Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
Checkmate
Enforces task completion: turns your goal into pass/fail criteria, runs a worker, judges the output, feeds back what's missing, and loops until every criteri...
skill openclawclawhub Free
Enforces task completion: turns your goal into pass/fail criteria, runs a worker, judges the output, feeds back what's missing, and loops until every criteri...
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- README.md, SKILL.md, prompts/criteria-judge.md, prompts/intake.md, prompts/judge.md, prompts/orchestrator.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 2.0.4
Provenance
- Publisher
- InsipidPoint
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Checkmate
A deterministic Python loop (scripts/run.py) calls an LLM for worker and judge roles. Nothing leaves until it passes β and you stay in control at every checkpoint.
Requirements
OpenClaw platform CLI (openclaw) β must be available in PATH. Used for: openclaw gateway call sessions.list β resolve session UUID for turn injection openclaw agent --session-id <UUID> β inject checkpoint messages into the live session openclaw message send β fallback channel delivery (e.g. Telegram, Signal) Python 3 β run.py is pure stdlib; no pip packages required No separate API keys or env vars needed β routes through the gateway's existing OAuth
Security & Privilege Model
β οΈ This is a high-privilege skill. Read before using in batch/automated mode. Spawned workers and judges inherit full host-agent runtime, including: exec (arbitrary shell commands) web_search, web_fetch All installed skills (including those with OAuth-bound credentials β Gmail, Drive, etc.) sessions_spawn (workers can spawn further sub-agents) This means the task description you provide directly controls what the worker does β treat it like code you're about to run, not a message you're about to send. Batch mode (--no-interactive) removes all human gates. In interactive mode (default), you approve criteria and each checkpoint before the loop continues. In batch mode, criteria are auto-approved and the loop runs to completion autonomously β only use this for tasks and environments you fully trust. User-input bridging writes arbitrary content to disk. When you reply to a checkpoint, the main agent writes your reply verbatim to user-input.md in the workspace. The orchestrator reads it and acts on it. Don't relay untrusted third-party content as checkpoint replies.
When to Use
Use checkmate when correctness matters more than speed β when "good enough on the first try" isn't acceptable. Good fits: Code that must pass tests or meet a spec Docs or reports that must hit a defined quality bar Research that must be thorough and cover specific ground Any task where you'd otherwise iterate manually until satisfied Trigger phrases (say any of these): checkmate: TASK keep iterating until it passes don't stop until done until it passes quality loop: TASK iterate until satisfied judge and retry keep going until done
Architecture
scripts/run.py (deterministic Python while loop β the orchestrator) ββ Intake loop [up to max_intake_iter, default 5]: β ββ Draft criteria (intake prompt + task + refinement feedback) β ββ βΈ USER REVIEW: show draft β wait for approval or feedback β β approved? β lock criteria.md β β feedback? β refine, next intake iteration β ββ (non-interactive: criteria-judge gates instead of user) β ββ βΈ PRE-START GATE: show final task + criteria β user confirms "go" β (edit task / cancel supported here) β ββ Main loop [up to max_iter, default 10]: ββ Worker: spawn agent session β iter-N/output.md β (full runtime: exec, web_search, all skills, OAuth auth) ββ Judge: spawn agent session β iter-N/verdict.md ββ PASS? β write final-output.md, notify user, exit ββ FAIL? β extract gaps β βΈ CHECKPOINT: show score + gaps to user continue? β next iteration (with judge gaps) redirect:X β next iteration (with user direction appended) stop? β end loop, take best result so far Interactive mode (default): user approves criteria, confirms pre-start, and reviews each FAIL checkpoint. Batch mode (--no-interactive): fully autonomous; criteria-judge gates intake, no checkpoints.
User Input Bridge
When the orchestrator needs user input, it: Writes workspace/pending-input.json (kind + workspace path) Sends a notification via --recipient and --channel Polls workspace/user-input.md every 5s (up to --checkpoint-timeout minutes) The main agent acts as the bridge: when pending-input.json exists and the user replies, the agent writes their response to user-input.md. The orchestrator picks it up automatically. Each agent session is spawned via: openclaw agent --session-id <isolated-id> --message <prompt> --timeout <N> --json Routes through the gateway WebSocket using existing OAuth β no separate API key. Workers get full agent runtime: exec, web_search, web_fetch, all skills, sessions_spawn.
