「findings」の検索結果

AI systematic knowledge acquisition from unfamiliar territory — deliberate model-building with feedback loops. Maps spaced repetition principles to AI reasoning: survey the territory, hypothesize structure, explore with probes, integrate findings, verify understanding, and consolidate for future retrieval. Use when encountering an unfamiliar codebase or domain, when a user asks about a topic requiring genuine investigation rather than recall, when multiple conflicting sources require building a coherent model, or when preparing to teach a topic and deep understanding is required first.

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-only audit of a GitHub repository's security posture. Gathers ref protection (rulesets AND classic branch protection), Actions token permissions, code and supply-chain features (Dependabot, secret scanning, push protection, CodeQL), and repo hygiene toggles via `gh api`, then classifies findings against essential / recommended / advanced tiers into a PASS/GAP report. Makes NO changes. Use when reviewing a repo before open-sourcing or a release, auditing a public user-owned repo whose CI auto-commits to the default branch, verifying a hardening change actually took effect, or producing a baseline security posture report for a repository.

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。

Alternate /pr-review and /pr-address on a PR until the PR is truly mergeable — no new review findings, zero unresolved inline threads, zero unaddressed top-level reviews or issue comments, all CI checks green, and two consecutive quiet polls after CI settles. Use when the user wants a PR polished to merge-ready without setting a fixed number of rounds.

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。

Generate professional reports from analysis results. Use when user needs to create formatted documents summarizing findings.

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 code review on staged changes or a pull request. Checks for bugs, security issues, performance problems, and best practices. Use when user says "review code", "check my code", "review PR", or "is this code okay". Optional +check flag validates findings via a fresh-context subagent.

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。

Analyze queried data for trends, week-over-week comparisons, distributions, funnels, cohorts, top-N lists, anomalies, sanity checks, and report-ready findings. Use after or alongside ClickHouse queries when the user wants insight rather than raw rows.

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。

Analyze queried data for trends, week-over-week comparisons, distributions, funnels, cohorts, top-N lists, anomalies, sanity checks, and report-ready findings. Use after or alongside ClickHouse queries when the user wants insight rather than raw rows.

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。

Connects the user with a LegalZoom attorney for legal consultation. Use when a user asks about attorneys, lawyers, or legal help, or when contract review reveals high risks or low-confidence findings.

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 for ANY bug bounty, penetration test, or web/API/mobile security assessment: recon, testing endpoints, analyzing Burp traffic or any bug-bounty platform's MCP (HackerOne, Intigriti, Bugcrowd, YesWeHack, Immunefi), reviewing APKs, bypassing a WAF, enforcing scope, hunting a specific vuln class, validating findings, writing reports, or when you are stuck on a target and about to give up. Activates automatically for all bug-bounty and pentest sessions. Runs an autonomous, never-surrender predator methodology: refuses to conclude "secure", exhausts each vuln class to depth, proves a real attacker-path with impact and no false positives, tracks coverage so nothing is re-tested or skipped, diagnoses failed tooling from full logs, and hunts at maximum effort with intelligent token use until the goal is found. Activates and follows instructions in ANY language the operator writes in (the skill itself is English). Bundles a per-class web-exploitation KB, a writeup library, and PayloadsAllTheThings.

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 code review on staged changes or a pull request. Checks for bugs, security issues, performance problems, and best practices. Use when user says "review code", "check my code", "review PR", or "is this code okay". Optional +check flag validates findings via a fresh-context subagent.

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。

Before committing any non-trivial change, dispatch the diff to a reviewer runtime via ATO (`ato dispatch <reviewer> --session <id>`), parse the numbered/severity-tagged findings, apply or defer each one with a recorded justification, then commit. Fights the "build passes therefore ship it" failure mode — what Garry Tan calls the AI agent complexity ratchet. Place in the v2.16 stack: this skill is the LAST gate. `ato-warroom` decides the design; `ato-mission` runs the multi-step work and produces the diff; `ato-review` checks the diff before commit. When the review is part of a Mission, dispatch the review with `--require-tools read_file,grep,git_diff,git_log` so the reviewer can walk the source itself instead of reasoning from a paraphrase (PR-1.5 tool surface). Receipts land in `execution_logs` and the Mission narrative. Fires automatically before commits touching public surface (CLI subcommands, Tauri commands, MCP tools, schema migrations, security boundaries) or whenever a diff exceeds ~50 LOC of behavior 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。

Use when optimizing Convex database read bandwidth, documents-read cost, query indexes, full-table scans, function-level usage dashboard findings, or code that uses .filter(), unbounded .collect(), N+1 reads, or expensive reactive Convex queries.

