1,962 件 ・ 関連度順
概要と使いどころ
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability.
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。
Reduce time-to-first-API-call (TTFAC) by optimizing every step of the developer onboarding journey. This skill covers authentication simplification, sandbox environments, interactive documentation, and identifying and eliminating common failure points.
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 local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
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 an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
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。
Triage failed Agent QA runs with MCP evidence, artifacts, logs, fixed failure categories, confidence, and actionable next steps.
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。
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
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。
Evaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt changes, reproducing failures, or running agent regression tests.
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。
Converges an underspecified request into a typed IntentSpec before planning or acting. Use when the user asks to implement, add, change, refactor, fix, migrate, configure, handle, triage, sort out, look into or decide something and the request leaves decisions open (which objects, which approach, what happens on failure, which trade-off), contradicts itself, admits two readings, or rests on an approach its sources may rule out — in a codebase, a ticket queue, a research brief or a runbook — or when the user says "clarify the intent", "what do you need from me", or invokes intent-router. Looks up what its sources hold (code, history, decision records, a ticket log, an order record, the policy in force) before asking; asks only preference or irreversible questions, one at a time, with a recommended default; halts instead of guessing; checks the delivered work against the spec. Silent on a fully stated task its sources do not contradict. Not for explaining existing state ("what does X do", "why is Y slow").
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 an evidence-based investigation of a bug, failure, or unexpected behavior with investigate and publishes the resulting investigation report to a user-specified Confluence location. Use when the user wants something debugged, diagnosed, or root-caused AND the findings posted to a Confluence space or page. Requires a configured Atlassian MCP server. Does not investigate to a local file only — use investigate. Does not publish an arbitrary existing markdown file — use markdown-to-confluence. Does not document an already-understood feature to Confluence — use project-documentation-to-confluence. Does not plan or specify a new feature to Confluence — use plan-a-feature-to-confluence. Does not publish to Jira — use work-items-to-jira.
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。
Performs deep architectural analysis of a specified module, directory, or feature area by examining structural coupling, data flow, concurrency patterns, risk, and SOLID alignment. Use when the user wants to assess, evaluate, or review the architecture, design quality, dependency structure, coupling, cohesion, or technical debt of an existing part of the codebase. Not for investigating specific bugs, runtime errors, or failures — use investigate. Not for test planning — use automated-test-planning. Not for file-level code review — use code-review. Not for researching open-ended options, prior art, or how something works — use research. Not for designing a new interface or contract — use design-an-api. Not for planning the change its findings imply — use plan-a-change. Not for discovering bounded contexts, ubiquitous language, or where code boundaries diverge from domain boundaries — use ddd-analysis. Not for writing documentation or architectural decision records.
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 update a runbook for an operational scenario — an incident an alert fires for, a recurring scheduled task, or a known failure mode on a live service — using a consistent template. Use when writing, drafting, authoring, or updating a runbook for an alert, incident, on-call procedure, scheduled maintenance, or operational SOP. Applies a YAGNI preflight requiring the scenario to be real before producing the runbook. Does not produce feature or system documentation — use project-documentation. Does not record architectural decisions — use architectural-decision-record. Does not create coding standards — use coding-standard.
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。
Write code through a disciplined, BDD-framed Test-Driven Development loop: build a behavior test list, then drive each behavior through red-green-refactor with an enforced observed-failure gate. Use when the user wants to implement, build, or write code test-first, "do TDD", follow "red-green-refactor", drive code from tests, choose the next test by the Transformation Priority Premise (TPP) or ZOMBIES ordering, or grow a feature behavior-by-behavior with tests leading. This skill writes and changes code; it does not produce a test plan document (use automated-test-planning, or manual-test-planning for a plan a person runs by hand), review or audit existing code (use code-review), restructure existing code outside a TDD loop (use refactor, or plan-a-change to plan a multi-module restructure), specify what a feature should do (use plan-a-feature), or find the root cause of a bug (use investigate). Runs its loop to completion without pausing for review; to review each behavior as it lands, use pairing.
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 human-readable, progressive-disclosure overview of unfamiliar code or a pull request's changes — why it exists (the real problem it solves or goal it serves for the business or a user), and from there what it does, how it flows, and where to start — so you can get up to speed before working on or reviewing it. Use when you want to understand, get oriented in, make sense of, explain, or get up to speed on a chunk of code, a file, a directory, a symbol, or a PR's changes. Writes the overview to a scratch file and changes no code. Does not review code quality or raise findings — use code-review for auditing changes or post-code-review-to-pr for posting them. Does not produce durable feature or system documentation — use project-documentation. Does not assess architecture or structural risk — use architectural-analysis. Does not diagnose bugs or root-cause failures — use investigate. Does not pace a person through the code one step at a time in conversation — use code-walkthrough.
