「only」の検索結果

Compile a PAM control's iOS Obj-C/Swift module into the FLAT device-slice `.framework` for a `.ppmplugin` bundle (never an `.xcframework` — the wrap CI won't descend into one). Mac-only (Xcode). Builds from a throwaway staged copy so canonical `ios/` and the podspec stay untouched, references React-Core headers only (React is weak-linked and provided by the wrap host at runtime, no CocoaPods), generates the required umbrella header, module map and Info.plist, sets the critical build settings, asserts manifest conformance, then runs a device-only `xcodebuild archive` and copies out the flat framework to `ppmplugin/staging/ios/`. Known limitation — the React weak-link flags aren't yet validated against a live wrap host and the RN pin must match the host's. Run after /generate-ppmplugin-manifest for an iOS or Both target, before /assemble-ppmplugin.

日本語の概要は準備中です。原文の説明を表示しています。

Report-only QA — same browser-based testing as qa but documents bugs with screenshots and repro steps only, no code changes. Health score formula weighted across 8 categories. Outputs to .gstack/qa-reports/.

日本語の概要は準備中です。原文の説明を表示しています。

Weekly, on a Friday, read only everywhere. Scores the week from the kit's own ledgers with a source path beside every number, cuts it by platform, framework, pillar, slot time, and post length, rewrites the drafting standards from that evidence and from nothing else, replays the browser flows the other routines depend on, and files exactly one thing to stop and one to do more of. It publishes only where you released the channel, never replies, spends only where you released it, never touches a credential, and never writes a number it did not measure.

日本語の概要は準備中です。原文の説明を表示しています。

Weekdays, file work only, no browser at all. Reads every ledger, queue file, and run record, turns yesterday's ticks into facts a machine can count, folds the slot inbox, rewrites the content calendar, and writes the one short brief the member opens first. Its most important line names which slots publish today and how to stop them. It publishes only where you released the channel, never replies, spends only where you released it, and never touches a credential.

日本語の概要は準備中です。原文の説明を表示しています。

Weekly, on a Friday, read only everywhere. Scores the week from the ledgers with a source path beside every number, replays the browser flows the other routines depend on, names one thing to kill and one thing to scale, and files both as cards. It sends only where you released the channel, spends only where you released it, never touches a credential, and never writes a number it did not count out of a named file this run.

日本語の概要は準備中です。原文の説明を表示しています。

Monthly, on the last weekday, file work only, no browser at all. Folds the decision ledger, scores this Employee's own judgement against the metric files that measured it rather than against its own predictions, appends one outcome line per closed decision, retires a move proposed three times and never accepted, and rewrites the priorities where the evidence disagrees with them. It refuses to publish a calibration figure on too few closed decisions, changes nothing outside its own folder, proposes nothing to anybody, sends only where you released the channel, spends only where you released it, and never touches a credential.

日本語の概要は準備中です。原文の説明を表示しています。

Weekly, file work only, no browser at all. Reads everything the week produced, picks exactly three moves, and argues both sides of each one before the member reads a word of it, with every clause carrying a number or an observation from a file it names. It argues against its own top recommendation last, records a predicted effect and the metric that would show it so the monthly review can score it, and files each move onto the register. It sends only where you released the channel, spends only where you released it, never deploys, and never touches a credential.

日本語の概要は準備中です。原文の説明を表示しています。

Runs once by hand on the first day and once a month after that. On the first run it researches the business from its own public surfaces, reads the member's own already published posts, and builds the voice file from real samples rather than from an idea of a voice, then writes the plan, creates the proof inventory, seeds the opening slots, and registers the recurring jobs. On every monthly run it re reads the evidence the kit produced and rebuilds only what the evidence contradicts. It publishes only where you released the channel, never replies, spends only where you released it, and it never enters a credential.

