[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78VV4PVFJS155P7JJEJF0SA":3,"skill-same:01M78VV4PVFJS155P7JJEJF0SA":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M78VV4PVFJS155P7JJEJF0SA","what-next",null,"Report what to work on next in this repository — an active handoff waiting to be resumed, work already in flight, ready issues ranked the way the board ranks them, what needs the user, what needs shaping first, and blocks that have quietly cleared — and recommend the one command to run. Read-only. Use when the user asks what to work on next, what is ready or what to pick up, or when a phase ends with no next piece of work chosen.","jwh3times\u002Fmagic-agenda","jwh3times","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1965019?v=4","01M720KXPKWJRK0WCC0ZD480M7","Jerry Holland","01M77VPX1A7NMCAXQSW5C0BRFJ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwhat-next\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: what-next\ndescription: Report what to work on next in this repository — an active handoff waiting to be resumed, work already in flight, ready issues ranked the way the board ranks them, what needs the user, what needs shaping first, and blocks that have quietly cleared — and recommend the one command to run. Read-only. Use when the user asks what to work on next, what is ready or what to pick up, or when a phase ends with no next piece of work chosen.\nargument-hint: \"A focus: agent, human, bugs, or a label, area or field value (optional)\"\nmetadata:\n  settings: issue-tracker triage-labels handoffs dev-flow\n---\n\n# What next\n\nScan this repository's trackers and board, rank the open work, and say what to pick up next. The\ndevelopment flow's routing table says which command takes each kind of work; this skill finds the\nwork, ranks it, and names the command. It recommends and stops: the human starts every phase.\n\n**Read-only.** Never change a label, field, assignee, issue or PR, and never claim an issue or a\nhandoff: `\u002Fimplement`, `\u002Flets-go` and the other phase commands do that when the work begins.\nTracker problems the scan finds are reported, for the user or `end-session` to fix. The settings\nfiles step 0 may write are the only files this skill ever changes; reading the handoff map may also\nfetch a copy of the map and its document into the local Handoffs folder.\n\nRun shell snippets in bash (Git Bash on Windows).\n\n## 0. Settings\n\nThis skill reads `docs\u002Fagents\u002Fissue-tracker.md`, `docs\u002Fagents\u002Ftriage-labels.md` and\n`docs\u002Fagents\u002Fhandoffs.md`. Follow `.agents\u002Fskills\u002Fwhat-next\u002Fsettings\u002FREADME.md` to read them and\ncomplete any that are missing; the definitions sit beside it. It never sets up the handoffs machine\nconfig (`.agents\u002Fskills\u002Fhandoff\u002Fmachine-config.md`): that writes a file, so a machine without one\nskips the handoff check (step 1). Then read:\n\n- `.agents\u002Fskills\u002Fwhat-next\u002Fsettings\u002Fdev-flow.md` `## Procedure`: **The gate** (what makes an issue\n  ready), **Routing** (which command takes which work, and what \"nobody has started\" means) and\n  **Private work**. Read `docs\u002Fagents\u002Fdev-flow.md` too, for what this repository adds to the flow.\n- The other sections of `docs\u002Fagents\u002Fissue-tracker.md` (such as **Blocking** or **Wayfinding\n  operations**): they say how this repository records blockers and maps.\n\nFrom the settings, work out before collecting:\n\n- **Trackers:** the `Public repository`, and the `Private issue repository` unless `none`. A\n  `discover:` value is followed now; the private tracker's name stays out of anything public.\n- **Board meanings:** from `Board fields` and `Extra labels`, which values mean in progress, which\n  mean parked or deferred, which mean waiting on something outside the code, which mean waiting on\n  the owner, and which mean a spec or research must come first. A repository's own word for a state\n  counts (`Deferred`, `Deferred trigger`, `P3 - parked`, `deferred`, `blocked-by-human`).