[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74WV41AF8SHRBH5528M96SE":3,"skill-same:01M74WV41AF8SHRBH5528M96SE":63},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M74WV41AF8SHRBH5528M96SE","dev-sprint",null,"phaedrus1992\u002Fllmenv","phaedrus1992","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F22475972?v=4","01M74WTJB2Y3041TQR80DYKMAR","Phaedrus","01M74WTJBSJTG3HBYX6WSS3E0M",4,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fbase\u002Fskills\u002Fdev-sprint\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"\u003C!-- markdownlint-disable MD003 MD013 MD022 MD041 -->\n---\nname: dev-sprint\ndescription: Use when user asks \"start sprint\", \"pick up work\", \"what should I work on\". Selects 1-5 related issues from active milestone, synthesizes into composite work item (or picks single issue), hands off to ship-issue.\nmodel: haiku\nresources:\n\n- scripts\u002Flist-issues.sh\n- scripts\u002Fcreate-composite.sh\n- scripts\u002Fresolve-base-branch.sh\n- references\u002Fplugin-augmentation.md\n\n---\n\n# Dev Sprint\n\nPick 1-5 related issues, prioritizing lowest active milestone. Run a single issue by choice, or group related issues: same subsystem, shared code paths, blocking order.\nPrioritize bug fixes over new features.\nPick one issue deliberately, or as many as five. Either way, skip composite creation only if it's a single issue (Phase 3) — but **still run the full Phase 4 handoff**, not a stripped-down one. \"Directly\" means \"no composite,\" NOT \"skip the augmentation.\"\nSynthesize into composite.\nHand off to `ship-issue`. `ship-issue` owns branching, TDD, CI, pre-pr-review, merging. `dev-sprint` owns selection + synthesis.\n\n**Single-issue runs are not a fast path.** Whether the sprint is one issue or five, Phase 4's handoff augmentation is mandatory: the required `pre-pr-review` scans (slop-scan, etc.), the `ponytail:ponytail-review` pass after `pre-pr-review`, the propagated directives (subagent\u002Fexecuting-plans, review autonomy), and Phases 5–8 (docs, semver, changelog, deferred-work filing, verification). The only thing a single issue skips is building a composite issue (Phase 3) and the multi-issue closing refs. Everything else runs exactly as it does for a multi-issue sprint.\n\n**Hard rule — no orphan sprints:** Once a sprint composite is created (Phase 3), it owns the run. If scope must shrink, update the composite or close it with justification (see Phase 3.5). Never create a second composite while the first is open.\n\n## Setup\n\n**Create `.tmp\u002F` at project root before starting:**\n\n```bash\nmkdir -p .tmp\n```\n\nAll temp files in dev-sprint + sub-skills (`ship-issue`, `pre-pr-review`, etc.) use `.tmp\u002F` at project root, not `\u002Ftmp`. Keeps artifacts local, no system temp interference.\n\n## Phase 1: Triage Unmilestoned Issues\n\n**Before selecting work, every open issue must have a milestone.** List the orphans directly:\n\n```bash\n\"${CLAUDE_CONFIG_DIR}\u002Fskills\u002Fdev-sprint\u002Fscripts\u002Flist-issues.sh\" --no-milestone\n```\n\n(Add `--json` for machine-readable output to pipe through `jq`\u002F`python` — full bodies included, so no follow-up `gh issue view` needed.)\n\nAssign each unmilestoned issue to the right milestone:\n\n1. **Survey existing milestones first.** List with due dates + themes to place each orphan accurately:\n\n   ```bash\n   gh api repos\u002F:owner\u002F:repo\u002Fmilestones --jq '.[] | \"\\(.title) — \\(.description \u002F\u002F \"no description\") (due \\(.due_on \u002F\u002F \"none\"))\"'\n   ```\n\n2. **Match each orphan to best-fitting milestone** by topic\u002Fsubsystem + ordering (which release it belongs to). Bugs in shipped behavior → earliest open milestone; new features → milestone owning that area.