triaging-issues
Skill5.9k starsChanged 2 days agoApache-2.0View on GitHub
Grounding a GitHub work item before running the factory pipeline: checking for duplicates, working with the repo's existing labels, deciding whether to ask for clarification or proceed, and asking for reproduction details well. Load whenever a work item arrives from a GitHub issue or mention, and whenever asked to triage, label, dedupe, or close issues. Not needed for work items that arrive as plain requests with no GitHub issue behind them.
6 other projects use a version of this, 3 of them edited.
Trending
More talk lately.about the whole repository
Most recently taken up by
- getsentry/software-factoryedited, first seen Oct 25, 2026
- vercel-labs/kody-eve-templateedited, first seen Oct 13, 2026
- vercel-labs/eve-software-factory-templateedited, first seen Oct 13, 2026
- medusajs/medusatheir own version, first seen Oct 8, 2026
- pytorch/pytorchtheir own version, first seen Oct 8, 2026
- microsoft-foundry/foundry-agent-webapptheir own version, first seen Apr 21, 2026
Who's talking about vercel/eve
- @qdrddr.bsky.social“@vercel.com Eve #Agentic #framework uses #filesystem as interface for tools, just drop a #TypeScript code …”Bluesky · Oct 16, 2026 · 8 likes
- @projectnothing.bsky.social“When frameworks like eve break out, it’s a sign: AI agents are no longer side projects—they’re becoming a …”Bluesky · Jun 17, 2026 · 3 likes
- @github-trending-js.bsky.social“📦 vercel / eve ⭐ 5,184 (+40) 🗒 TypeScript The Open Framework for Building Agents”Bluesky · Sep 17, 2026 · 2 likes
- DataDog/dd-trace-js“feat(llmobs): add external experiment recorder”GitHub · Jul 31, 2026 · 2 reactions
- ComposioHQ/composio“chore(deps-dev): bump the npm-development group across 1 directory with 9 updates”GitHub · Nov 6, 2026 · 1 reactions
The biggest 5 of 56 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 56
Talked about on GitHub and Bluesky (56 times).
On GitHub · 49
- Jul 31, 2026feat(llmobs): add external experiment recorder — DataDog/dd-trace-js2 reactions · 5 comments
- Nov 6, 2026chore(deps-dev): bump the npm-development group across 1 directory with 9 updates — ComposioHQ/composio1 reaction · 5 comments
- Nov 3, 2026chore(deps-dev): bump the npm-development group across 1 directory with 8 updates — ComposioHQ/composio1 reaction · 6 comments
- Oct 30, 2026Bump the production-dependencies group across 1 directory with 11 updates — byronwade/rebuzzle.byronwade.com1 reaction · 6 comments
- Oct 30, 2026chore(deps-dev): bump the npm-development group with 7 updates — ComposioHQ/composio1 reaction · 6 comments
44 more on GitHub
- Oct 16, 2026chore(deps-dev): bump the npm-development group across 1 directory with 8 updates — ComposioHQ/composio1 reaction · 6 comments
- Oct 16, 2026chore(deps-dev): bump the npm-development group with 4 updates — ComposioHQ/composio1 reaction · 6 comments
- Oct 13, 2026chore(deps-dev): bump the npm-development group with 3 updates — ComposioHQ/composio1 reaction · 5 comments
- Oct 9, 2026chore(deps-dev): bump the npm-development group across 1 directory with 7 updates — ComposioHQ/composio1 reaction · 6 comments
- Sep 25, 2026chore(deps-dev): bump the npm-development group with 8 updates — ComposioHQ/composio1 reaction · 4 comments
- Sep 14, 2026chore(deps): bump the production-dependencies group across 1 directory with 13 updates — byronwade/rebuzzle.byronwade.com1 reaction · 5 comments
- Sep 11, 2026chore(deps-dev): bump the npm-development group with 5 updates — ComposioHQ/composio1 reaction · 4 comments
- Sep 7, 2026chore(deps): bump the production-dependencies group across 1 directory with 12 updates — byronwade/rebuzzle.byronwade.com1 reaction · 4 comments
- Sep 1, 2026@nuxt/kit missing @nuxt/schema dependency breaks TypeScript with pnpm 12 GVS — nuxt/nuxt1 reaction
- Aug 31, 2026chore(deps): bump the production-dependencies group with 11 updates — byronwade/rebuzzle.byronwade.com1 reaction · 4 comments
- Aug 13, 2026基于 vercel/eve 实现 agents demo 切片 — SawanaLabs/agent-demos1 reaction · 3 comments
- Jul 28, 2026fix(nitro): vercel function rules - preserve relative symlinks — nitrojs/nitro1 reaction · 4 comments
- Jul 3, 2026Add Eve adapter (eve_gateway + eve_local) — paperclipai/paperclip1 reaction · 6 comments
- Jun 30, 2026Install eve skill from vercel/eve — TommyBez/evex1 reaction · 2 comments
- Jun 19, 2026[codex] Read downloads from the sandbox stream — remiconnesson/eve-single-user-agent-starter1 reaction · 1 comment
- Nov 3, 2026[ARCHITECTURE ASSESSMENT] Eve.dev adoption — no control-plane replacement; bounded comparative pilot — mastermindx-market-intelligence/Mastermind0 reactions
- Nov 2, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 27, 2026Telegram HITL: при нажатии кнопки подтверждения теряется нажавший (auth: null) — в вендоренном eve 0.51.1 нет фикса vercel/eve#4241 — smixs/iva-agent0 reactions · 1 comment
