borghei/Claude-Skills / project-management/execution/issue-triage
issue-triage
VerifiedMove engineering issues and external PRs through a triage state machine and write agent-ready briefs. Use when clearing a triage queue, deciding if a report is real or wanted, or handing an issue to a coding agent.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.4 KB |
| assets/agent_brief_template.md | markdown | 2.1 KB |
| assets/label_scheme_template.md | markdown | 2.7 KB |
| assets/out_of_scope_entry_template.md | markdown | 1.6 KB |
| assets/sample_agent_brief_clean.md | markdown | 2.6 KB |
| assets/sample_agent_briefs.json | config | 2.8 KB |
| assets/sample_triage_history.json | config | 3.7 KB |
| assets/sample_triage_history_clean.json | config | 3.4 KB |
| assets/triage_notes_template.md | markdown | 2.1 KB |
| references/agent-briefs.md | markdown | 10.3 KB |
| references/evidence-and-out-of-scope.md | markdown | 9.2 KB |
| references/state-machine-and-labels.md | markdown | 10.4 KB |
| scripts/agent_brief_linter.py | script | 10.1 KB |
| scripts/triage_state_validator.py | script | 12.6 KB |
assets/sample_agent_brief_clean.md
View on GitHub# Agent briefs ready for hand-off
Both briefs below pass the linter (exit 0). The first goes to a coding agent;
the second stays with a human and says why.
## Agent Brief
**ID:** #231
**Target state:** ready-for-agent
**Category:** bug
**Summary:** A webhook delivery that receives a 503 is retried twice instead of once
**Current behavior:**
When the receiving endpoint answers 503, a retry is scheduled from the failure
callback and again from the timeout watchdog, so the receiver gets two
identical retries about 30 seconds apart.
**Desired behavior:**
Each failed delivery attempt schedules exactly one retry, whichever failure
path observes the error. Retries keep the existing backoff schedule and carry
the idempotency key of the original attempt.
**Key interfaces:**
- `DeliveryAttempt` status: an attempt reaches `retry_scheduled` at most once
- `RetryPolicy.next_delay(attempt_number)` is unchanged
**Acceptance criteria:**
- [ ] A 503 response produces exactly one scheduled retry for that attempt
- [ ] A timeout followed by a late 503 for the same attempt produces exactly one scheduled retry
- [ ] Every retry carries the idempotency key of the original delivery
- [ ] The backoff delays (10s, 30s, 90s) are unchanged
**Out of scope:**
- Changing the retry schedule or the maximum attempt count
- Dead-letter queue behaviour after the final attempt
**Verification:** `make test-integration TEST=webhook_retry`
## Agent Brief
**ID:** #238
**Target state:** ready-for-human
**Category:** enhancement
**Summary:** Finish the contributor's machine-readable output flag for the list command
**Current behavior:**
The pull request adds a `--json` flag that serialises the item list. Success
output works; errors still print as plain text and the flag has no tests.
**Desired behavior:**
With `--json`, all output including errors is one well-formed JSON document on
stdout, and exit codes match the plain-text command. Without the flag, output
is byte-for-byte unchanged.
**Key interfaces:**
- Error payload under `--json`: `{"error": string}`
- The serialiser the pull request already adds is reused, not duplicated
**Acceptance criteria:**
- [ ] `list --json` emits valid JSON when the command succeeds
- [ ] `list --json` emits `{"error": ...}` when the command fails
- [ ] Exit codes with `--json` equal the exit codes without it
- [ ] Output without `--json` is byte-for-byte unchanged
**Out of scope:**
- Adding `--json` to any other command
- Changing the success payload shape the pull request defines
**Why not delegated:** The JSON shape becomes a public contract that downstream scripts will parse; a maintainer has to approve it.
**Verification:** `make test TEST=cli_list`
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 |