日本語の概要は準備中です。原文の説明を表示しています。

Weekly, heavy browser lane, read only toward the world with no exception. Works the surfaces on its own watchlist through one contiguous browser phase, captures one dated observation per real change with a verbatim quote and the exact URL, refuses to report any change against a surface it has no baseline for, and writes one capped weekly page. It types nothing that changes anything, takes no action on LinkedIn ever, sends only where you released the channel, spends only where you released it, and never touches a credential.

日本語の概要は準備中です。原文の説明を表示しています。

Weekdays, browser only where a link genuinely needs verifying. Writes tomorrow's slots, one draft per due slot per destination, from the voice file, the drafting standards, and the dated material captured this morning. It rotates the post framework so no skeleton repeats, enforces the plain text and character budget rules the platforms actually impose, and judges every candidate before it lands. It publishes only where you released the channel, never schedules, never replies, spends only where you released it, and never touches a credential.

日本語の概要は準備中です。原文の説明を表示しています。

Weekly, on a Friday, read only everywhere. Scores the week from the ledgers with a source beside every number, replays the browser flows the other routines depend on, names one thing to kill and one thing to scale, and files both as cards. It sends only where you released the channel, spends only where you released it, never touches a credential, and never writes a number it did not measure.

日本語の概要は準備中です。原文の説明を表示しています。

Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.

日本語の概要は準備中です。原文の説明を表示しています。

Use only when the user explicitly invokes obra test-driven-development for iron-law examples. Core TDD is docs/ai/skills/tdd/SKILL.md. Do not use this for docs-only, formatting-only, or generated-mirror changes.

日本語の概要は準備中です。原文の説明を表示しています。

Test-driven development for substantive feature, bug-fix, and behavior-changing work. Use automatically when implementing features, fixing bugs, or changing behavior (red → green → refactor). Also use when the user mentions TDD, /tdd, /TDD, or red-green-refactor. Do not use for documentation-only, formatting-only, exact generated-mirror, or provenance-only changes.

日本語の概要は準備中です。原文の説明を表示しています。

Routes substantive ML, AI, data, scientific-computing, and software-engineering requests to the smallest useful set of managed repository skills. Invoke proactively when a request names or implies a package, framework, model family, dataset, modality, workflow, backend, deployment target, evaluation method, or implementation approach that may benefit from repository guidance, even if no repository is named. Narrow progressively from area to family to repository root: inspect only the one or two most likely area pages; compare candidates by capability, task surface, model/data format, training versus inference versus evaluation intent, runtime constraints, and root-skill description; then open only the selected root and relevant sub-skills, references, or scripts. Select multiple repositories only when each adds a distinct capability. Do not load the whole collection, treat dependencies or incidental integrations as capabilities, choose by name alone, or force a match when no exact taxonomy family applies.

日本語の概要は準備中です。原文の説明を表示しています。

Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".

日本語の概要は準備中です。原文の説明を表示しています。

Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (claims.json) + the other auditors' confirmed findings — never free-floating LLM critique. Two fresh cross-model codex threads: an attack writes the ~200-word rejection paragraph (every accusation tagged to an existing claim_id/finding_id), a defense decomposes it and rules each point against the anchored evidence. MEMO-ONLY: emits adversarial-case-builder.memo.md (fed to the adjudicator via --memo) and carries NO verdict weight — tools/adjudicate_findings.py lists it in ZERO_WEIGHT_SKILLS and caps it at info. Honest-null allowed (the paper may survive). Run LAST. Detect-only. Adapted from ARIS kill-argument. Triggers: "adversarial case", "strongest objection", "rejection memo", "kill argument", "最强拒稿点".