\n\n## 1. Collect\n\n```bash\nme=\"$(gh api user --jq .login)\"\nrepository=\"\u003CPublic repository>\"   # owner\u002Fname\n```\n\n`board_owner` and `board_number` below are the two words of the `Board` setting.\n\n**The active handoff**, through the script the `handoff` skill installs, as `lets-go` reads it:\n\n```bash\nnode .agents\u002Fskills\u002Fhandoff\u002Fhandoff-map.mjs get --key \u003CMap key>\n```\n\n- **`file` is null** (or `inMap` is false): no handoff waits for this repository.\n- **`file` is set and `exists` is true**: a handoff waits to be resumed. Read the document's\n  **Where you are** and first **Next step** for the report; do not act on them.\n- **`file` is set and `exists` is false**: the document has not reached this machine yet (the\n  `note` says why). Report it as pending.\n- **`conflicts` not empty**: report that the map has conflicting copies, which `lets-go` resolves\n  with the user.\n- **An error**, a missing script, or no machine config (the error names `config`): the handoff\n  check was not read. Never run `config --write` from here.\n\n**Open issues**, once per tracker, with `owner` and `name` split from its `owner\u002Fname`:\n\n```bash\ngh api graphql --paginate -f owner=\"$owner\" -f name=\"$name\" -f query='\nquery($owner: String!, $name: String!, $endCursor: String) {\n  repository(owner: $owner, name: $name) {\n    issues(states: OPEN, first: 100, after: $endCursor) {\n      pageInfo { hasNextPage endCursor }\n      nodes {\n        number title createdAt updatedAt url\n        labels(first: 20) { nodes { name } }\n        assignees(first: 5) { nodes { login } }\n        issueDependenciesSummary { blockedBy totalBlockedBy blocking }\n        closedByPullRequestsReferences(first: 5, includeClosedPrs: false) { nodes { number isDraft } }\n        parent { number title }\n      }\n    }\n  }\n}' --jq '.data.repository.issues.nodes[]'\n```\n\n`issueDependenciesSummary.blockedBy` counts open blockers only (0 means no native blocker holds it),\n`totalBlockedBy` counts closed ones too, and `blocking` counts the open issues waiting on this one.\n\n**Open PRs** on the `Public repository`:\n\n```bash\ngh pr list -R \"$repository\" --state open --limit 200 \\\n  --json number,title,author,isDraft,reviewDecision,closingIssuesReferences,statusCheckRollup,headRefName,createdAt\n```\n\n**The board**, unless `Board` is `none`:\n\n```bash\ngh project item-list \"$board_number\" --owner \"$board_owner\" --format json --limit 1000\n```\n\nItems come back in the board's manual order, top first, which is what `board order` in\n`Priority order` reads. Each item's field values are keys named by the field in lower case\n(`priority`, `blocked by`); `content.number` and `content.repository` join it to an issue, and an\nitem whose `content.type` is `DraftIssue` is a board draft. Reading a board needs the token's\n`read:project` scope (`gh auth status`). Without it, or on any other failure, rank without the\nboard and say so in the report; never stop over it.\n\n**Security findings**, when the `Security findings` setting is the default (draft advisories):\n\n```bash\ngh api \"repos\u002F$repository\u002Fsecurity-advisories?state=draft\" --jq length\n```\n\nA count only, never a title or summary. An error prints `not readable`, never `0`.\n\n## 2. Classify\n\nPut each open issue in exactly one bucket, taking the first that fits:\n\n1. **Someone else's** — assigned only to people other than `me`. Count it; do not list it.\n2. **Finish first** — named by an open PR (the issue's `closedByPullRequestsReferences`, or a PR's\n   `closingIssuesReferences`); or assigned to `me`, or in an in-progress board state, and not\n   waiting (4). Assigned work that is waiting goes to **Waiting**, and the report's hygiene line\n   names it.\n3. **Parked** — `wontfix`, or a label or board value that means parked or deferred. Count only.\n4. **Waiting** — an open native blocker (`blockedBy` above 0); the `blocked` label or an extra label\n   meaning the same; a board field naming a blocker outside the project (a cleared value such as\n   `Nothing`, `None` or `Ready — …` names none); a gate value that means waiting on something\n   outside the code; or `needs-info`. Count by reason; do not list. A stale block (below) is not\n   waiting.