- Oct 26, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 19, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 18, 2026T2: Preserve authenticated attachments when continuing copied history — FranciscoMoretti/chat-js0 reactions
- Oct 18, 2026T1/T2: Adopt upstream structured history imports with completed tools and attachments — FranciscoMoretti/chat-js0 reactions
- Oct 17, 2026Research: Eve project primer — setup, models via AI Gateway, approvals, subagents, Next.js mount, deploy — rymanacevedo/business-wiki-agent0 reactions · 2 comments
- Oct 12, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 11, 2026`vercel dev` stalls silently (no port, no error) when the Next.js dev-manifest config loader exits non-zero — vercel/vercel0 reactions
- Oct 6, 2026Research: custom SPARQL-generation model + separate review layer (prior art: eve + Qwen + Jev data analyst) — wazootech/wazoo-memorybench0 reactions
- Oct 3, 2026[Add] eve (vercel/eve) — PyTorchKR/landscape0 reactions
- Sep 30, 2026Research report - numbered build order, hackathon checklist, runtime pick — VasuBansal7576/return-intelligence-voice0 reactions
- Sep 19, 2026未対応のカードの効果の翻訳を、会話の中で Pull Request として足せるようにする — mokosystem/pokemon-tcg-buddy0 reactions
- Sep 1, 2026sep 2026 — kimtth/azure-openai-llm-notes0 reactions
- Aug 12, 2026Ship an eve and AI SDK memory integration guide — Studio-Moser/Advisaur-MCP0 reactions
- Aug 12, 2026Evaluate eve as a seventh distribution channel — tartinerlabs/skills0 reactions · 2 comments
- Aug 10, 2026epic(ai): the agent harness -- vision, prior art, and the plan to stand behind "or the agent harness itself" — routecraftjs/routecraft0 reactions · 4 comments
- Jul 14, 2026Epic: publish TypeScript SDK and durable Eve approval channel — asiraky/mayi0 reactions · 2 comments
- Jul 13, 2026@ai-sdk/openai: support ordered additional_tools after a normal tool result — vercel/ai0 reactions · 4 comments
- Jul 4, 2026feat(eve): import Agent Runs and OpenTelemetry evidence into fak session ledgers — anthony-chaudhary/fak0 reactions
- Jul 4, 2026test(eve): run eve evals as fak parity and regression witnesses — anthony-chaudhary/fak0 reactions · 7 comments
- Jul 4, 2026feat(eve): lease-gate shared-sandbox subagent fan-out from child session streams — anthony-chaudhary/fak0 reactions · 1 comment
- Jul 4, 2026feat(eve): preflight MCP/OpenAPI connections for scoped auth, allowlists, and approval gates — anthony-chaudhary/fak0 reactions · 1 comment
- Jul 4, 2026feat(eve): compile agent/ directories into fak policy and mount manifests — anthony-chaudhary/fak0 reactions · 1 comment
- Jul 4, 2026epic(eve): Vercel eve integration bridge - filesystem agents, policy lint, evals, and observability — anthony-chaudhary/fak0 reactions
- Jun 23, 2026@vercel/connect/eve: support context-aware Slack installation selection — vercel/vercel0 reactions
- Jun 19, 2026Remove sandbox stream compatibility fix after Eve #117 is released — remiconnesson/eve-single-user-agent-starter0 reactions
- Jun 19, 2026Add Vercel Eve sandbox backend adapter support — sandbox0-ai/sandbox00 reactions
On Bluesky · 7
- Oct 16, 2026@vercel.com Eve #Agentic #framework uses #filesystem as interface for tools, just drop a #TypeScript code into a folder, the filename… — @qdrddr.bsky.social8 likes and reposts · 1 reply
- Jun 17, 2026When frameworks like eve break out, it’s a sign: AI agents are no longer side projects—they’re becoming a new pillar of mainstream software… — @projectnothing.bsky.social3 likes and reposts
- Sep 17, 2026📦 vercel / eve ⭐ 5,184 (+40) 🗒 TypeScript The Open Framework for Building Agents — @github-trending-js.bsky.social2 likes and reposts
- Sep 20, 2026github.com/vercel/eve GitHub - vercel/eve: The Open Framework for Building Agents — @technews4869.bsky.social1 likes and repost
- Aug 11, 2026Cloudflare OS blog: blog.cloudflare.com/cloudflare-os/, github.com/cloudflare/cloudflare-os Vercel eve: vercel.com/blog/introducing-eve ·… — @akash-bhatia.bsky.social1 likes and repost
2 more on Bluesky
- Jul 2, 2026Vercel's eve is a filesystem-first framework for durable AI agents: an agent is a directory of instructions, tools, skills, channels, and… — @agentpalisade.bsky.social1 likes and repost
- Jun 17, 2026The Framework for Building Agents https://github.com/vercel/eve — @laxima-tech.bsky.social1 likes and repost
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 3
- vercel-labs/eve-software-factory-template★ 1.2k100% same
- vercel-labs/kody-eve-template★ 1362% same
- getsentry/software-factory★ 0100% same
Wrote their own version · 3
- pytorch/pytorch★ 106ksame name
- medusajs/medusa★ 37ksame name
- microsoft-foundry/foundry-agent-webapp★ 124same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository115 other files it gives its agents.