\n\n   ```bash\n   gh issue edit \u003Cissue> --milestone \"\u003Cmilestone-title>\"\n   ```\n\n3. **No existing milestone fits? OK to create one** — or rename existing milestones for better ordering or topic coverage. Prefer reuse\u002Frename over proliferating near-duplicate milestones.\n\n   ```bash\n   # create\n   gh api repos\u002F:owner\u002F:repo\u002Fmilestones -f title=\"vX.Y\" -f description=\"\u003Ctheme>\" -f due_on=\"\u003CISO8601 or omit>\"\n   # rename \u002F re-describe (milestones are addressed by number, not title)\n   gh api -X PATCH repos\u002F:owner\u002F:repo\u002Fmilestones\u002F\u003Cnumber> -f title=\"\u003Cnew title>\" -f description=\"\u003Cnew theme>\"\n   ```\n\n**Goal:** after this phase, `No Milestone` is empty (or holds only issues you've deliberately, with justification, decided are out of scope for any milestone). Re-run `list-issues.sh` to confirm before selection.\n\n## Phase 2: Select Related Issues\n\n```bash\n\"${CLAUDE_CONFIG_DIR}\u002Fskills\u002Fdev-sprint\u002Fscripts\u002Flist-issues.sh\"\n```\n\nPick lowest milestone with open issues. Choose 1-5 related issues from that milestone: one issue alone (deliberately), or multiple related issues (same subsystem, shared code paths, blocking order).\n\nPrefer: shared files, unblock each other. Avoid: mixed domains.\n\n## Phase 3: Create Composite Issue\n\nComposite body structure:\n\n```markdown\n## Issues\n- #N — \u003Ctitle>\n- #N — \u003Ctitle>\n\n## Scope\n\u003CShared subsystem\u002Fdata flow\u002Fbehavior. Why together.>\n\n## Acceptance Criteria\n\u003CMerged & deduplicated criteria from all issues>\n\n## Implementation Notes\n\u003COrdering constraints. Known shared files.>\n```\n\n**CRITICAL:** List all sub-issues in composite body. Source of truth for what PR must close.\n\n```bash\n\"${CLAUDE_CONFIG_DIR}\u002Fskills\u002Fdev-sprint\u002Fscripts\u002Fcreate-composite.sh\" \"Sprint: \u003Ctheme>\" \"\u003Cbody>\" \"\u003Cmilestone>\" \"\u003Clabels>\"\n```\n\nMilestone required; **labels optional** (upstream `ship-issue`\u002F`pr-review` no longer enforce labels, label sets vary per repo). Labels = 4th arg, **comma-separated** for multiple — e.g. `\"bug,area-core\"`. Use labels that exist in repo (`gh label list`); script validates each, attaches the existing ones, skips missing ones with a warning rather than failing. Script prints new issue number on its final line—capture it, pass to `ship-issue`.\n\n### Phase 3.5: Composite is Immutable (READ BEFORE PROCEEDING)\n\n**Once the composite issue is created, it IS the sprint. You may not silently abandon it and create a new one.**\n\nThis is the orphan-sprint failure mode: composite #A is created with sub-issues #X, #Y, #Z; mid-run you decide #Y and #Z are too much; you create composite #B covering only #X and ship that; #A is left OPEN with #Y and #Z dangling, milestone view corrupted, planned work silently dropped.\n\n**Forbidden:** creating a second composite during the same dev-sprint run while the first is still OPEN. Tempted to? Stop, apply one resolution below instead.\n\n**If scope must shrink after Phase 3 (e.g. one bug harder than expected, another turns out blocked):**\n\n1. **Preferred — keep the composite, shrink the PR:** Pick the subset you'll actually ship. Update composite body to mark deferred sub-issues:\n\n```markdown\n   ## Issues\n   - #X — \u003Ctitle>  ✅ (this PR)\n   - #Y — \u003Ctitle>  ⏸ deferred → #\u003Cfollowup>\n   - #Z — \u003Ctitle>  ⏸ deferred → #\u003Cfollowup>\n   ```\n\n   For each deferred sub-issue, post a comment explaining the defer + linking the follow-up plan (or leave it open with no comment if follow-up is just \"next sprint\"). Composite stays open until its PR merges; on merge, `Closes #\u003Ccomposite>` + `Closes #X` only. #Y and #Z stay open for a future sprint.