\n5. **Needs you** — `ready-for-human`, `blocked-by-human` or a like extra label, or a gate value\n   that waits on the owner's decision or action.\n6. **Ready for an agent** — ready by **The gate**: route a `bug` to `\u002Fdiagnosing-bugs`, and a\n   `ready-for-agent` issue to `\u002Fimplement`.\n7. **Needs shaping** — everything else, with its route from **Routing**: no triage label or\n   `needs-triage` → `\u002Ftriage`; a gate value calling for a spec or research → `\u002Fgrill-with-docs`, then\n   `\u002Fto-spec`; a `wayfinder:map` → `\u002Fwayfinder` (group its child tickets, found by `parent`, under\n   it rather than listing them). With `New work: draft item`, count the board's drafts here too.\n\n**Stale blocks.** An issue carrying a blocked label or gate value, with no open native blocker\n(`blockedBy` 0, `totalBlockedBy` above 0) and no outside blocker in a board field, was blocked only\nby issues that have since closed. Classify it as though unblocked, mark it `stale block`, and list\nit in the report's hygiene line. It is often the best pick, and only a tracker edit stands between\nit and the queue.\n\n**The gate needs the body.** Labels alone cannot show it: a `ready-for-agent` label on a free-form\nbody is a raw issue, and `\u002Ftriage` posts its brief as a comment. Check only the items the report\nwill list, as ranking reaches them: `gh issue view \u003Cn> -R \u003Ctracker> --json body,comments`. One that\nfails moves to **Needs shaping**, routed to `\u002Ftriage`.\n\n**PRs.** Each of `me`'s open PRs goes in **Finish first**, with its state: checks failing, changes\nrequested, approved and waiting for a merge, a draft, or waiting for review. Another author's\nnon-draft PR, a dependency bot's included, goes there too, as a review or merge to make, with its\nchecks' state.\n\n**Private work** is classified and routed like the rest, and marked `[private]` in the report.\n\n**An active handoff** heads **Finish first**, routed to `\u002Flets-go`: another session parked its work\nfor this one to resume, and its document names the next step. A pending one (its document not here\nyet) is listed there too, with no route. The map does not record which machine wrote a handoff, so\nthe report names the document and its date: a handoff this machine wrote is waiting for the other\none, and is left alone.\n\n## 3. Rank\n\nWithin each bucket, order by:\n\n1. `Priority order`, key by key. An item missing a key's value sorts after every item that has one.\n2. The open issues it unblocks (`blocking`), most first.\n3. Age (`createdAt`), oldest first.\n\nWith `Priority order: none`, or the board unreadable, rank by 2 and 3 alone and say so.\n**Finish first** goes: the active handoff, then PRs with failing checks or changes requested, then\napproved PRs, then PRs waiting for review, then assigned issues with no PR, then drafts.\n\n**The recommendation** is, in order:\n\n1. The top of **Finish first**, unless it holds only drafts or a pending handoff. An active handoff\n   whose document is here is resumed with `\u002Flets-go`, which brings the checkout to its state before\n   anything else starts. A green PR with nothing requested is finished by the user's review and\n   merge, which the recommendation names; it never merges.\n2. Otherwise the higher-ranked of the tops of **Ready for an agent** and **Needs you**, comparing\n   by the same keys. On a tie, the **Needs you** item: no agent can take it, and it may unblock\n   others.\n3. Otherwise the top of **Needs shaping**.\n4. Otherwise nothing: say the queue is empty, with the **Waiting** counts.\n\n## 4. Report\n\nAn argument narrows the report: `agent` keeps **Finish first** and **Ready for an agent**, `human`\nkeeps **Finish first** and **Needs you**, `bugs` keeps `bug` issues, and anything else keeps the\nitems whose labels, board values or titles match it. The recommendation comes from what is kept.\n\nRefer to each item by its title with its number (`Add the lap filter (#212)`), never by number\nalone. List at most ten items per bucket and count the rest. Leave out an empty bucket.