「bounded」の検索結果

Audit context files (CLAUDE.md, .claude/ tree, READMEs, docs) for broken references and verifiably stale content. Runs a deterministic offline link/path checker first, then a bounded semantic review where every finding must cite evidence. Reports findings; fixes only on request. Use when the user says "docs check", "/docs-checker", "check the docs for stale content", "audit CLAUDE.md", or when a scheduled cloud routine fires.

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。

Defensive triage skill for OpenClaw, Hermes Agent, host integrity, and OpenClaw skill-supply-chain scanning. Detects prompt injection, session drift, context overflow, host anomalies, and unsafe skills while keeping actions bounded and auditable.

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。

Create or materially revise a durable specification when the user explicitly requests a spec/new feature contract or a named ambiguity requires formal DEFINE; do not trigger for ordinary bounded edits, implementation, task breakdown alone, review, or documentation of already-settled behavior.

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。

Run one bounded adversarial pass when the user explicitly requests a report-style stress test or ROSE identifies a concrete material loophole in an existing strategy, spec, plan, review, or claim; do not trigger for an interactive grill/frontier interview or merely before write-back, implementation, reconciliation, or completion.

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。

Run a bounded red-green-refactor feedback loop only when the user explicitly requests TDD, accepts reproduction-first proof for a bug, or an accepted high-risk behavior specifically requires red/green evidence; do not trigger for every logic, bug, behavior, or implementation change.

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。

Simplify a bounded code area when the user explicitly requests behavior-preserving refactoring or a named complexity/readability problem is the accepted task; do not trigger automatically after implementation, during every review, for adjacent cleanup, or when behavior may change.

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。

Perform direct, bounded browser inspection through the `browser.qa` capability when the user requests runtime UI evidence or one browser-specific claim needs DOM/accessibility/console/network/visual verification; do not trigger for every UI change, backend work, delegated QA, or durable E2E artifact routing.

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。

Implement an accepted change in bounded dependency-ordered increments when the user requests implementation and the scope benefits from multiple coherent slices; do not trigger merely because work touches multiple files, changes behavior, or is over an arbitrary line count.

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。

Perform a bounded security design/hardening pass for explicit security or threat-model intent, or a concrete auth/authorization/secret/untrusted-input/file-upload/sensitive-data risk; do not trigger for every input, data store, third-party call, implementation, review, or release.

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。

Research one bounded mature-project/prior-art question when the user explicitly asks how established projects handle it or ROSE names a decision-shaping prior-art gap; do not trigger automatically for IDEATE, DEFINE, BUILD, implementation, local review, or every design choice.

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。

Prefer a fresh matching specialist for a clear bounded non-trivial package when current capabilities and permissions permit it; use direct ROSE work only for accepted direct-work exceptions or a concrete block.

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。

Clarify a concrete requirements decision, create one bounded static interview packet, or run an explicitly user-invoked frontier batch over a plan, decision, or idea; trigger on explicit grill/interview/refinement intent or a named material ambiguity, not on ordinary planning, implementation, research, test-plan, report-style review, or BUILD 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。

Repair one concrete reproducible build, typecheck, lint, test, packaging, or CI failure with a bounded root-cause-first loop; do not trigger for runtime bugs without a failing gate, broad test strategy, dependency/toolchain migration, or generic implementation.

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。

Run the AILI delivery lifecycle from natural-language IDEATE, DEFINE, BUILD, and SHIP intent or the equivalent slash shortcuts; use for idea shaping, spec/test definition, bounded BUILD package queues, review-repair closeout, or adapter routing without exposing internal stage commands.

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。

Conduct one bounded evidence-grounded code review when the user explicitly requests review or ROSE names a concrete unresolved correctness/quality risk; do not trigger automatically after implementation, before every merge, for every bug fix/refactor, or as a completion gate.

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。

Detect XML/SVG/YAML entity expansion (Billion Laughs) vulnerabilities in parsers that allow unbounded entity definitions.

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。

Interpret and design bounded FIPA communicative-act exchanges using XC00037H semantics while keeping delivery, authority, and external effects separate. NOT for proving delivery, task authorization, or external effect completion.

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。

Designs and audits data retention and file compaction for an embedded SQLite datastore in a long-lived service — a unified retention registry (one declared policy per table), TTL / absolute-age / row-count-cap policies, a fail-loud coverage guard, WAL/checkpoint tuning, and auto_vacuum/incremental-vacuum so pruning actually shrinks the file. Use when a SQLite DB grows unbounded, a table has an index but no DELETE, a pruned DB never shrinks on disk, metrics are stored as raw events forever, or a new table needs bounding. Keywords retention policy, TTL, reaper, prune, VACUUM, auto_vacuum, incremental_vacuum, WAL checkpoint, freelist, DB bloat, row cap, per-tenant quota. NOT for Postgres/MySQL/server-DB partitioning or TTL, log-line rate-limiting/sampling, backup/replication, schema migrations, or query-performance indexing.

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。

Synthesizes evidence-linked feedback from validation results, confidence evidence, and iteration triggers. Proposes bounded revision guidance for a stated acceptance failure. Activate on 'synthesize feedback', 'improvement suggestions', 'actionable feedback', 'iteration guidance', 'feedback generation'. NOT for iteration detection (use dag-iteration-detector) or convergence tracking (use dag-convergence-monitor).

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。

Specifies bounded DAG execution contracts and evaluates executor receipts for dispatch, cancellation, joins, and effect reconciliation. Use when an implementation must bind a planned DAG to named runtime controls. NOT for claiming an executor is active, spawning agents, or certifying an effect from a plan.

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。

Investigates DAG incidents with a precise top event, timeline, competing hypotheses, barriers, propagation, and bounded recovery. NOT for automated root-cause classification, trace collection, or performance profiling.

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。

Produces a narrow-interval quality signal for a WinDAGs skill that a third party can verify without inspecting model weights or method internals. The mechanism is attribution-kNN over a tamper-evident outcome log (task→skills→accept/reject store), combined with a conformal-prediction calibration certificate that provides a formal coverage guarantee. Thompson/Beta sampling is explicitly rejected as a category error: it produces a selection signal for stationary i.i.d. rewards, not an attestation signal for context-dependent LLM output quality. The resulting bundle — outcome-log Merkle root + conformal threshold + optional TEE guardrail signature — constitutes a "narrow-interval trust" credential: verifiable, bounded, and internals-opaque.

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。

Design a bounded FIPA-style conversation and map it cautiously to JADE behavior APIs. NOT for treating a JADE API example as protocol delivery or application authorization proof.

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。

Install Port Daddy's bounded interactive coordination hooks ("tentacles", from the Giant Squid Harness) into the INTERACTIVE sessions of agentic coding CLIs (Claude Code, Codex, Gemini, Antigravity/agy) by auto-detecting which CLIs are installed and writing PER-PROJECT hook config behind a runtime gate, so coordination fires only inside a Port Daddy project while the daemon is running — never machine- wide-always-on. Use when the user says "install port daddy hooks", "agent CLI hooks", "interactive session hooks", "make coordination hooks fire in interactive sessions", "codex/gemini/agy hooks", or "auto-detect agent CLIs". NOT for generic software/package installation; NOT for installing the Port Daddy daemon or `pd` CLI itself (delegate to the `port-daddy` skill / `pd setup`); NOT for MCP server setup (delegate to `pd mcp install`); NOT for authoring new skills (delegate to `skill-architect` / `skill-creator`); NOT for editing the tentacle scripts themselves (owned by the Giant Squid Harness program; this installer layer is pd-adr-090).

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。