0

local-test

18

suyoumo/ClawProBench

Skill Claude CodeCodex

Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation.

823 8d ago A 22 tokens original Apache-2.0

new-project

19

suyoumo/ClawProBench

Skill Claude CodeCodex

Create and structure a new autonomous project — "/new-project ".

823 8d ago A 19 tokens original Apache-2.0

parallel-pr-review

20

suyoumo/ClawProBench

Skill Claude CodeCodex

Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.

823 8d ago A 67 tokens original Apache-2.0

plan-mode

21

suyoumo/ClawProBench

Skill Claude CodeCodex

Structured planning mode for autonomous task execution. Creates plans as MemoryDocs, executes via Missions, tracks progress with live checklist.

823 8d ago A 27 tokens original Apache-2.0

portfolio

22

suyoumo/ClawProBench

Skill Claude CodeCodex

Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…

823 8d ago A 69 tokens original Apache-2.0

suyoumo/ClawProBench

Skill Claude CodeCodex

Product strategy and feature prioritization — score features by user demand evidence, effort (human vs AI-assisted), strategic alignment, and market signal. Anti-sycophantic forcing questions to cut through opinion.

823 8d ago A 46 tokens original Apache-2.0

project-setup

24

suyoumo/ClawProBench

Skill Claude CodeCodex

Add a GitHub repository as a tracked project — creates workspace entity, installs workflow automation missions, and includes in dev brief scope.

823 8d ago A 30 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: