bot-tasks

Included with Lifetime

$97 forever

Check bot notifications for tasks requested by the repo owner, then execute them using a team

General

What this skill does

# Process Bot Task Requests

Check the bot account's GitHub notifications for issues and PRs where the owner has asked the bot to do something, then execute those tasks.

Read the bot and owner accounts from the org's CLAUDE.md `## Automation config` table (`bot_account` and `owner_account`).

## Helper script

A pre-built script at `~/.claude/scripts/bot-tasks.sh` collects unprocessed task requests in one pass.
Run it first to avoid spending tokens on notification parsing.

```bash
~/.claude/scripts/bot-tasks.sh > /tmp/bot-tasks.json
```

If the script is missing or not executable, run `/setup-scripts` to regenerate it.

The script outputs a JSON object with:
- `notifications`: raw notification list
- `tasks`: array of unprocessed task requests with `thread_id`, `repo`, `type`, `number`, `title`, `url`, `comment_id`, `request` (the comment body)

Tasks are identified by:
- Direct mentions of the bot account in comments by the owner
- Comments by the owner on bot-authored issues/PRs containing task language
- Filtered to exclude comments already reacted to with 👀 (eyes emoji)

## Emoji deduplication

When a task request is processed:
1. React to the comment with 👀 (eyes) to mark it as seen
2. This prevents re-processing on future runs

```bash
gh api -X POST "repos/{repo}/issues/comments/{comment_id}/reactions" -f content=eyes
```

## Cron integration

A cron trigger script at `~/.claude/scripts/cron-bot-tasks.sh` polls every 5 minutes.
It only triggers Claude Code if there are new unprocessed requests.
Set up via: `crontab -e` and add:
```
*/5 * * * * ~/.claude/scripts/cron-bot-tasks.sh >> ~/.claude/logs/cron-bot-tasks.log 2>&1
```

## Phase 1: Parse script output

Read the `tasks` array from the JSON.
Skip if empty.

## Phase 2: Triage

Present a numbered list of tasks found:
- Issue/PR link
- What the owner asked for (quote the relevant comment)
- Repo
- Estimated complexity (simple/medium/complex)

Ask the user to confirm which tasks to execute, or proceed with all if invoked with `--all`.

## Phase 3: Execute as a team

Spawn a team with one teammate per task (up to 5 concurrent).
Each teammate:

1. Clones or navigates to the repo
2. Creates a worktree branch if code changes are needed
3. Implements the requested change using /pr patterns
4. Runs tests and linting
5. Commits, pushes, and creates a PR (or pushes to existing PR branch)
6. Replies to the original issue/comment confirming what was done
7. Reacts to the original comment with 👀 to mark as processed

For non-code tasks (labelling, closing, commenting):
- Execute directly without a worktree

## Phase 4: Clean up

1. Mark processed notifications as read: `gh api -X PATCH notifications/threads/{id}`
2. Report results to the team lead

## Phase 5: Summary

Report:
- Tasks completed (with PR/comment links)
- Tasks skipped (with reason)
- Tasks that failed (with error details)

## Auto-Exit When Standalone

**IMPORTANT**: If this command is being run as a standalone request, automatically exit after completing all phases successfully.

Files: 1

Size: 3.1 KB

Complexity: 5/100

Category: General

Source: https://github.com/seabbs/skills/tree/main/plugins/bot-automation/skills/bot-tasks

Related in General

modeling-omnistudio-epc-catalog

Included

Salesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).

Generalscripts

relationship-science-coach

Included

Use this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.

Generalscripts

building-sf-integrations

Included

Salesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).

Generalscripts

venue-templates

Included

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.

Generalscripts

let-fate-decide

Included

Draws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.

Generalscripts

net-ops

Included

Cross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.

Generalscripts