\n\n```markdown\n## What next: \u003Crepository>\n\n**Next:** \u003Ctitle> (#\u003Cn>) \u003C[private]> — run `\u003Ccommand> \u003Cn>`. \u003COne line: why this, above the rest.>\n\n### Finish first\n- Active handoff `\u003Cfile>` (\u003Cdate>) — \u003Cits first next step> — `\u002Flets-go`, unless this machine wrote\n  it \u003Cor: pending, not on this machine yet>\n- \u003Ctitle> (#\u003Cn>) — \u003CPR state, or \"assigned, no PR\"> — \u003Cwhat finishing takes>\n\n### Ready for an agent (\u003Ccount>)\n1. \u003Ctitle> (#\u003Cn>) — \u003Crank values>; unblocks \u003Ck> — `\u002Fimplement` or `\u002Fdiagnosing-bugs`\n\n### Needs you (\u003Ccount>)\n1. \u003Ctitle> (#\u003Cn>) — \u003Cthe decision or action owed>\n\n### Needs shaping (\u003Ccount>)\n1. \u003Ctitle> (#\u003Cn>) — \u003Cwhy it is not ready> — `\u003Croute>`\n\n### Waiting\n\u003Cn> blocked by open issues, \u003Cn> on outside parties, \u003Cn> needing info, \u003Cn> parked, \u003Cn> others'\nwork.\u003C, \u003Cn> draft security advisories open.>\n\n**Tracker hygiene:** \u003Cstale blocks, assigned work that is waiting, ready-for-agent labels on raw\nissues, open items with no `Priority order` value, conflicting state labels — or \"none found\">.\n**Not read:** \u003Cthe handoff map, the board, the private tracker or advisories, with why — or leave\nthe line out>.\n```\n\nThen stop. Say which command the recommendation runs, and wait: the user starts the next phase.\nRunning in a subagent or a non-interactive run, return the report to the caller instead.\n","# What next\n\nScan this repository's trackers and board, rank the open work, and say what to pick up next. The\ndevelopment flow's routing table says which command takes each kind of work; this skill finds the\nwork, ranks it, and names the command. It recommends and stops: the human starts every phase.\n\n**Read-only.** Never change a label, field, assignee, issue or PR, and never claim an issue or a\nhandoff: `\u002Fimplement`, `\u002Flets-go` and the other phase commands do that when the work begins.\nTracker problems the scan finds are reported, for the user or `end-session` to fix. The settings\nfiles step 0 may write are the only files this skill ever changes; reading the handoff map may also\nfetch a copy of the map and its document into the local Handoffs folder.\n\nRun shell snippets in bash (Git Bash on Windows).\n\n## 0. Settings\n\nThis skill reads `docs\u002Fagents\u002Fissue-tracker.md`, `docs\u002Fagents\u002Ftriage-labels.md` and\n`docs\u002Fagents\u002Fhandoffs.md`. Follow `.agents\u002Fskills\u002Fwhat-next\u002Fsettings\u002FREADME.md` to read them and\ncomplete any that are missing; the definitions sit beside it. It never sets up the handoffs machine\nconfig (`.agents\u002Fskills\u002Fhandoff\u002Fmachine-config.md`): that writes a file, so a machine without one\nskips the handoff check (step 1). Then read:\n\n- `.agents\u002Fskills\u002Fwhat-next\u002Fsettings\u002Fdev-flow.md` `## Procedure`: **The gate** (what makes an issue\n  ready), **Routing** (which command takes which work, and what \"nobody has started\" means) and\n  **Private work**. Read `docs\u002Fagents\u002Fdev-flow.md` too, for what this repository adds to the flow.\n- The other sections of `docs\u002Fagents\u002Fissue-tracker.md` (such as **Blocking** or **Wayfinding\n  operations**): they say how this repository records blockers and maps.\n\nFrom the settings, work out before collecting:\n\n- **Trackers:** the `Public repository`, and the `Private issue repository` unless `none`. A\n  `discover:` value is followed now; the private tracker's name stays out of anything public.\n- **Board meanings:** from `Board fields` and `Extra labels`, which values mean in progress, which\n  mean parked or deferred, which mean waiting on something outside the code, which mean waiting on\n  the owner, and which mean a spec or research must come first. A repository's own word for a state\n  counts (`Deferred`, `Deferred trigger`, `P3 - parked`, `deferred`, `blocked-by-human`).