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。
Researches an open-ended question — options, possible solutions, prior art, trade-offs, or how something works — and produces a durable, evidence-backed, adversarially-validated report that recommends an option without committing the team to any artifact. Use when you want to research approaches, weigh options, survey prior art or the state of the art, or understand how something works before committing to a direction. Does not diagnose a bug, failure, or root cause — use investigate. Does not specify a feature — use plan-a-feature. Does not create or update a coding standard — use coding-standard. Does not compare two concrete artifacts for gaps — use gap-analysis. Does not assess an existing module's architecture — use architectural-analysis. Does not capture feedback on Han's own skills — use han-feedback.
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 original short videos using the 反差喜剧｜越从容越失控 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.
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 original short videos using the 角色登场｜失误后借身体特征破局 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.
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 is brittle, drifting, repeatedly failing, or needs a Reliable Skill Contract. Trigger for phrases like skill lifeguard, reliable skill, self-maintaining skill, negative examples, verification checkpoints, drift signals, replay hooks, or failure log to skill patch. Audits or patches skills so high-value workflows include explicit forbidden behaviors, checkpoints, machine-checkable done conditions, replay or smoke hooks, and drift detection.
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 whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. Use when asked to assess agent readiness, repeated agent failures, Rules/Skills/Hooks/Memory effectiveness, missing validation or recovery loops, or whether a harness repair improved later outcomes. Do not use for code-only audits, AGENTS-only audits, individual skill reliability reviews, or executing the task itself.
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。
Apply the bioengineering, mechanobiology, and lymphatic transport reasoning of J. Brandon Dixon, professor of mechanical and biomedical engineering at Georgia Institute of Technology. Reach for this skill whenever analyzing lymphatic biomechanics, active vessel contractility versus passive drainage, peristaltic fluid transport, microfluidic organ-on-a-chip design, preclinical lymphedema models, non-invasive functional imaging, targeted nanomedicine delivery, or automated disease staging. Use this skill to critique bioengineering assumptions, guide quantitative protocol design, evaluate biomechanical pump failure, and formulate interdisciplinary biomedical solutions.
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。
Deploy funnelcake (api + relay) to ANY environment (production, staging, poc) on GKE via ArgoCD. Use when: (1) Deploying new funnelcake commits, (2) Building Docker images for GKE (amd64), (3) Running ClickHouse migrations, (4) Troubleshooting ImagePullBackOff errors, (5) Syncing staging/poc after production deployment. Covers complete workflow with PRE-FLIGHT CHECKLIST to prevent common deployment failures.
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。
Fix content serving failures caused by metadata (KV store, database) being out of sync with actual storage (GCS, S3, filesystem). Use when: (1) Content exists in storage but API returns "processing" or "not ready", (2) Webhook callbacks that update metadata failed silently, (3) Backfill scripts generated content but didn't update status records, (4) HLS/transcoded content exists but transcode_status is not "Complete", (5) Handler checks metadata status BEFORE checking if content actually exists in storage.
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。
Fix black camera/microphone preview in Flutter macOS apps launched via `flutter run` from a terminal emulator (cmux, iTerm, Terminal.app, VS Code integrated terminal, Cursor, etc.). Use when: (1) camera plugin reports initialized but preview is black with no frames, (2) logs show "initialization completed via timeout" or similar first-frame timeout fallback, (3) AVCaptureSession.startRunning() returns without error but zero frames arrive, (4) the app's Info.plist has NSCameraUsageDescription and entitlements (com.apple.security.device.camera, audio-input) are correctly set, (5) no permission dialog ever appears, (6) same failure mode for microphone. Root cause is macOS TCC attributing camera/mic requests to the *responsible process* (the parent terminal) rather than the Flutter app itself. TCC refuses to prompt because the terminal is hardened-runtime without a camera entitlement, and silently denies. Not a bug in the camera plugin — would reproduce with ANY camera code.
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。
Fix Gorse recommendation engine pods crashing with "user: unknown userid 65532" error. Use when: (1) Gorse master/server/worker pods show CrashLoopBackOff or Error status, (2) Logs show "failed to get user directory" with unknown userid, (3) Running gorse containers with runAsNonRoot security context and custom UID. The gorse images call os.UserHomeDir() at startup which requires the UID to exist in /etc/passwd.
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。
Fix test failures when adding retry/fallback logic causes mock call count mismatches. Use when: (1) Test fails with "Expected: <1>, Actual: <2>" or similar call count errors after adding retry or fallback mechanisms, (2) MissingStubError appears for methods in new fallback code paths, (3) Mockito verify().called(N) assertions fail after behavior changes. Applies to Dart/Flutter with Mockito, but pattern is universal.
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。