\n\n   ```bash\n   gh issue edit \u003Ccomposite> --body \"$(updated body)\"\n   gh issue comment \u003CY> --body \"Deferred from sprint #\u003Ccomposite>. Will be picked up in a follow-up sprint.\"\n   ```\n\n1. **Alternative — abandon the composite cleanly:** Original framing wrong and you want a fresh composite? You must close the old one first with a justification comment:\n\n   ```bash\n   gh issue comment \u003Ccomposite> --body \"Closing as superseded. Original scope (#X #Y #Z) was too broad for one sprint. Replacing with #\u003Cnew-composite> covering #X only. #Y and #Z return to milestone backlog.\"\n   gh issue close \u003Ccomposite>\n   ```\n\n   Only after the old composite is CLOSED may you create a new one.\n\n**Self-check before running `create-composite.sh` a second time in one run:** Has a composite already been created in this run? If yes, you are in the orphan path. STOP and apply resolution 1 or 2 above. Never create a second composite without closing or updating the first.\n\n## Phase 4: Hand Off to ship-issue\n\n**Applies to single-issue runs too.** Where this phase says \"composite-id,\" use the single issue's number instead. The base-branch resolution, scans, ponytail pass, propagated directives, and PR verification all run regardless of issue count.\n\n### Phase 4a: Select the base branch (milestone → release branch)\n\n**The composite's milestone decides the base branch — not `main` by default.** A milestone titled `X.Y — \u003Ctheme>` (or `vX.Y`) is a patch line: if a `release\u002FX.Y.x` branch exists on the remote, branch from it so the work doesn't drag in unreleased feature work that lives only on `main` (and doesn't duplicate commits already on the release branch). Only fall back to the default branch when **no** matching `release\u002FX.Y.x` exists.\n\n**Use the script — don't eyeball it.** `resolve-base-branch.sh` performs this evaluation deterministically (same result every run) and prints the base branch on stdout:\n\n```bash\n# By composite issue number (looks up its milestone via gh):\nBASE_BRANCH=\"$(\"${CLAUDE_CONFIG_DIR}\u002Fskills\u002Fdev-sprint\u002Fscripts\u002Fresolve-base-branch.sh\" --issue \u003Ccomposite-id>)\"\n# …or by milestone title directly:\nBASE_BRANCH=\"$(\"${CLAUDE_CONFIG_DIR}\u002Fskills\u002Fdev-sprint\u002Fscripts\u002Fresolve-base-branch.sh\" --milestone \"\u003Cmilestone>\")\"\necho \"Base branch for this sprint: $BASE_BRANCH\"\n```\n\nThe script falls back to the repo default branch when the milestone has no matching `release\u002FX.Y.x` (a milestone with no release line is not an error). Diagnostics go to stderr; only the branch name is on stdout, safe for `$(...)` capture.\n\nPull latest of `$BASE_BRANCH` before invoking. **Pass `$BASE_BRANCH` into the `ship-issue` handoff** (see example below) so it branches from the right place instead of assuming `main`. Check `references\u002Fplugin-augmentation.md` for plugin, include in message.\n\n**IMPORTANT: All temp files in dev-sprint + sub-skills use `.tmp\u002F` at project root. Ensure `.tmp\u002F` exists before invoking sub-skills. Sub-skills must not use `\u002Ftmp`.**\n\n**CRITICAL: Include sub-issue list in `ship-issue` invocation.** Propagates to `pre-pr-review` so PR has all closing refs.