「read-only」の検索結果

Verifies workspace state and staged changes as a read-only preflight. Use before commits or PRs to confirm staged set is clean and correct.

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。

Deep-scan any tools you connect (CRM, email, support, reviews, analytics, billing, database) to produce a data-grounded Ideal Customer Profile and a reusable persona library. Read-only by default. Use when you need to define or refresh your ICP, build buyer personas from real data instead of guesses, or generate the persona inputs that the customer-panel-of-experts and prospect-panel-simulator skills consume.

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 a skill fails for a missing tool or the environment needs checking. Diagnoses Python, R, Node, Claude Code, Git, Zotero and configured MCP servers and prints a pass/fail table with links to the setup docs. Read-only; installs nothing.

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 references must be written, rendered or converted. Checks [@key] citation keys, renders the reference list with a journal CSL via pandoc, converts [N] markers, injects Zotero Word field codes and runs manuscript-DOCX cross-reference QC. Read-only auditing is /verify-refs.

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。

Read huge, dense, read-only text as rendered PNG pages instead of raw text — image tokens scale with pixels, not characters, so token-dense bulk (big files, vendored code, diffs, logs) costs ~60–75% less as an image. Use when you must skim or reason over thousands of lines you will NOT edit or byte-copy. Lossy on exact strings: never for files you'll Edit, secrets, hashes, or byte-exact values. Fable-class readers only.

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。

Delegate search- and review-heavy work to Honey's read-only subagents so large reads return compressed instead of bloating context.

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。

Read huge dense read-only text as PNG pages via pxpipe export: ~60-75% fewer input tokens. Lossy on exact strings; never for files you will edit.

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。

Read huge read-only text as PNG pages; big input cut.

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。

Decide when to delegate to Honey's read-only subagents (hive-scout, hive-reviewer) instead of working inline, so the expensive tokens — large file reads and review passes injected back into the orchestrator's context — come back compressed (Honey Lever 3). Use when a task is search-heavy or review-heavy, spans many files, or you want to keep the orchestrator's context small. Not for trivial one-file 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。

只读检索小红书公开内容，并把账号数据、标题、封面、互动量、作者近期内容和低粉爆款整理成可追溯证据。用户要求查公开账号或笔记数据时使用；不得点赞、收藏、评论、发布、删除或导出登录凭证。 English: Read-only research for public Xiaohongshu content, collecting traceable evidence such as account data, titles, covers, engagement, recent posts, and low-follower breakout examples. Use for public account or post research; never like, save, comment, publish, delete, or export credentials.

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。

Route substantial coding or repository-review work through a two-stage Sol commander/verifier and separate Luna Max CLI worker. Use when the user explicitly asks Sol to direct or supervise Luna, explicitly requests this router, needs an isolated auditable Luna-owned implementation with a Sol review loop, or asks to diagnose or measure the router itself. Do not use merely because a task involves coding, verification, progress reporting, or token saving. For small or straightforward tasks, keep work in Sol unless the user explicitly requests Luna; router configuration, usage, and efficiency questions should use read-only inspection without launching a worker.

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。

Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default. Use when a user mentions logs_2.sqlite, logs_2.sqlite-wal, block_log_inserts, SSD/TBW wear, or explicitly asks to protect, clean up, verify, or restore Codex diagnostic logging.

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 and organize AI coding-agent instructions, including AGENTS.md, CLAUDE.md, skills, and agent definitions. Use when the user asks to diagnose conflicting instructions, excessive approval pauses, broad skill triggers, duplicate guidance, or broken instruction references, or to clean up that instruction set. Ordinary code review, Markdown editing, or application debugging alone does not trigger this workflow. Inspection stays read-only; apply changes when authorized.

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。

Investigate or fix a GitHub issue by number or URL. Keep investigation-only requests read-only.

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。

Execute read-only SQL queries against multiple PostgreSQL databases. Use when: (1) querying PostgreSQL databases, (2) exploring database schemas/tables, (3) running SELECT queries for data analysis, (4) checking database contents. Supports multiple database connections with descriptions for intelligent auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.

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。

GitLab CLI for managing issues, merge requests, CI/CD pipelines, and repositories. Use when: (1) Creating, reviewing, or merging MRs, (2) Managing GitLab issues, (3) Monitoring or triggering CI/CD pipelines, (4) Working with self-hosted GitLab instances, (5) Automating GitLab workflows from the command line. Requires GITLAB_TOKEN (recommend minimal scopes). The `glab api` command enables arbitrary API calls - use read-only tokens when possible.

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。

Cross-agent self-inspection of your AI-agent stack. Audits skills, MCP servers, hooks, plugins, commands, credentials, and memory files across Claude Code, Codex, OpenClaw, and NanoClaw. Produces a structured inventory and narrative briefing with cross-ecosystem risk analysis. Use when the user asks to audit their own setup, check what they have installed, review their agent stack security posture, or understand cross-tool interactions. Use when a user has accumulated skills/plugins/MCP servers over time and wants visibility into their attack surface. Use after installing new skills or plugins. Do NOT use for vetting external code before install (that is repo-forensics). Do NOT use for incident response during active attacks. Do NOT use for fixing or patching vulnerabilities (forensify is read-only).

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。

Review and assess every issue in the TMDb project board's Backlog column — re-verify each against current main with a read-only fan-out, close the mechanically dead, promote the actionable to Ready with priority, size and execution order, and leave the rest in Backlog naming the decision they need. Use to groom the backlog, before planning a release, or on a schedule. Runs headless: it decides for itself within the rules below.

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。

Survey a whole React codebase as a senior React engineer, using React Doctor's scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the React code", "audit this codebase", "make this app faster / more robust", or wants a roadmap of fixes rather than a review of a single diff. For a regression check or a fix-it-now pass, use the `react-doctor` skill instead.

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。

Finds the cause of a hard bug by running several read-only subagents in parallel, each attacking it from a different angle (change history, code path, data and state, environment, reproduction), then checking their evidence, ranking the hypotheses and naming the one experiment that would confirm the leader. It diagnoses and does not fix. Use when someone says "hunt this bug with multiple agents", "swarm on this regression", "investigate in parallel", "find the root cause", or when a failure is intermittent, crosses components, or has resisted a first look.

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。

Reconstructs the workflow behind a past artifact by querying local ax session, recall, and commit history data. Use when a user asks "what made X work", "how was Y shipped/built", "extract workflow from <date|sha>", "workflow around <topic>", "recipe for this feature", or similar. It finds the anchor session or commit, inspects ax sessions, ax recall, and ax sessions show, and returns an ordered read-only narrative with decisions and evidence.

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。

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。

Verify the active host install, package, command ownership, enforcement, wrapper self-test, and active-dispatch coverage gap. Read-only.

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。