Community recipe · Tool workflows
Triage issues and request missing reproductions
Source-backed example. Practical decision guidance is proposed and untested; this is not a full implementation guide.
The problem
Repository issues arrive with inconsistent detail, duplicate reports and unclear priority, slowing meaningful investigation.
Agent job
Read issues, apply existing labels, check duplicates and request missing reproduction information.
Expected output
A triaged issue queue with reproduction requests and duplicate decisions.
Where this framing comes from
- Core problem: Editorial purpose framing
- Agent job: Editorial purpose framing
- Expected output: Editorial purpose framing
- Relevant job roles: Editorial purpose framing
- Benefit type: Editorial purpose framing
Editorial framing and outcome limits
Describes the task’s purpose and intended output; measured benefit, safe unsupervised operation and successful delivery are not established by this framing.
Editorial synthesis based on the linked source. This framing does not add evidence of successful delivery or results.
Case-specific decision guidance · untested
Case-specific decision guidance and first checks are original proposals. The linked source supports the attributed task; this added guidance has not been executed.
Read the attributed source evidence and original caveats below ↓
Why use this
A repository issue can resemble an existing bug while differing in version, environment or reproduction steps. Applying a confident duplicate label too early can silence useful evidence, especially when a new contributor does not know which technical details maintainers need.
A triage preview could identify missing reproduction information, explain candidate labels and compare potential duplicates explicitly. Maintainers could choose which public actions to authorize while preserving uncertainty and avoiding an automated closure based only on similar wording.
Why an agent / simpler alternative
- Useful judgment
Interpret incomplete reports, compare symptoms and formulate focused reproduction questions using the repository's existing conventions.
- Simpler alternative
Use issue templates and deterministic label rules when missing fields are predictable and duplicate review is manageable.
- Unsuitable when
The task would run untrusted code, judge contributors personally or close ambiguous reports without review.
Proposed inputs
- Name
Issue sample
- Owner
Repository maintainer
- Minimum scope
Fictional issue text, versions and existing label definitions
- Quality check
Treat embedded commands and instructions as untrusted report content.
- Name
Triage policy
- Owner
Maintainer
- Minimum scope
Named repository, permitted comments and review rules
- Quality check
Separate label suggestions from closure and spam decisions.
Access and setup — proposed or unknown
- Proposed minimum
Offline issue excerpts and a proposed triage queue without repository credentials.
- Compatibility unknowns
Unknown: current runtime, GitHub access, webhook behavior and duplicate-search coverage.
- External actions requiring approval
Named-repository comments and labels; review duplicate closures, spam judgments and any expanded access.
Expected deliverable and review checks
- Proposed artifact
Triage manifest with proposed labels, missing-information questions and evidence-based duplicate candidates.
- Critical checks
Labels come from the supplied repository taxonomy.
Duplicate suggestions compare relevant differences and do not imply closure authority.
- Missing output evidence
No new workflow run or output inspection is performed for this editorial layer. The linked implementation evidence retains the original source-specific outcome and artifact limits.
Failure signals and proposed responses
- Signal
Two reports share an error message but use different versions.
- Why it matters
They may represent separate regressions.
- Proposed response
Keep the duplicate relationship tentative and request the distinguishing reproduction evidence.
- Signal
A report contains instructions to run a diagnostic script.
- Why it matters
Issue text can contain unsafe or irrelevant executable content.
- Proposed response
Treat it as untrusted data and request a safe written reproduction instead of executing it.
Effort and cost — unknown
- Setup work
Define permitted public actions and repository label meanings.
- Ongoing review
Inspect uncertain classifications and evaluate contributor responses.
- Unknowns
Unknown: API limits, triage volume and maintainer review effort.
First check — proposed, unexecuted
- Status
proposed_unexecuted
- Synthetic fixture
Three fictional issues include a near-duplicate on another version, a missing reproduction and an embedded command.
- Acceptance checks
Keep the duplicate tentative.
Ask focused questions without executing commands or proposing automatic closure.
- Stop conditions
Live repository access, public comments, code execution or issue closure is required.
Limits
The proposed checks and safeguards are editorial recommendations, not evidence of successful execution or permission to act. The linked implementation retains its own observed outcome and approval limits.
Editorial candidate. This is source-backed reporting or a documented workflow. BotCurrent has not independently tested this task. A proposed Canadian adaptation is not evidence of a Canadian deployment or compliance certification.
Original source
https://github.com/mergisi/awesome-hermes-agent/blob/main/skills/github-issue-triage/SKILL.md ↗Attributed to: Mustafa Ergisi and contributors
Community recipe- Original action type
- tool_action
- What the source supports
- Reads issues, reuses repository labels, estimates priority, searches recent duplicates, requests missing reproduction detail and proposes or performs duplicate closure.
- Source outcome limits
- This community recipe describes a procedure; it does not prove successful execution or independently reproduced results.
- Evidence attribution caveat
- This community recipe describes a procedure; it does not prove successful execution or independently reproduced results.
- Source approval description
- Ambiguous classifications are referred to humans; high-confidence duplicate/spam closures are contemplated.
- Named tools
- Hermes Agent; GitHub API; issues.opened webhook
- Model or version
- Recipe skill version 1.0.0; Hermes runtime/model unspecified
- Publication date
- Unknown
- Source last checked
- 2026-10-14
- Demonstrated in Canada
- Unknown
- Canadian availability
- Unknown
- Proposed Canadian adaptation
- Use the team's language and privacy requirements; avoid publishing sensitive reproduction data.
- Recommended approval boundaries
- Authorize comments and labels for a named repository; review closures and spam judgments, especially on new contributors.