\n\nExample message:\n\n```text\nSprint: Validation & Error Handling\n\nBase branch: release\u002F1.0.x   ← branch from this, NOT main (from Phase 4a)\n\nSub-issues to close on PR merge:\n- #315 — Code quality: socket validation\n- #325 — P0: Add error handling and validation\n- #330 — Sprint composite issue\n\n[Continue with ship-issue instructions...]\n```\n\n**For agentic workers:** REQUIRED: Use superpowers:subagent-driven-development (if subagents available) or superpowers:executing-plans to implement this plan. Steps use checkbox (`- [ ]`) syntax for tracking.\n\nApplies to any sub-skill that launches agents to do the work (`ship-issue`, `pre-pr-review`). Include this directive in the handoff message so it propagates.\n\n**Review phase autonomy:** `ship-issue` → `pre-pr-review` fixes apply automatically, no user prompts. Fix or defer, then create PR.\n\n**Required scans during `pre-pr-review`:** Include in `ship-issue` handoff so it propagates to `pre-pr-review`:\n\n- `\u002FUsers\u002Fphaedrus\u002Fgit\u002Fmy-llmenv\u002Fbundles\u002Fbase\u002Fscripts\u002Fslop-scan.sh scan . --lint`\n\n  Always invoke slop-scan through this pinned wrapper (it runs `slop-scan@0.3.0`\n  and is on the permission allowlist). Do **not** call `npx slop-scan` directly —\n  the unpinned, agent-chosen form is blocked by the supply-chain auto-policy.\n\n**After `pre-pr-review` completes:** Run `ponytail:ponytail-review` and apply all suggestions automatically before creating the PR. No user prompts — apply and commit.\n\n**PR closing references (MANDATORY):**\n\n```text\nCloses #\u003Ccomposite-id>\nCloses #\u003Cissue-1>\nCloses #\u003Cissue-2>\nCloses #\u003Cissue-3>\n```\n\nComposite first, then sub-issues. GitHub auto-closes on merge. Every sprint PR closes all sub-issues, not just composite.\n\n**Sprint meta-issue:** Sprint tracked via issue? Add closing ref:\n\n```text\nCloses #\u003Ccomposite-id>\nCloses #\u003Cissue-1>\n...\nCloses #\u003Csprint-tracking-issue>\n```\n\nBranch (created by `ship-issue` from `$BASE_BRANCH` selected in Phase 4a):\n\n```text\nfeat\u002F\u003Ccomposite-id>-\u003Ctheme-slug>   # forked from $BASE_BRANCH (release\u002FX.Y.x or default)\n```\n\nFollow `ship-issue` exactly—no skips.\n\n## Phase 5: Documentation & Semver\n\nAfter `ship-issue`, update docs + version.\n\n**Docs:** Update README.md, docs\u002F for:\n\n- Features\u002FAPIs → examples + usage\n- Behavior changes → update sections\n- Types\u002Ffunctions → API docs\n- Config changes → options\u002Fenv vars\n\n**Semver:**\n\n- **MAJOR**: Breaking API\u002Fbehavior\u002Fconfig\n- **MINOR**: New features, APIs, config options (backward-compatible)\n- **PATCH**: Bug fixes, internal improvements\n\nUpdate `package.json` \u002F `Cargo.toml` \u002F `pyproject.toml` + any version refs. Commit with code.\n\n**CHANGELOG (always run the `keepachangelog` skill at the end of the sprint):** Invoke the `keepachangelog` skill to update `CHANGELOG.md` if the sprint introduced any user-visible changes (features, behavior changes, config changes, bug fixes). If `keepachangelog` modifies `CHANGELOG.md`, commit it. If nothing warrants a changelog entry, leave it unchanged. This runs on every sprint — never skip it.\n\n## Phase 6: Deferred Work & Pre-Existing Issues\n\n**Defer only if:**\n\n- Pre-existing bugs outside sprint scope\n- Features needing brainstorm\u002Fdesign\n- Work needing `feature-dev` or architecture review\n- External dependency blocks\n\n**Do NOT defer:** Fix non-complex issues immediately, mid-sprint OK.