- AGENTS.mdAGENTS.md
- apps/docs/AGENTS.mdAGENTS.md
- apps/templates/eve-agent-python-template/AGENTS.mdAGENTS.md
- apps/templates/eve-agent-python-template/apps/web/AGENTS.mdAGENTS.md
- apps/templates/eve-chat-template/AGENTS.mdAGENTS.md
- apps/templates/eve-coding-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-content-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-contentful-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-data-analyst-template/AGENTS.mdAGENTS.md
- apps/templates/eve-discord-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-llm-council-template/AGENTS.mdAGENTS.md
- apps/templates/eve-mem0-template/AGENTS.mdAGENTS.md
- apps/templates/eve-memory-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-slack-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-software-factory-template/AGENTS.mdAGENTS.md
- apps/templates/eve-sre-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-tanstack-start-template/AGENTS.mdAGENTS.md
- apps/templates/eve-vercel-drives-starter/AGENTS.mdAGENTS.md
- apps/templates/eve-voice-template/AGENTS.mdAGENTS.md
- apps/templates/kody-eve-template/AGENTS.mdAGENTS.md
- apps/templates/marketing-team-eve-template/AGENTS.mdAGENTS.md
- apps/templates/openinstinct/AGENTS.mdAGENTS.md
- apps/templates/personal-agent-template/AGENTS.mdAGENTS.md
- apps/templates/sanity-copilot-eve-template/AGENTS.mdAGENTS.md
- apps/templates/slack-company-brain-template/AGENTS.mdAGENTS.md
- packages/eve-agent-desktop/AGENTS.mdAGENTS.md
- packages/eve-code/AGENTS.mdAGENTS.md
- packages/eve-computer-use/AGENTS.mdAGENTS.md
- packages/eve-custom-skills/AGENTS.mdAGENTS.md
- packages/eve-git/AGENTS.mdAGENTS.md
- packages/eve/src/internal/nitro/AGENTS.mdAGENTS.md
- apps/templates/eve-agent-python-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-chat-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-coding-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-content-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-contentful-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-data-analyst-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-discord-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-llm-council-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-mem0-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-memory-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-slack-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-software-factory-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-sre-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-tanstack-start-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-vercel-drives-starter/CLAUDE.mdCLAUDE.md
- apps/templates/eve-voice-template/CLAUDE.mdCLAUDE.md
- apps/templates/kody-eve-template/CLAUDE.mdCLAUDE.md
- apps/templates/marketing-team-eve-template/CLAUDE.mdCLAUDE.md
- apps/templates/openinstinct/CLAUDE.mdCLAUDE.md
- apps/templates/personal-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/sanity-copilot-eve-template/CLAUDE.mdCLAUDE.md
- apps/templates/slack-company-brain-template/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- gh-pr-descriptionSkill
- pr-shepherdSkill
- technical-writingSkill
- test-auditSkill
- create-payment-credentialSkill
- dashboard-chat-best-practicesSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 15 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
15
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Search the repo's existing issues for the same symptom before doing anything.
- Distinctive: line 14
Search by the error message, the API or feature name, and a plain description of the symptom.
- Distinctive: line 15
Treat it as a duplicate only when the underlying cause matches, not just the surface symptom.
- Distinctive: line 17
When it duplicates a closed issue that was fixed: point to the fix and the release that carries it, and ask the reporter to confirm on that …
- Distinctive: line 18
When you are not sure, say so in your comment ("this looks related to #42") and leave both open rather than closing on a guess.