Your Job (main agent)
When checkmate is triggered: Get your session UUID (for direct agent-turn injection): openclaw gateway call sessions.list --params '{"limit":1}' --json \ | python3 -c "import json,sys; s=json.load(sys.stdin)['sessions'][0]; print(s['sessionId'])" Also note your --recipient (channel user/chat ID) and --channel as fallback. Create workspace: bash <skill-path>/scripts/workspace.sh /tmp "TASK" Prints the workspace path. Write the full task to workspace/task.md if needed. Run the orchestrator (background exec): python3 <skill-path>/scripts/run.py \ --workspace /tmp/checkmate-TIMESTAMP \ --task "FULL TASK DESCRIPTION" \ --max-iter 10 \ --session-uuid YOUR_SESSION_UUID \ --recipient YOUR_RECIPIENT_ID \ --channel <your-channel> Use exec with background=true. This runs for as long as needed. Add --no-interactive for fully autonomous runs (no user checkpoints). Tell the user checkmate is running, what it's working on, and that they'll receive criteria drafts and checkpoint messages via your configured channel to review and approve. Bridge user replies: When user responds to a checkpoint message, check for pending-input.json and write their response to workspace/user-input.md.
Bridging User Input
When a checkpoint message arrives (the orchestrator sent the user a criteria/approval/checkpoint request), bridge their reply: # Find active pending input cat <workspace-parent>/checkmate-*/pending-input.json 2>/dev/null # Route user's reply echo "USER REPLY HERE" > /path/to/workspace/user-input.md The orchestrator polls for this file every 5 seconds. Once written, it resumes automatically and deletes the file. Accepted replies at each gate: GateContinueRedirectCancelCriteria review"ok", "approve", "lgtm"any feedback textβPre-start"go", "start", "ok""edit task: NEW TASK""cancel"Iteration checkpoint"continue", (empty)"redirect: DIRECTION""stop"
Parameters
FlagDefaultNotes--max-intake-iter5Intake criteria refinement iterations--max-iter10Main loop iterations (increase to 20 for complex tasks)--worker-timeout3600sPer worker session--judge-timeout300sPer judge session--session-uuidβAgent session UUID (from sessions.list); used for direct turn injection β primary notification path--recipientβChannel recipient ID (e.g. user/chat ID, E.164 phone number); fallback if injection fails--channelβDelivery channel for fallback notifications (e.g. telegram, whatsapp, signal)--no-interactiveoffDisable user checkpoints (batch mode)--checkpoint-timeout60Minutes to wait for user reply at each checkpoint
Workspace layout
memory/checkmate-YYYYMMDD-HHMMSS/ βββ task.md # task description (user may edit pre-start) βββ criteria.md # locked after intake βββ feedback.md # accumulated judge gaps + user direction βββ state.json # {iteration, status} β resume support βββ pending-input.json # written when waiting for user; deleted after response βββ user-input.md # agent writes user's reply here; read + deleted by orchestrator βββ intake-01/ β βββ criteria-draft.md β βββ criteria-verdict.md (non-interactive only) β βββ user-feedback.md (interactive: user's review comments) βββ iter-01/ β βββ output.md # worker output β βββ verdict.md # judge verdict βββ final-output.md # written on completion
Resume
If the script is interrupted, just re-run it with the same --workspace. It reads state.json and skips completed steps. Locked criteria.md is reused; completed iter-N/output.md files are not re-run.
Prompts
Active prompts called by run.py: prompts/intake.md β converts task β criteria draft prompts/criteria-judge.md β evaluates criteria quality (APPROVED / NEEDS_WORK) β used in non-interactive mode prompts/worker.md β worker prompt (variables: TASK, CRITERIA, FEEDBACK, ITERATION, MAX_ITER, OUTPUT_PATH) prompts/judge.md β evaluates output against criteria (PASS / FAIL) Reference only (not called by run.py): prompts/orchestrator.md β architecture documentation explaining the design rationale
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
6 Docs
- SKILL.md
- prompts/criteria-judge.md
- prompts/intake.md
- prompts/judge.md
- prompts/orchestrator.md
- README.md