\n\n```bash\ngh issue create \\\n  --title \"Title\" \\\n  --body \"Found during sprint X, [details]\" \\\n  --milestone \"vX.X\" \\\n  --label \"bug\"   # optional; use a label that exists in this repo (gh label list)\n```\n\n**REQUIRED:** All issues from any skill need:\n\n- `--milestone` (no exceptions)\n- `--label` is **optional** — if used, must be a label that exists in repo (`gh label list`). Don't invent labels.\n\n## Phase 6a: Issue Creation Standards (All Skills)\n\n**MANDATORY for all issues:**\n\n1. **Milestone**: Active milestone or current sprint (required)\n2. **Body**: Where found, why deferred, repro steps (if bug), blockers\n3. **Label**: optional — if used, must already exist in the repo (`gh label list`)\n\n**Enforce in skill scripts:** require the milestone, but treat the label as optional and validate it against the repo (warn, don't reject) rather than against a fixed allowlist:\n\n```bash\nif [[ -z \"$MILESTONE\" ]]; then\n  echo \"Error: Milestone is required for all issues\" >&2\n  exit 1\nfi\n\ndeclare -a GH_ARGS=(issue create --title \"$TITLE\" --body \"$BODY\" --milestone \"$MILESTONE\")\nif [[ -n \"${LABEL:-}\" ]]; then\n  if gh label list --limit 200 --json name --jq '.[].name' | grep -Fxq \"$LABEL\"; then\n    GH_ARGS+=(--label \"$LABEL\")\n  else\n    echo \"Warning: label '$LABEL' not found in repo; creating without it.\" >&2\n  fi\nfi\ngh \"${GH_ARGS[@]}\"\n```\n\n## Phase 7: Verify PR (base branch + closing references)\n\nAfter the PR is created, verify two invariants **before** allowing the merge.\n\n### 7a: Base branch matches the milestone\n\nThe PR must target the branch `resolve-base-branch.sh` selected in Phase 4a — not whatever the agent defaulted to. Recompute the expected base and compare it to the PR's actual base:\n\n```bash\nEXPECTED_BASE=\"$(\"{${CLAUDE_CONFIG_DIR}\u002Fskills\u002Fdev-sprint\u002Fscripts\u002Fresolve-base-branch.sh\" --issue \u003Ccomposite-id>)\"\nACTUAL_BASE=\"$(gh pr view \u003Cpr-number> --json baseRefName --jq .baseRefName)\"\nif [[ \"$EXPECTED_BASE\" != \"$ACTUAL_BASE\" ]]; then\n  echo \"BASE MISMATCH: PR targets '$ACTUAL_BASE' but milestone wants '$EXPECTED_BASE'\" >&2\n  # Fix in place — retarget the PR (no reopen needed):\n  gh pr edit \u003Cpr-number> --base \"$EXPECTED_BASE\"\n  # Re-verify, and confirm the diff still makes sense against the new base\n  # (a wrong base can hide or invent changes). If the branch was forked from\n  # the wrong base, rebase onto $EXPECTED_BASE before retargeting.\nfi\n```\n\n**Failure condition:** PR merges into the wrong base (e.g. `main` for a `1.0` milestone). This is the exact misfire Phase 4a exists to prevent — 7a is the catch-net if the branch was still created from the wrong place.\n\n### 7b: Closing references\n\nVerify a closing ref for every sub-issue:\n\n```bash\ngh pr view \u003Cpr-number> --json body --jq .body | grep -c \"^Closes #\"\n```\n\nCount must equal sub-issue count. If not, fix immediately:\n\n```bash\ngh pr edit \u003Cpr-number> --body \"$(gh pr view \u003Cpr-number> --json body --jq .body)\nCloses #\u003Cmissing-issue-id>\"\n```\n\n**Failure condition:** PR merges without closing all sub-issues. Sprint not complete until all closed.\n\n## Phase 8: Task Cleanup\n\n`TaskList`. Mark stale tasks `deleted` via `TaskUpdate`. Keep composite task if planning new sprint.