- Distinctive: line 22
Every repo has its own label taxonomy, and an invented label is worse than none.
- Distinctive: line 25
Read the label descriptions when they exist.
- Distinctive: line 27
Remove a label only when it is clearly wrong for the issue, and say why in a comment when the removal isn't obvious.
- Distinctive: line 28
If the repo has almost no labels, don't compensate by inventing structure.
- Distinctive: line 35
Ask when the report is plausible but not actionable: no steps, no expected-versus-actual behavior, contradictory details, or several …
- Distinctive: line 43
Ask for the smallest set of things that would make the issue actionable, as a short list: exact version, steps or a minimal repro, expected …
- Distinctive: line 44
Ask specific questions over generic ones.
- Distinctive: line 50
When someone explicitly asked for a triage pass, do the reversible parts directly: comment, apply and correct labels, link duplicates.
- Distinctive: line 51
When the requester is on a surface that can't see repo activity as it happens (a Linear session), your reply must carry the full outcome: …
- Distinctive: line 52
Never take a triage action on an issue nobody asked you about, even if you notice it needs one while working.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Triaging Issues
How to ground a GitHub issue before the factory pipeline runs on it, or when someone asks for a triage pass outright. The order matters: read, dedupe, label, then decide what the issue needs. Never comment on or change an issue you haven't read in full, including its existing comments and labels.
1. Check for duplicates before anything else
Running the pipeline on a duplicate wastes a full implementation cycle, and a duplicate comment on a fresh report saves everyone the most time, but only if you are right.
- Search the repo's existing issues for the same symptom before doing anything. Search closed issues as well as open ones: many "new" bugs were already fixed or already rejected.
- Search by the error message, the API or feature name, and a plain description of the symptom. One search is not enough; reporters describe the same bug in different words.
- Treat it as a duplicate only when the underlying cause matches, not just the surface symptom. Two crashes with the same error text can have different roots.
- When it is a duplicate of an open issue: comment linking the original by number, apply the repo's duplicate label if one exists, and note anything the new report adds (a new environment, a cleaner reproduction) on the original. Don't run the pipeline twice for one problem.
- When it duplicates a closed issue that was fixed: point to the fix and the release that carries it, and ask the reporter to confirm on that version before closing.
- When you are not sure, say so in your comment ("this looks related to #42") and leave both open rather than closing on a guess.
2. Label with the repo's vocabulary, never your own
Every repo has its own label taxonomy, and an invented label is worse than none.
- List the repo's existing labels first and work only from that set. Never create a label or apply a name you assume exists.
- Read the label descriptions when they exist; "bug" versus "regression" versus "confirmed" often carry specific local meaning.
- Apply the fewest labels that place the issue: usually one for type (bug, feature, question) and one for area or status when the repo has them.
- Remove a label only when it is clearly wrong for the issue, and say why in a comment when the removal isn't obvious.
- If the repo has almost no labels, don't compensate by inventing structure. Note the gap when you report back instead.
3. Ask or proceed?
This decision feeds the classifier's needs_clarification judgment, and yours before it. Default to proceeding when the intent is clear; ask when building the wrong thing is a real risk.
- Proceed with stated assumptions when the report is plausible and the gap is small: a missing version when the bug reproduces on the current one, a vague title over a clear body.
- Ask when the report is plausible but not actionable: no steps, no expected-versus-actual behavior, contradictory details, or several incompatible readings of what's wanted. Apply the repo's needs-repro or needs-more-info style label if it has one.
- Close directly only when the issue is a confirmed duplicate, already fixed in a release the reporter can upgrade to, plainly off topic for the repo, or spam. Always leave a comment saying why, with links. Never close someone's issue because you personally judge it low value; flag it instead.
4. Asking for reproduction details
The comment asking for more info decides whether the reporter comes back. Keep it short, specific, and warm.
- Open by engaging with what they reported, not with a form letter. One sentence showing you read the issue.
- Ask for the smallest set of things that would make the issue actionable, as a short list: exact version, steps or a minimal repro, expected versus actual behavior, and environment only if it plausibly matters.
- Ask specific questions over generic ones. "Does this happen with X disabled?" gets an answer; "please provide more details" gets silence.
- Close with what happens next: that the factory will pick the issue up once the details land.
- See
references/repro-request-structure.mdfor the comment shape and worked examples.
5. Report what you did
- When someone explicitly asked for a triage pass, do the reversible parts directly: comment, apply and correct labels, link duplicates. Then report what you did, issue by issue, with numbers and links.
- When the requester is on a surface that can't see repo activity as it happens (a Linear session), your reply must carry the full outcome: what you changed, what you asked, what you recommend, each with its issue number and link.
- Never take a triage action on an issue nobody asked you about, even if you notice it needs one while working. Mention it instead.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