日本語の概要は準備中です。原文の説明を表示しています。

MEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide from the paper alone — ADV-TRIVIAL-COMBINATION (standard A+B+C / 缝合 stapling) and ADV-DUPLICATE-PUBLICATION (repackaged / duplicate submission). The executor RETRIEVES candidate prior work (DBLP fuzzy-title + boolean · WebSearch · WebFetch) from the paper's own title + contribution spans in the evidence ledger; TWO fresh cross-model codex reviewers (one per axis) LAY OUT the overlap side-by-side against each anchored contribution claim. It NEVER rules 'trivial' or 'duplicate' (that is a human judgment) and absence of a match is NOT evidence of originality. Emits novelty-duplication-advisory.memo.md + an info-only findings mirror; carries NO verdict weight — tools/adjudicate_findings.py lists it in ZERO_WEIGHT_SKILLS and caps it at info. Detect-only. Adapted from ARIS novelty-check, reframed from 'is MY idea novel' to 'here is the overlap a reviewer should weigh'. Triggers: "novelty advisory", "duplication check", "prior-work overlap", "is this stapling", "缝合", "查重", "重复发表", "duplicate submission".

日本語の概要は準備中です。原文の説明を表示しています。

Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/check_presentation.py — dup-table + pipeline-artifact) plus a fresh cross-model GROSS-cases-only semantic pass (thin-float, LLM-figure, page-padding), every above-info finding span-anchored to the evidence ledger (claims.json). The adjudicator CAPS everything at minor (SURFACE_ONLY_SKILLS + SURFACE_PATTERNS) — these contribute at most SOFT_FLAGS, never a HARD verdict — default false_positive_risk:high. NOTE: the pure AI writing-STYLE impressions (AI-flavor prose, defensive 'not-X-but-Y' hedging, narrative-arc, jargon-stuffing, invented codenames) MOVED to the zero-verdict-weight AIS track — for those use skills/ai-style-impressions, NOT this. Emits presentation-signals.findings.json; NEVER computes the verdict. Triggers: "presentation signals", "surface check", "duplicate tables", "排版信号".

日本語の概要は準備中です。原文の説明を表示しています。

Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no variance/seeds (HP-SIG-OVERLAP); and a cross-row 'improves over baseline by X%' is arithmetically wrong (HP-DELTA-ERROR, cross-row form only). A versioned per-domain baseline profile + a live leaderboard/recency search are assembled by the EXECUTOR as structured facts; a fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per dimension) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Works at L0 (stated comparisons) and deepens at L2 (configs/result files). A completeness question it cannot settle internally becomes needs_external_check, never a guessed missing baseline. Emits baseline-comparison-audit.findings.json; computes NO verdict. Detect-only. Triggers: "baseline audit", "missing baselines", "is the comparison fair", "weak baseline", "baseline 误报", "SOTA earned?".

日本語の概要は準備中です。原文の説明を表示しています。

Turns implementation work into working code, reviewed and verified. Use when the user delegates a feature, story, bug fix, or meaningful change; a bare story or issue link counts. Skip obvious, low-risk mechanical maintenance such as small ignore-file, typo-only, formatting-only, or configuration-hygiene edits. Explicit BMAD requests always qualify. Do not volunteer for user-directed interactive edits or version-control operations that only record existing work.

日本語の概要は準備中です。原文の説明を表示しています。

Use test-driven development for behavior-changing feature or fix work, and whenever the user mentions TDD, test-first, red-green-refactor, tracer bullets, integration tests, or public-interface behavior tests. Skip for docs-only, path-only rename, formatting-only, or purely mechanical chores unless explicitly requested.

日本語の概要は準備中です。原文の説明を表示しています。

Conventions and APIs for the offload-project/laravel-invite-only package — polymorphic invitations, token acceptance, bulk invites, scheduled reminders, and event-driven hooks.

日本語の概要は準備中です。原文の説明を表示しています。

Use when building dependency-free Python 3.11+ scripts for airgapped, stdlib-only, or restricted environments where third-party package installation is prohibited — triggers on "stdlib-only", "airgapped", "no dependencies", "no internet", "restricted environment", or confirmed environments where external packages cannot be installed.

日本語の概要は準備中です。原文の説明を表示しています。