\n\n## 1. Collect\n\n```bash\nme=\"$(gh api user --jq .login)\"\nrepository=\"\u003CPublic repository>\"   # owner\u002Fname\n```\n\n`board_owner` and `board_number` below are the two words of the `Board` setting.\n\n**The active handoff**, through the script the `handoff` skill installs, as `lets-go` reads it:\n\n```bash\nnode .agents\u002Fskills\u002Fhandoff\u002Fhandoff-map.mjs get --key \u003CMap key>\n```\n\n- **`file` is null** (or `inMap` is false): no handoff waits for this repository.\n- **`file` is set and `exists` is true**: a handoff waits to be resumed. Read the document's\n  **Where you are** and first **Next step** for the report; do not act on them.\n- **`file` is set and `exists` is false**: the document has not reached this machine yet (the\n  `note` says why). Report it as pending.\n- **`conflicts` not empty**: report that the map has conflicting copies, which `lets-go` resolves\n  with the user.\n- **An error**, a missing script, or no machine config (the error names `config`): the handoff\n  check was not read. Never run `config --write` from here.\n\n**Open issues**, once per tracker, with `owner` and `name` split from its `owner\u002Fname`:\n\n```bash\ngh api graphql --paginate -f owner=\"$owner\" -f name=\"$name\" -f query='\nquery($owner: String!, $name: String!, $endCursor: String) {\n  repository(owner: $owner, name: $name) {\n    issues(states: OPEN, first: 100, after: $endCursor) {\n      pageInfo { hasNextPage endCursor }\n      nodes {\n        number title createdAt updatedAt url\n        labels(first: 20) { nodes { name } }\n        assignees(first: 5) { nodes { login } }\n        issueDependenciesSummary { blockedBy totalBlockedBy blocking }\n        closedByPullRequestsReferences(first: 5, includeClosedPrs: false) { nodes { number isDraft } }\n        parent { number title }\n      }\n    }\n  }\n}' --jq '.data.repository.issues.nodes[]'\n```\n\n`issueDependenciesSummary.blockedBy` counts open blockers only (0 means no native blocker holds it),\n`totalBlockedBy` counts closed ones too, and `blocking` counts the open issues waiting on this one.\n\n**Open PRs** on the `Public repository`:\n\n```bash\ngh pr list -R \"$repository\" --state open --limit 200 \\\n  --json number,title,author,isDraft,reviewDecision,closingIssuesReferences,statusCheckRollup,headRefName,createdAt\n```\n\n**The board**, unless `Board` is `none`:\n\n```bash\ngh project item-list \"$board_number\" --owner \"$board_owner\" --format json --limit 1000\n```\n\nItems come back in the board's manual order, top first, which is what `board order` in\n`Priority order` reads. Each item's field values are keys named by the field in lower case\n(`priority`, `blocked by`); `content.number` and `content.repository` join it to an issue, and an\nitem whose `content.type` is `DraftIssue` is a board draft. Reading a board needs the token's\n`read:project` scope (`gh auth status`). Without it, or on any other failure, rank without the\nboard and say so in the report; never stop over it.\n\n**Security findings**, when the `Security findings` setting is the default (draft advisories):\n\n```bash\ngh api \"repos\u002F$repository\u002Fsecurity-advisories?state=draft\" --jq length\n```\n\nA count only, never a title or summary. An error prints `not readable`, never `0`.\n\n## 2. Classify\n\nPut each open issue in exactly one bucket, taking the first that fits:\n\n1. **Someone else's** — assigned only to people other than `me`. Count it; do not list it.\n2. **Finish first** — named by an open PR (the issue's `closedByPullRequestsReferences`, or a PR's\n   `closingIssuesReferences`); or assigned to `me`, or in an in-progress board state, and not\n   waiting (4). Assigned work that is waiting goes to **Waiting**, and the report's hygiene line\n   names it.\n3. **Parked** — `wontfix`, or a label or board value that means parked or deferred. Count only.\n4. **Waiting** — an open native blocker (`blockedBy` above 0); the `blocked` label or an extra label\n   meaning the same; a board field naming a blocker outside the project (a cleared value such as\n   `Nothing`, `None` or `Ready — …` names none); a gate value that means waiting on something\n   outside the code; or `needs-info`. Count by reason; do not list. A stale block (below) is not\n   waiting.