Run the eval suites deferred by the upstream-pointer sweep PRs
Maintainer antworten meist innerhalb von 1 Tag
Dieses Issue hat noch niemand übernommen.
Bewertung
- Schwierigkeit
- 4/5
- Geschätzter Aufwand
- 3-5 Tage
- Anfängerfreundlichkeit
- 35/100
- Issue-Typ
- Bug
- Klarheit
- Klar beschrieben
- Aktivitätsstatus
- Aktiv
- Tech-Stack
- shell
- Bereich
- ai-infra-agents, testing-qa
Rechercherichtung
Start with the listed PRs and their eval lists, then run /evals:plugin-eval against merged main for each skill. The issue groups runs for behavior or output changes first, followed by pointer-only changes. Done when all listed eval runs are complete; file any regression as a separate bug issue linking this one.
Vom Indexierungsmodell aus dem Issue-Text verfasst.
Beschreibung
Description
The upstream-pointer sweep PRs (#7061-#7274) merged with their eval runs deferred: they mostly replace restated upstream Claude Code docs text with pointer records. Each PR body lists the skills whose eval run was owed. This issue collects those lists so the runs are not lost once the PRs close.
Run first: PRs that also changed behavior or output
- #7241 source-control:
babysit_gh.pyrecognizes the cloud proxy's GraphQL refusal wording, which changes how the unattended babysit loop falls back to REST. Evals:check, plus a babysit-prs run against a PR in a cloud session. - #7239 work-items:
work/scripts/preflight.shprints corrected warning text (one test assertion updated). Evals:attend-queue,setup,ship,work. - #7245 harness-ops: the install-state audit table has new swept rows (uploads, dev-mods, usage-data), a jobs kept row, and a reworded backups note. Evals:
audit-install-state,audit-native-overlap,audit-performance,audit-skill-visibility,check,machine-profile,prerequisites. - #7254 instruction-placement: the migrate shim check reads the AGENTS.md plugin option under both its old and new ID. Evals:
migrate,audit,delta, plus architecturemap-containers,map-context,map-flow,map-landscape,record-decision. - #7253 context-budget: the audit's emitted known-uncovered note text changed. Evals:
audit,check.
Pointer-only PRs
- #7061 discipline:
use-your-skills,sweep-all(sweep-all eval case 8 was updated with the worktree-containment wording) - #7133 autonomy:
setup(evals 6, 7, 31),check - #7136 harness-config:
audit-instructions,audit-pass,draft-auto-mode-rules,unhobble,audit - #7250 code-tidying:
audit-dead-code,batch-simplify,audit,check - #7251 discovery:
check,research,trace-intent - #7252 disk-hygiene:
audit,check,clean,setup - #7255 formatters:
checkin actionlint, bash-format, biome-format, eol-normalizer, go-format, markdown-format, powershell-format, ruff-format, typos-format - #7258 context-guard:
check - #7259 docs-hygiene:
audit-encapsulation,audit-progressive-disclosure,rename-references - #7260 planning:
interview,plan,design,prd,draft-goal-condition,improve, multi-agentcheckandsetup - #7261 guardrails: desktop-notification
check, machine-healthauditandsetup, repo-fleet-hygieneapplyandaudit, repo-hygieneclean - #7262 harness-memory:
audit,stateless - #7263 misc:
clarify, context7checkandlookup,audit-tools,build-cli, developer-experiencesetup,generate-file-name-gate, dometrainsetup, event-stormingmethodology,simulation, firecrawlupdate,reach,advise,manage,object-writing - #7264 skill-quality:
check,setup - #7265 review:
scan, bugssetup,write,explain-change,security-review - #7266 testing: code-metrics
principles, mutation-testingaudit,check,plan,write - #7267 plugin-quality: evals
methodology,audit-posture, plugin-qualityaudit - #7268 performance:
teach,book-distill,docpage-digest,map-corpus, knowledgesetup,go-faster - #7270 session-flow:
audit-friction,check,clean-stop,continue-in-background,handoff,reanchor,reconcile,running-retro,show-options - #7271 visual:
learn-style,diagnose, computer-usesetup, mirosetup,use, playwrightcheck,demo-video,present,visualize - #7274 playbooks:
boris,repo-sweep,update - #7242 lib and #7272 repo-docs: no skill evals owed.
Run each with /evals:plugin-eval against the merged main. A regression goes in its own bug issue that links this one.
Affected area
Plugin skills across the marketplace (see the list).
Found during the upstream-pointer sweep (PRs #7061-#7274).
- Vorherrschende Sprache
- Shell
- Sterne
- 22
- Forks
- 2
- Ø Merge
- 8 Std. 24 Min.
- Gemergte PRs (30 T.)
- 947
Entwicklungsumgebung
- Kein Dockerfile und keine Docker-Compose-Datei
- Keine Pull-Request-Vorlage
- Beitragsleitfaden lesen
Erste Schritte
- Lesen Sie das ganze Issue und danach den Beitragsleitfaden des Projekts.
- Schreiben Sie ins Issue, dass Sie es übernehmen — das erspart doppelte Arbeit.
- Forken Sie das Repository und arbeiten Sie in einem Branch.
- Öffnen Sie einen Pull Request, der die Issue-Nummer nennt.
Mehr aus melodic-software/claude-code-plugins
-
needs-human needs-triage priority: medium
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 65/100
melodic-software/claude-code-plugins#7455 · 1 Kommentar ·
Maintainer antworten meist innerhalb von 1 Tag
-
priority: medium
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 68/100
melodic-software/claude-code-plugins#7351 · 2 Kommentare ·
Maintainer antworten meist innerhalb von 1 Tag
-
agent-ready priority: high work-class: scoped
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 74/100
melodic-software/claude-code-plugins#7312 · 3 Kommentare ·
Maintainer antworten meist innerhalb von 1 Tag
-
priority: medium
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 76/100
melodic-software/claude-code-plugins#7288 · 2 Kommentare ·
Maintainer antworten meist innerhalb von 1 Tag
-
knowledge: docpage-digest dual verification defines no verdict vocabulary or pass/fail thresholdOffenneeds-human
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 78/100
melodic-software/claude-code-plugins#7286 · 2 Kommentare ·
Maintainer antworten meist innerhalb von 1 Tag
Alle Issues in melodic-software/claude-code-plugins
Ähnliche Issues
-
Standalone Unix updater reports success when curl fails (`curl | sh` masks the exit status); Windows path is unaffectedEvtl. vergeben @akhil9tiet hat das heute übernommen. Offenbug CLI windows-os
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 72/100
openai/codex#54465 · 1 Kommentar ·
Maintainer antworten meist innerhalb von 1 Tag
-
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 72/100
interledger/rhyza#352 ·
Maintainer antworten meist innerhalb von 1 Tag
-
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 74/100
non7top/dotfiles-personal#41 ·
Maintainer antworten meist innerhalb von 1 Tag
-
Build: the CUDA backend fails without cuDNN instead of skipping the cuDNN shim (as the cuDF shim does)Evtl. vergeben Ein verknüpfter Pull Request ist offen oder bereits gemergt. Offen
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 68/100
beehive-lab/TornadoVM#1248 ·
Maintainer antworten meist innerhalb von 1 Tag
-
Dev
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 62/100
ankidroid/Anki-Android#22555 ·
Maintainer antworten meist innerhalb von 1 Tag