repro-template
A bug isn't ready to fix until you can trigger it on demand. Fill this out *before* editing any code.
$ npx -y skills add vanara-agents/skills --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
A bug isn't ready to fix until you can trigger it on demand. Fill this out *before* editing any code.
Agent definition
repro-template.mdMinimal Reproduction Checklist
A bug isn't ready to fix until you can trigger it on demand. Fill this out *before* editing any code.
1. The failure (verbatim)
- **Error message / stack trace:** _paste the full text, unedited_
- **Where it surfaced:** `file:line` of the top user-code frame
- **Expected vs actual behavior:** _one line each_
2. The trigger
- **Exact input / steps:**
1. _step_ 2. _step_ 3. _failure observed_
- **Frequency:** [ ] every time [ ] intermittent (___ % of runs) [ ] only under load/concurrency
- **First seen:** _commit / version / date_ — and the last known-good version, if any
3. The environment
| Factor | Value | |---|---| | OS / runtime version | | | Dependency versions | | | Config / env vars | | | Data / fixtures | |
4. Reduce to the minimum
Strip everything that *doesn't* affect the outcome until you have the smallest case that still fails:
- [ ] Removed unrelated code paths
- [ ] Replaced external calls with fixed stubs/fixtures
- [ ] Hard-coded the triggering input
- [ ] Confirmed it **still fails** after reduction
- [ ] Confirmed it is **deterministic** (or documented the flake rate + suspected race)
5. The repro artifact
A runnable snippet or single failing test is the goal — paste it here:
# minimal failing command or test
$ npm test -- checkout.spec.js -t "applies discount once"
✗ applies discount once (expected 90, got 81)
> If you cannot produce a deterministic repro after a bounded effort, **stop**. Record what you tried and > exactly what additional evidence (logs, prod input, env access) you need — do not guess-edit.
Read more
Minimal Reproduction Checklist
A bug isn't ready to fix until you can trigger it on demand. Fill this out *before* editing any code.
1. The failure (verbatim)
- **Error message / stack trace:** _paste the full text, unedited_
- **Where it surfaced:** `file:line` of the top user-code frame
- **Expected vs actual behavior:** _one line each_
2. The trigger
- **Exact input / steps:**
1. _step_ 2. _step_ 3. _failure observed_
- **Frequency:** [ ] every time [ ] intermittent (___ % of runs) [ ] only under load/concurrency
- **First seen:** _commit / version / date_ — and the last known-good version, if any
3. The environment
| Factor | Value | |---|---| | OS / runtime version | | | Dependency versions | | | Config / env vars | | | Data / fixtures | |
4. Reduce to the minimum
Strip everything that *doesn't* affect the outcome until you have the smallest case that still fails:
- [ ] Removed unrelated code paths
- [ ] Replaced external calls with fixed stubs/fixtures
- [ ] Hard-coded the triggering input
- [ ] Confirmed it **still fails** after reduction
- [ ] Confirmed it is **deterministic** (or documented the flake rate + suspected race)
5. The repro artifact
A runnable snippet or single failing test is the goal — paste it here:
# minimal failing command or test $ npm test -- checkout.spec.js -t "applies discount once" ✗ applies discount once (expected 90, got 81)
> If you cannot produce a deterministic repro after a bounded effort, **stop**. Record what you tried and > exactly what additional evidence (logs, prod input, env access) you need — do not guess-edit.
🐒 Free agents, skills & packs for Claude Code One subscription. An army of Claude Code agents. 30 production-grade agents, skills, and packs for Claude Code — free, Apache-2.0, install with one command.
Repo: vanara-agents/skills
Other agents on vanara-agents-skills.
- AGENT
Use when designing a new HTTP/GraphQL API or changing an existing one — modeling resources, defining endpoint contracts, choosing status codes, pagination, filtering, error envelopes, versioning, and idempotency. Produces a reviewable API contract plus an OpenAPI snippet, not
Open agent - review-notes
This shows how the api-designer agent reviews a flawed draft. Findings are severity-ranked so the implementer fixes the contract-breakers first. Severity legend: **CRITICAL** (breaks clients / data risk), **HIGH** (real bug or inconsistency), **MEDIUM** (maintainability),
Open agent - contract-and-openapi
The contract is the deliverable. Express it as an **OpenAPI 3.1** document so it is human-readable *and* machine-checkable. This reference covers how to structure that document and what `scripts/lint-openapi.mjs` enforces.
Open agent - design-checklist
Run through this before declaring an API contract done. It is ordered the way you should *design*: resources first, cross-cutting rules last. Every box is a place real APIs go wrong in production.
Open agent - versioning-and-evolution
APIs are forever once published: a consumer you've never met may depend on any field you expose. Design so you can **add without breaking**, and version explicitly when you must break.
Open agent - pr-comment-template
Copy-paste templates for leaving review comments. Keep each comment to one finding: an anchor, the problem, and the fix.
Open agent