\n5. **Needs you** — `ready-for-human`, `blocked-by-human` or a like extra label, or a gate value\n   that waits on the owner's decision or action.\n6. **Ready for an agent** — ready by **The gate**: route a `bug` to `\u002Fdiagnosing-bugs`, and a\n   `ready-for-agent` issue to `\u002Fimplement`.\n7. **Needs shaping** — everything else, with its route from **Routing**: no triage label or\n   `needs-triage` → `\u002Ftriage`; a gate value calling for a spec or research → `\u002Fgrill-with-docs`, then\n   `\u002Fto-spec`; a `wayfinder:map` → `\u002Fwayfinder` (group its child tickets, found by `parent`, under\n   it rather than listing them). With `New work: draft item`, count the board's drafts here too.\n\n**Stale blocks.** An issue carrying a blocked label or gate value, with no open native blocker\n(`blockedBy` 0, `totalBlockedBy` above 0) and no outside blocker in a board field, was blocked only\nby issues that have since closed. Classify it as though unblocked, mark it `stale block`, and list\nit in the report's hygiene line. It is often the best pick, and only a tracker edit stands between\nit and the queue.\n\n**The gate needs the body.** Labels alone cannot show it: a `ready-for-agent` label on a free-form\nbody is a raw issue, and `\u002Ftriage` posts its brief as a comment. Check only the items the report\nwill list, as ranking reaches them: `gh issue view \u003Cn> -R \u003Ctracker> --json body,comments`. One that\nfails moves to **Needs shaping**, routed to `\u002Ftriage`.\n\n**PRs.** Each of `me`'s open PRs goes in **Finish first**, with its state: checks failing, changes\nrequested, approved and waiting for a merge, a draft, or waiting for review. Another author's\nnon-draft PR, a dependency bot's included, goes there too, as a review or merge to make, with its\nchecks' state.\n\n**Private work** is classified and routed like the rest, and marked `[private]` in the report.\n\n**An active handoff** heads **Finish first**, routed to `\u002Flets-go`: another session parked its work\nfor this one to resume, and its document names the next step. A pending one (its document not here\nyet) is listed there too, with no route. The map does not record which machine wrote a handoff, so\nthe report names the document and its date: a handoff this machine wrote is waiting for the other\none, and is left alone.\n\n## 3. Rank\n\nWithin each bucket, order by:\n\n1. `Priority order`, key by key. An item missing a key's value sorts after every item that has one.\n2. The open issues it unblocks (`blocking`), most first.\n3. Age (`createdAt`), oldest first.\n\nWith `Priority order: none`, or the board unreadable, rank by 2 and 3 alone and say so.\n**Finish first** goes: the active handoff, then PRs with failing checks or changes requested, then\napproved PRs, then PRs waiting for review, then assigned issues with no PR, then drafts.\n\n**The recommendation** is, in order:\n\n1. The top of **Finish first**, unless it holds only drafts or a pending handoff. An active handoff\n   whose document is here is resumed with `\u002Flets-go`, which brings the checkout to its state before\n   anything else starts. A green PR with nothing requested is finished by the user's review and\n   merge, which the recommendation names; it never merges.\n2. Otherwise the higher-ranked of the tops of **Ready for an agent** and **Needs you**, comparing\n   by the same keys. On a tie, the **Needs you** item: no agent can take it, and it may unblock\n   others.\n3. Otherwise the top of **Needs shaping**.\n4. Otherwise nothing: say the queue is empty, with the **Waiting** counts.\n\n## 4. Report\n\nAn argument narrows the report: `agent` keeps **Finish first** and **Ready for an agent**, `human`\nkeeps **Finish first** and **Needs you**, `bugs` keeps `bug` issues, and anything else keeps the\nitems whose labels, board values or titles match it. The recommendation comes from what is kept.\n\nRefer to each item by its title with its number (`Add the lap filter (#212)`), never by number\nalone. List at most ten items per bucket and count the rest. Leave out an empty bucket.