reporter-clarification-loop
/reporter-clarification-loop
Ask each reporter the one or two questions whose answers unblock triage, instead of silently guessing their intent or step order. Use when reports leave critical detail ambiguous: environment, step order, preconditions or the actual request sent
- Author
- Wsh7Ash ↗
- Repository
- patchwise ↗
- Licence
- MIT
- Last repository change
- 28.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 2
No signals detected. Repository changed on 28.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Ask each reporter the one or two questions whose answers unblock triage, instead of silently guessing their intent or step order. Use when reports leave critical detail ambiguous: environment, step order, preconditions or the actual request sent
Original author description
Ask each reporter the one or two questions whose answers unblock triage, instead of silently guessing their intent or step order. Use when reports leave critical detail ambiguous: environment, step order, preconditions or the actual request sent
How it works
- Procedure
- Signals
- Patterns
- Pitfalls
- Done when
- References
SKILL.md preview
--- name: reporter-clarification-loop description: "Ask each reporter the one or two questions whose answers unblock triage, instead of silently guessing their intent or step order. Use when reports leave critical detail ambiguous: environment, step order, preconditions or the actual request sent" pack: patchwise version: 1.0.0 category: defensive-security tags: [reporter, communication, triage] --- # Reporter Clarification Loop > Ask each reporter the one or two questions whose answers unblock triage, instead of silently guessing their intent or step order **Use when:** reports leave critical detail ambiguous: environment, step order, preconditions or the actual request sent **Avoid when:** the report already includes everything reproduction needs, in which case a reply would merely add latency ## Procedure 1. Identify precisely which fields, if clarified, would move reproduction or severity from uncertain to actionable. 2. Draft the minimal question set and link each question to the blocked decision it unblocks. 3. Send the questions through the channel that keeps context intact, including the reasoning so the reporter sees why it matters. 4. Set the review window in terms the reporter can act on, so waiting replaces guessing rather than resetting the clock. 5. When the reply arrives, update the normalized record and re-run the affected triage steps from that point. 6. Record the exchange so disputes about what was claimed later resolve from the conversation rather than memory. ## Signals - Reproduction repeatedly fails because two conditions seem to conflict, until the reporter explained their sequence. - The reporter's environment detail arrives after your reproduction attempt and changes most assumptions. - Clarifications shift the affected scope, which typically means triage is restarting rather than resuming. - Several reports stall over the same repeated question, which indicates an intake template gap rather than reporter behavior. ## Patterns **1. Question** ```text for F-0113: what exact version are you running, and were the two tokens used in the same session? ``` **2. Blocked on** ```text reproduction blocked on precondition=version; severity blocked on scope=one-vs-all ``` **3. Update row** ```text reply 2026-10-28: tokens in same session -> scope narrower; update record, resume repro ``` ## Pitfalls - Asking every question at once, when only one or two answers truly change the next decision. - Guessing the reporter's environment rather than asking, which propagates unverifiable assumptions into records. - Forgetting to update the record after clarification arrives, so the queue's later reading forgets the newer information. ## Done when - Ambiguous fields are asked through the reporter with the reasoning attached, then answers reflected in the record. - The question-exchange trail is stored so the trajectory from claim to confirmed evidence is reconstructable. ## References - [ISO 29147 - disclosure process](https://www.iso.org/standard/72311.html) - [HackerOne - triage guidance for teams](https://www.hackerone.com/)
Versions
The database has no other skills named reporter-clarification-loop.
Database snapshot: 13.11.2026 · package version 4fe2d3ba9304 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100reporter-follow-up-and-thanks
Close the loop with the reporter: what was verified, what was fixed and which follow-ups remain, until the report is visibly resolved. Use when the fix is verified and the reporter's submission deserves closure it can actually read - 90repro-gpu-issue
Reproduce a 3D graphics problem reported against UTM (Neptune D3D, Venus, the guest-tools GPU driver), from a utmapp/UTM GitHub issue or a games-db report (db-triage follows it from step 2; answer-utm-issue hands graphics issues to it) — extract the reporter's exact environment,… - 100playwright-execute
Run Playwright tests or suites and upload the resulting report to Katalon True Platform. Use when you need to execute Playwright scripts, package scripts, spec files, projects, or suites, configure or verify @katalon/playwright-reporter, upload Playwright reports with Katalon… - 90test-results-reporter
When the user needs to execute test suites and generate formatted test reports with pass/fail status, summary statistics, and detailed results. This skill involves reading test specifications, running tests, evaluating outcomes, and creating structured markdown reports with…