xiduzo/wtf / skills/wtf.health
wtf.health
VerifiedThis skill should be used when a developer or lead wants a project status overview — what is blocked, stale, unverified, or waiting on a next step — for example "project health check", "what's blocking the release", "standup summary", or "what's left in this epic". Scans all open WTF issues — Traces plus legacy Tasks — and produces a triage-ready health report with actionable next steps.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.5 KB |
| evals/evals.json | config | 4.5 KB |
| evals/fixtures/clean.json | config | 230 B |
| evals/fixtures/implemented-not-verified.json | config | 1.6 KB |
| evals/fixtures/legacy-task-and-unticked-plan.json | config | 2.4 KB |
| evals/fixtures/stale-designed.json | config | 1.7 KB |
evals/evals.json
View on GitHub{
"skill_name": "wtf.health",
"evals": [
{
"id": 1,
"prompt": "Run a health check on the project. Test mode: skip step 0 (gh setup already confirmed) and step 1 (use 'Full project' scope). Instead of running `gh issue list` commands in step 2, read `evals/fixtures/clean.json` and use its `epics`, `features`, `traces`, `bugs`, and `pull_requests` arrays as the live issue data. Each array matches the `gh issue list --json number,title,labels,updatedAt` format.",
"expected_output": "A health report stating that all open issues are in a healthy state, with no ⚠️ or 🕐 sections.",
"files": [
"evals/fixtures/clean.json"
],
"expectations": [
"The report includes the phrase 'All open issues are in a healthy state'",
"The report does not contain any ⚠️ Needs attention section",
"The report does not contain any 🕐 Stale section"
]
},
{
"id": 2,
"prompt": "Run a health check on the project. Test mode: skip step 0 (gh setup already confirmed) and step 1 (use 'Full project' scope). Instead of running `gh issue list` commands in step 2, read `evals/fixtures/implemented-not-verified.json` and use its `epics`, `features`, `traces`, `bugs`, and `pull_requests` arrays as the live issue data. Each array matches the `gh issue list --json number,title,labels,updatedAt` format (the features array also carries `body`).",
"expected_output": "A health report with a ⚠️ Needs attention section showing trace #42 as implemented but not verified, with the next step suggesting `wtf.verify-trace`.",
"files": [
"evals/fixtures/implemented-not-verified.json"
],
"expectations": [
"The ⚠️ Needs attention section includes trace #42",
"The report identifies the gap as implemented but not verified",
"The suggested next step references verify-trace or wtf.verify-trace for trace #42"
]
},
{
"id": 3,
"prompt": "Run a health check on the project. Test mode: skip step 0 (gh setup already confirmed) and step 1 (use 'Full project' scope). Instead of running `gh issue list` commands in step 2, read `evals/fixtures/stale-designed.json` and use its `epics`, `features`, `traces`, `bugs`, and `pull_requests` arrays as the live issue data. Each array matches the `gh issue list --json number,title,labels,updatedAt` format (the features array also carries `body`). Today's date is 2026-05-04.",
"expected_output": "A health report with a 🕐 Stale section containing trace #17, indicating it has been inactive since being designed, with a stale count of at least 7 days.",
"files": [
"evals/fixtures/stale-designed.json"
],
"expectations": [
"The 🕐 Stale section includes trace #17",
"The report indicates the trace has had no activity since it was designed",
"The stale duration shown is at least 7 days"
]
},
{
"id": 4,
"prompt": "Run a health check on the project. Test mode: skip step 0 (gh setup already confirmed) and step 1 (use 'Full project' scope). Instead of running `gh issue list` commands in step 2, read `evals/fixtures/legacy-task-and-unticked-plan.json` and use its `epics`, `features`, `traces`, `tasks`, `bugs`, and `pull_requests` arrays as the live issue data. `tasks` is what the legacy-Task filter of the Trace query returns. Each array matches the `gh issue list --json number,title,labels,updatedAt` format (the features array also carries `body`; pull_requests carry `state`). Today's date is 2026-05-04.",
"expected_output": "A health report that lists legacy Task #33 as waiting for QA and marks it 'legacy Task', and flags Trace #42 under ⚠️ Needs attention as verified while its Trace Plan entry in Feature #10 is still unticked (Trace Plan out of sync). The next step for #42 is to tick the plan entry (or re-run verify-trace), not to write a new Trace. Nothing suggests write-trace for the legacy Task.",
"files": [
"evals/fixtures/legacy-task-and-unticked-plan.json"
],
"expectations": [
"The report lists issue #33 and marks the finding 'legacy Task'",
"The ⚠️ Needs attention section includes trace #42 with a 'Trace Plan out of sync' finding (verified label, plan entry unticked)",
"The suggested next step for #42 refers to ticking its Trace Plan entry in Feature #10 or re-running verify-trace, not write-trace",
"The report does not suggest write-trace for legacy Task #33",
"The summary counts line reports 1 legacy Task"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |