Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.
.claude/skills/foryourhealth111-pixel-sentry/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 98% | 45 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 138% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 109% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -20% | 0% |
SENTRY_AUTH_TOKEN (read-only scopes such as project:read, event:read) or to log in and create one before running commands.SENTRY_AUTH_TOKEN as an env var.SENTRY_ORG, SENTRY_PROJECT, SENTRY_BASE_URL.{your-org}/{your-project}, time range 24h, environment prod, limit 20 (max 50).If the token is missing, give the user these steps:
project:read, event:read, and org:read.SENTRY_AUTH_TOKEN as an environment variable in their system.Use scripts/sentry_api.py for deterministic API calls. It handles pagination and retries once on transient errors.
bashexport CODEX_HOME="${CODEX_HOME:-$HOME/.codex}" export SENTRY_API="$CODEX_HOME/skills/sentry/scripts/sentry_api.py"
User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills).
bashpython3 "$SENTRY_API" \ list-issues \ --org {your-org} \ --project {your-project} \ --environment prod \ --time-range 24h \ --limit 20 \ --query "is:unresolved"
bashpython3 "$SENTRY_API" \ list-issues \ --org {your-org} \ --project {your-project} \ --query "ABC-123" \ --limit 1
Use the returned id for issue detail or events.
bashpython3 "$SENTRY_API" \ issue-detail \ 1234567890
bashpython3 "$SENTRY_API" \ issue-events \ 1234567890 \ --limit 20
bashpython3 "$SENTRY_API" \ event-detail \ --org {your-org} \ --project {your-project} \ abcdef1234567890
Always use these endpoints (GET only):
/api/0/projects/{org_slug}/{project_slug}/issues//api/0/issues/{issue_id}//api/0/issues/{issue_id}/events//api/0/projects/{org_slug}/{project_slug}/events/{event_id}/org_slug, project_slug: default to {your-org}/{your-project} (avoid non-prod orgs).time_range: default 24h (pass as statsPeriod).environment: default prod.limit: default 20, max 50 (paginate until limit reached).search_query: optional query parameter.issue_short_id: resolve via list-issues query first.{your-org}{your-project}{ABC-123}Example prompt: “List the top 10 open issues for prod in the last 24h.” Expected: ordered list with titles, short IDs, counts, last seen.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | fail→pass | 3,902 | 7,151 | +83% | 1 | 1 | 0% | 701 | 1,667 | +138% | 0 | 0 | — |
case-19 | pass→fail | 9,717 | 1,475 | -85% | 1 | 1 | 0% | 1,715 | 1,360 | -21% | 0 | 0 | — |
case-01 | fail→fail | 8,260 | 8,524 | +3% | 1 | 1 | 0% | 1,271 | 1,667 | +31% | 0 | 0 | — |
case-02 | fail→fail | 8,390 | 5,592 | -33% | 1 | 1 | 0% | 1,267 | 1,428 | +13% | 0 | 0 | — |
case-03 | fail→pass | 10,223 | 12,623 | +23% | 1 | 1 | 0% | 2,082 | 3,096 | +49% | 0 | 0 | — |
case-04 | pass→pass | 10,654 | 5,136 | -52% | 1 | 1 | 0% | 2,142 | 2,161 | +1% | 0 | 0 | — |
case-05 | fail→pass | 11,937 | 3,631 | -70% | 1 | 1 | 0% | 2,111 | 1,889 | -11% | 0 | 0 | — |
case-06 | fail→pass | 6,617 | 8,207 | +24% | 1 | 1 | 0% | 1,300 | 2,711 | +109% | 0 | 0 | — |
case-07 | fail→pass | 10,965 | 3,008 | -73% | 1 | 1 | 0% | 2,195 | 1,763 | -20% | 0 | 0 | — |
case-08 | fail→pass | 10,675 | 2,452 | -77% | 1 | 1 | 0% | 2,217 | 1,626 | -27% | 0 | 0 | — |
case-10 | pass→pass | 3,494 | 1,680 | -52% | 1 | 1 | 0% | 636 | 1,363 | +114% | 0 | 0 | — |
case-11 | pass→fail | 8,778 | 2,393 | -73% | 1 | 1 | 0% | 1,280 | 1,517 | +19% | 0 | 0 | — |
case-12 | fail→pass | 15,122 | 5,102 | -66% | 1 | 1 | 0% | 2,525 | 2,051 | -19% | 0 | 0 | — |
case-13 | pass→pass | 12,664 | 3,081 | -76% | 1 | 1 | 0% | 2,605 | 1,717 | -34% | 0 | 0 | — |
case-14 | fail→pass | 6,901 | 2,494 | -64% | 1 | 1 | 0% | 1,233 | 1,598 | +30% | 0 | 0 | — |
case-15 | pass→fail | 9,598 | 1,579 | -84% | 1 | 1 | 0% | 1,439 | 1,379 | -4% | 0 | 0 | — |
case-16 | fail→pass | 13,783 | 2,711 | -80% | 1 | 1 | 0% | 2,369 | 1,499 | -37% | 0 | 0 | — |
case-17 | pass→pass | 4,000 | 1,555 | -61% | 1 | 1 | 0% | 704 | 1,332 | +89% | 0 | 0 | — |
case-18 | pass→pass | 4,363 | 2,170 | -50% | 1 | 1 | 0% | 838 | 1,512 | +80% | 0 | 0 | — |
case-20 | fail→pass | 10,868 | 3,496 | -68% | 1 | 1 | 0% | 1,934 | 1,839 | -5% | 0 | 0 | — |
case-21 | pass→pass | 8,737 | 7,976 | -9% | 1 | 1 | 0% | 1,789 | 2,617 | +46% | 0 | 0 | — |
case-22 | pass→pass | 8,942 | 7,270 | -19% | 1 | 1 | 0% | 1,640 | 2,428 | +48% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 20 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +32 percentage points is the difference between those two pass rates over the 20 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.