Demo-Slap Highlight Skill

---

name: demo-slap

description: Generate CS2 highlights and fragmovies from demos using the Demo-Slap API, with optional Leetify integration and Demo-Slap match history fallback to select recent matches. Use when a user asks to record a highlight, render a clip, make a fragmovie, clip a round, or turn a CS2 demo into MP4 video.

metadata:

{

"openclaw": {

"requires": {

"env": ["DEMOSLAP_API_KEY"],

"bins": ["python3", "openclaw"]

}

}

}

---

# Demo-Slap Highlight Skill

Generate MP4 highlights and fragmovies from CS2 demos.

This skill is designed for OpenClaw environments where background jobs, local helper scripts, and chat-aware delivery are available. It uses Python 3 scripts and the `requests` package for HTTP API access.

Expected runtime inputs:

Scripts

Run bundled scripts relative to the skill root, usually from `scripts/`.

Demo-Slap

| Script | Purpose |

|--------|---------|

| `demo_slap_matches.py` | List recent matches from Demo-Slap `/public-api/matches` |

| `demo_slap_resolve.py` | Try to resolve replay/demo URL from Demo-Slap match history by index; fail clearly if the API exposes only `jobId` |

| `demo_slap_match_pick.py` | Pick a Demo-Slap match by index and return structured match info including `jobId` |

| `demo_slap_analyze.py` | Submit a demo for analysis, poll until done, output highlights JSON |

| `demo_slap_render.py` | Render one or more highlights, poll until done, output clip URL |

| `demo_slap_common.py` | Shared utilities (config, API calls, state) |

Leetify

| Script | Purpose |

|--------|---------|

| `leetify/leetify_matches.py` | List recent matches |

| `leetify/leetify_resolve.py` | Resolve replay URL by username + match index |

| `leetify/leetify_save_id.py` | Save username -> Steam64 ID mapping |

| `leetify/leetify_common.py` | Shared Leetify utilities |

Match source selection

Runtime files

Use these files as optional local runtime state during execution:

These files are runtime helpers for local operation and are not required to understand or inspect the skill package itself.

`state.json` tracks the current operation:

{
  "status": "idle|analyzing|rendering|done|error",
  "job_id": "...",
  "render_job_id": "...",
  "chat_id": "telegram:182314856",
  "clip_urls": {"highlight_id": "https://..."},
  "progress": "polling 3/30",
  "last_completed_op": "analyze|render",
  "notification": {
    "sent": false,
    "sent_at": null,
    "last_attempt_at": null,
    "error": null
  },
  "updated_at": "ISO timestamp"
}

Workflow

1. Find the match

Preferred path when `LEETIFY_API_KEY` is available:

python3 scripts/leetify/leetify_matches.py <USERNAME> [--limit 10]

Fallback path when `LEETIFY_API_KEY` is missing but `DEMOSLAP_API_KEY` is available:

python3 scripts/demo_slap_matches.py [<USERNAME>] [--limit 10]

python3 scripts/demo_slap_match_pick.py [<USERNAME>] --match-index <N>

2. Resolve replay URL

Preferred path when using Leetify:

python3 scripts/leetify/leetify_resolve.py <USERNAME> --match-index <N>

When using Demo-Slap fallback:

python3 scripts/demo_slap_match_pick.py [<USERNAME>] --match-index <N>

3. Analyze in background

python3 -u scripts/demo_slap_analyze.py --url '<REPLAY_URL>' --username <USERNAME> --chat-id <CHAT_ID>

Run with `exec(background: true)` and keep the returned process/session id.

Optional deployment-specific watchdog pattern for OpenClaw environments:

Agent workflow:

1. Choose the match source:

- Leetify if `LEETIFY_API_KEY` exists

- Demo-Slap `/public-api/matches` if `LEETIFY_API_KEY` is missing and `DEMOSLAP_API_KEY` exists

2. If using Leetify, resolve the replay URL and run analyze

3. If using Demo-Slap fallback, pick a match and inspect the returned `jobId`

4. If the selected Demo-Slap match already has analyze data, continue by `jobId` instead of forcing analyze-by-URL

5. Use or enable a deployment watchdog only when long-running analyze/render work benefits from it

6. Launch analyze or render and save the returned process/session id when applicable

7. Let the watchdog deliver the result when a deployment uses one

8. Disable the watchdog again after terminal delivery

4. Render in background

# Single highlight
python3 -u scripts/demo_slap_render.py <JOB_ID> <HIGHLIGHT_ID> --chat-id <CHAT_ID>

# Fragmovie
python3 -u scripts/demo_slap_render.py <JOB_ID> <ID1> <ID2> ... --fragmovie --chat-id <CHAT_ID>

Run with `exec(background: true)` and keep the returned process/session id.

Optional deployment-specific watchdog pattern for OpenClaw environments:

Agent workflow:

1. Enable or reuse a deployment watchdog only when needed for the active run

2. Launch render and save the returned process/session id

3. Poll process output for the `Estimated finish:` line and tell the user the ETA if present

4. Let the watchdog deliver the result when one is in use

5. Disable the watchdog again after terminal delivery

**Critical:** set `<CHAT_ID>` from inbound metadata of the originating request. Treat hardcoded chat identifiers as local examples only, not as a reusable default.

5. Check status

Read `data/state.json`.

Setup

Map username to Steam ID

python3 scripts/leetify/leetify_save_id.py <USERNAME> <STEAM_64_ID>

Configure API keys

Prefer environment variables:

Source selection rules:

Optional local fallback for controlled self-hosted setups: put them in `data/config.json`.

Support

For access and support, please join our Discord community: https://discord.gg/8nfh26W9wQ