\n\n## References\n\nPlugin\u002Fagent guidance: `references\u002Fplugin-augmentation.md`\n",{},"main","2ccf515b8e8251dfd0392546073a1baaf42e79cf","examples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fbase\u002Fskills\u002Fdev-sprint",1,"https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv","https:\u002F\u002Fgithub.com\u002Fphaedrus1992","2026-11-15 01:43:22",{"source":7,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add phaedrus1992\u002Fllmenv --skill dev-sprint",{"tool":35,"command":36},"bunx","bunx skills add phaedrus1992\u002Fllmenv --skill dev-sprint",{"tool":38,"command":39},"pnpm","pnpm dlx skills add phaedrus1992\u002Fllmenv --skill dev-sprint","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fbase\u002Fskills\u002Fdev-sprint\u002FSKILL.md",true,[43,49,55,59],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"references\u002Fplugin-augmentation.md","REFERENCE","参考文档",1323,"https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fbase\u002Fskills\u002Fdev-sprint\u002Freferences\u002Fplugin-augmentation.md",{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"scripts\u002Fcreate-composite.sh","SCRIPT","脚本",3266,"https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fbase\u002Fskills\u002Fdev-sprint\u002Fscripts\u002Fcreate-composite.sh",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"scripts\u002Flist-issues.sh",4714,"https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fbase\u002Fskills\u002Fdev-sprint\u002Fscripts\u002Flist-issues.sh",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fresolve-base-branch.sh",4148,"https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fbase\u002Fskills\u002Fdev-sprint\u002Fscripts\u002Fresolve-base-branch.sh",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M74WW2BKBJSM8QS9BAEYMC24","clippy","Rust clippy linter skill","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbundles\u002Frust-defaults\u002Fskills\u002Fclippy\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M74WW0P1A8YWDVYM864T6J5X","hello","Hello world skill","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbundles\u002Fbase\u002Fskills\u002Fhello\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M74WVXR7Y3XMRDXXVGTZD9HT","setup-llmenv","Interactive setup wizard for new llmenv users. Evaluates existing Claude Code configuration, helps sort into bundles, and writes llmenv-native equivalents.","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-llmenv\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M74WVVKQPW6TKJHCTB5WHQKG","llmenv","How to use llmenv's built-in features (task tracker, memory, context-mode, codebase-memory) effectively. Load this first; it points to a reference file per enabled feature rather than dumping all of them into context.","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fskills\u002Fllmenv\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M74WVQEJ1S6T2M3DEF3JJF66","fyi","Use when the user asks for an \"fyi\", \"morning todo\", \"morning briefing\", \"what's on my plate\", \"what do I have open\", \"what's in flight\", \"where did I leave off\", \"what needs my attention today\", or \"my open work across projects\". Surveys the user's currently-open, in-flight, and pending work across GitHub, Linear, Slack, Pylon, and Notion, then produces a ranked, GitHub-markdown briefing for the day. Forward-looking sibling of daily-update (which reports what already happened).","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fwork\u002Fskills\u002Ffyi\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M74WVMF20C830E3NT7GSJH2P","daily-update","Use when the user asks for a \"standup\", \"scrum update\", \"daily update\", \"status update\", \"what did I work on\", or \"what did I do yesterday\". Scans llmenv session logs, Linear, Slack, and GitHub for the user's own activity on a given day and produces a short scrum-style update, copied to the clipboard as Slack markdown.","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fwork\u002Fskills\u002Fdaily-update\u002FSKILL.md",[],[]]