\n\n```markdown\n## What next: \u003Crepository>\n\n**Next:** \u003Ctitle> (#\u003Cn>) \u003C[private]> — run `\u003Ccommand> \u003Cn>`. \u003COne line: why this, above the rest.>\n\n### Finish first\n- Active handoff `\u003Cfile>` (\u003Cdate>) — \u003Cits first next step> — `\u002Flets-go`, unless this machine wrote\n  it \u003Cor: pending, not on this machine yet>\n- \u003Ctitle> (#\u003Cn>) — \u003CPR state, or \"assigned, no PR\"> — \u003Cwhat finishing takes>\n\n### Ready for an agent (\u003Ccount>)\n1. \u003Ctitle> (#\u003Cn>) — \u003Crank values>; unblocks \u003Ck> — `\u002Fimplement` or `\u002Fdiagnosing-bugs`\n\n### Needs you (\u003Ccount>)\n1. \u003Ctitle> (#\u003Cn>) — \u003Cthe decision or action owed>\n\n### Needs shaping (\u003Ccount>)\n1. \u003Ctitle> (#\u003Cn>) — \u003Cwhy it is not ready> — `\u003Croute>`\n\n### Waiting\n\u003Cn> blocked by open issues, \u003Cn> on outside parties, \u003Cn> needing info, \u003Cn> parked, \u003Cn> others'\nwork.\u003C, \u003Cn> draft security advisories open.>\n\n**Tracker hygiene:** \u003Cstale blocks, assigned work that is waiting, ready-for-agent labels on raw\nissues, open items with no `Priority order` value, conflicting state labels — or \"none found\">.\n**Not read:** \u003Cthe handoff map, the board, the private tracker or advisories, with why — or leave\nthe line out>.\n```\n\nThen stop. Say which command the recommendation runs, and wait: the user starts the next phase.\nRunning in a subagent or a non-interactive run, return the report to the caller instead.\n",{"name":5,"metadata":24,"description":7,"argument-hint":26},{"settings":25},"issue-tracker triage-labels handoffs dev-flow","A focus: agent, human, bugs, or a label, area or field value (optional)","main","4bef9674c378b0ab2b7a40deb99bbb5f8a3b546a",".agents\u002Fskills\u002Fwhat-next","https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda","https:\u002F\u002Fgithub.com\u002Fjwh3times","2026-11-15 02:06:57",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add jwh3times\u002Fmagic-agenda --skill what-next",{"tool":39,"command":40},"bunx","bunx skills add jwh3times\u002Fmagic-agenda --skill what-next",{"tool":42,"command":43},"pnpm","pnpm dlx skills add jwh3times\u002Fmagic-agenda --skill what-next","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwhat-next\u002FSKILL.md",true,[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"settings\u002Fdev-flow.md","REFERENCE","参考文档",5438,"https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwhat-next\u002Fsettings\u002Fdev-flow.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"settings\u002Fhandoffs.md",1585,"https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwhat-next\u002Fsettings\u002Fhandoffs.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"settings\u002Fissue-tracker.md",4028,"https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwhat-next\u002Fsettings\u002Fissue-tracker.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"settings\u002FREADME.md",3227,"https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwhat-next\u002Fsettings\u002FREADME.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"settings\u002Ftriage-labels.md",1236,"https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwhat-next\u002Fsettings\u002Ftriage-labels.md",[70,75,82,89,96,103],{"skillNo":71,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M78VV9DEMRWSM8X974XSEJ0F","https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwhat-next\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M77VVTQ3D1E750MPQKJB7GAJ","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M77VVQEWF676Q4AX7A3GPKYW","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M77VVMVZQ519TXXY5PADDJXY","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M77VVJXHVJ8GF7RKMD5H32QY","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M77VVGGQNPR0TTRAZT8JT087","triage","Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.","https:\u002F\u002Fgithub.com\u002Fjwh3times\u002Fmagic-agenda\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftriage\u002FSKILL.md",[],[]]