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 companies, competitors, funding, news, leadership, and market context with Exa Agent and advanced search. Use when researching companies, competitor analysis, market research, or building company lists. Writes findings the caller can fold into brand/competitors.md or brand/landscape.md. Prefer this over ad-hoc web search for company deep dives. Distinct from competitive-intel (full brand competitive file methodology) - this skill is the Exa research engine those foundation skills should call.

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-dive ONE competitor's organic footprint — exact ranking keywords and URLs, content themes, backlink profile, and exploitable gaps — with findings written into brand/competitors.md. Use this skill when the user names a competitor and wants to know what to learn from them, counter, or outrank, including head-to-head comparisons against the user's own domain. For market-level mapping first, use openseo-competitive-landscape. Triggers: "analyze competitor", "competitor keywords", "competitor backlinks", "beat <competitor>", "competitor seo teardown".

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。

Multi-agent research that keeps bringing gifts back — like cats! Dispatch multiple agents to research a topic in parallel, compile findings, and iterate on new discoveries.

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。

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

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。

Three-phase code review. Investigates internally, verifies findings, then reports only confirmed issues.

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, finish, or port PCB placement and routing using circuit intent, mechanical constraints, sourcing evidence, native DRC/connectivity, rendered views, and manufacturing feedback. Use before routing, after autorouting, before fabrication release, when adapting a proven board to another connector, enclosure, platform, or regional variant, or when reviewing layers, GND references, power distribution, decoupling, buses, controlled interfaces, RF keepouts, vias, cost-driving features, opens, or DRC findings.

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 the UI and style files changed in the working tree against this repo's own design system, before they are saved or committed. Runs the same deterministic check as the CLI's --check flag (no tokens, about a second): hardcoded colours where a token exists, near-identical colour twins, off-scale spacing, radii, font sizes and shadows, typefaces outside the system, arbitrary Tailwind values, static inline styles, !important, duplicate component definitions and imports of the copy to avoid, new tokens that copy an existing one, chart colours written by hand where the repo keeps a chart palette (and one calm warning asking for a palette where it keeps none), on a repo built on MUI, Mantine, Chakra or Ant Design, colours or pixel sizes written onto kit components where the theme has a value, and on a Tailwind theme or a shadcn repo, palette classes such as text-gray-500 where the theme names a colour of that kind. Findings name the file, the line and the fix. This is the small, fast check for what just changed; the roast skill is the full scan of the whole repo with a report.

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 this skill when routing adversary findings in Phase 4. Provides routing logic, iteration limit enforcement, and escalation protocols.

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。

Display the current VCSDD pipeline status for the active (or specified) feature. Shows phase, mode, sprint count, open findings, pending proofs, and the traceability summary.

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 Phase 4 (feedback routing) after an adversarial review FAIL. Routes adversary findings to the earliest affected phase, checks iteration limits, and escalates to human if limits are exceeded.

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 you need to query an OpenCTI instance — is this IOC already known, what entities/reports/campaigns exist for an actor — or push new intel into it — creating indicators/observables, labelling, TLP markings, relationships, or importing a STIX 2.1 bundle. Two-way integration. Commonly invoked by /ip-investigation and friends to check whether an indicator is already in your knowledge base, and by analytical skills that want to publish their findings back to OpenCTI. Reads $OPENCTI_URL and $OPENCTI_TOKEN.

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 user asks to investigate, check, enrich, or characterize an IP address (IPv4 or IPv6). Chains VirusTotal, Shodan, AbuseIPDB, GreyNoise, OTX, and optionally Censys in parallel, then consolidates findings and prioritizes follow-up IOCs. Invoked by /cti-orchestrator when the target is an IP.

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。