Menu
Report metrics and events to ClawOSS dashboard API via curl.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Discover FRESH issues in WELL-MAINTAINED repos (200+ stars). Merge-optimized: 60% easy wins (docs, typos, tests) + 40% bug fixes. Target agentic AI repos by CRITERIA (topic:llm/agent/rag + stars:>200). Verify repo health before queuing.
Orchestrator-level PR follow-up detection and delegation: scan open PRs for new review comments, classify feedback type, write context files to subagent-inputs, delegate to oss-pr-review-handler sub-agents. Does NOT implement changes directly.
Sub-agent skill for handling PR review feedback: clone repo, checkout PR branch, read all review comments (inline + general), implement requested changes, push updates, respond to reviewers via gh CLI, cleanup workspace. Spawned 1-per-PR by the orchestrator.
Submit a contribution PR (bug fix, docs fix, typo fix, or test addition) to an open-source repo: verify it's a valid contribution, push branch to fork, create PR with gh CLI, use repo's PR template, log submission, report to dashboard.
Triage GitHub issues: confirm contribution type (bug/docs/typo/test), assess feasibility, check repo health (merge velocity, review rate). Merge-optimized scoring: +5 docs/typo, +3 tests, +5 fast merge repos. REJECT issues in unhealthy repos.
Analyze repo health and conventions BEFORE queuing any issue. MANDATORY health gate: stars >=200, last commit <2wk, merge time <14d, review rate >50%, open PRs <50. Use /Users/kevinlin/clawOSS/scripts/repo-health-check.sh for automation.
| name | dashboard-reporter |
| description | Report metrics and events to ClawOSS dashboard API via curl. |
| user-invocable | false |
| disable-model-invocation | false |
Send telemetry to the dashboard. Agent ID: "clawoss", user: "BillionClaw".
Auth: Authorization: Bearer $CLAW_API_KEY. All curls use -s --max-time 10.
URL base: $DASHBOARD_URL (default: https://clawoss-dashboard.vercel.app)
Heartbeat — POST /api/ingest/heartbeat
{"agent_id":"clawoss","status":"alive","currentTask":"...","uptimeSeconds":N}
Metrics — POST /api/ingest/metrics
{"metrics":[{"provider":"kimi-code","model":"kimi-coding/k2p5","inputTokens":N,"outputTokens":N}]}
Cost is auto-computed server-side from the model name. If costUsd is omitted or 0, the dashboard uses its cost-models table (kimi-coding/k2p5: $0.60/$3.00 per MTok). You can send costUsd to override.
Logs — POST /api/ingest/logs
{"entries":[{"level":"info","source":"agent","message":"...","timestamp":"ISO8601"}]}
If dashboard unreachable, log locally and continue. Never block work for telemetry.
When logging sub-agent failures, include the standardized failure_reason category
from the taxonomy (see templates/subagent-result-schema.md). This enables dashboard
aggregation and pattern detection.
Log format for failures:
{"entries":[{"level":"warn","source":"agent","message":"sub-agent failure: {repo}#{issue} — {failure_category}: {details}","timestamp":"ISO8601","metadata":{"repo":"{repo}","issue":"{issue}","failureCategory":"{category}","failureDetails":"{details}"}}]}
The failureCategory field must be one of the taxonomy values (e.g., not_a_bug,
too_complex, repo_health_fail). The dashboard can aggregate these to show
which failure modes are most common and help the agent adapt its strategy.