1,226 件 ・ 関連度順
概要と使いどころ
Use when cutting a RELEASE CANDIDATE of riddl — tagging X.Y.Z-rc.N, publishing it as a GitHub prerelease, and later promoting it to a final release. Also use when the user says "cut an RC", "release candidate", "rc.1", or asks to promote an RC to final. For a normal release use /ship 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。
Search rad-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.
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 one surface of tdmcp (artist controls, library/packaging, CLI/DX, AI/LLM, or TouchDesigner depth) for candidate NEW features — inventory what exists, cross-check the roadmap, apply the gap-finding lenses, vet each idea, and emit a structured, novelty- and confidence-labelled candidate list to _workspace/discovery/. Use when a td-surveyor agent is scouting a surface during the feature-discovery harness.
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 turning something that happened into something that makes the next run better - "write a retro", "record this paper cut", "this bug escaped verification", "make this an eval", "why do we keep hitting this", "did that change actually help", "scorecard", "what did we learn from that run", "lessons keep getting re-learned". Covers the six-step loop (capture, classify, convert, change, measure, retro), the repo artifact each step produces, and how escaped bugs become eval cases. Do NOT use to design or judge a single workflow experiment (see `workflow-experimentation`, which this loop feeds), to decide where to run work (see `dogfooding`), or to debug one failed execution in the moment.
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 the team lead points Architect at a prior agistra.dev hub path and asks it to check for or perform additional migration — trigger phrasing such as 'migrate my data from <path>', 'check what didn't get migrated', 'did we miss anything from my old hub', or 'do a completeness pass on <path>'. Walks the prior hub's full directory tree read-only, diffs it against the fixed scripted migration scope plus any existing migration report, and asks the team lead one clear question at a time about anything a scripted migration would never have discovered. Never writes or copies anything itself — every confirmed item is delegated to the existing migration primitives. Do not use for the first-run scripted migration prompt during `npm run setup` — that is unrelated, already-automated flow this skill does not replace.
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 the team lead points Architect at a prior agistra.dev hub path and asks it to check for or perform additional migration — trigger phrasing such as 'migrate my data from <path>', 'check what didn't get migrated', 'did we miss anything from my old hub', or 'do a completeness pass on <path>'. Walks the prior hub's full directory tree read-only, diffs it against the fixed scripted migration scope plus any existing migration report, and asks the team lead one clear question at a time about a
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: 'intake this repo/skill', 'evaluate external skill', 'should we adopt X', a candidate repo URL plus an adoption question, or any external skill/workflow/tool surfaces as a possible fit for Agistra. Structured front-door evaluation of external skills, workflows, and similar capability artifacts before any install, promotion, or adaptation decision. Ends in exactly one classification: Install candidate, Adapt concept, or Reject. Never install first — intake 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。
作業パターンを skill 化すべきか判定する共通スキル。org-retro と org-curate から呼ばれ、 「skill 化推奨 / 候補止まり / curated ノートのまま」の 3 値と根拠を返す。 自動 skill 化はせず、推奨は machine-local な knowledge/skill-candidates.local.md に追記し、 窓口が候補キューが溜まった時点でバッチで人間に問い合わせる二段構え。
skill の棚卸し（廃止候補 / 重複統合 / owner 明記チェック）。 状態ベースで発火する: 候補キュー knowledge/skill-candidates.md の pending が 5 件以上、 または .claude/skills/ 配下の work-skill 数（org-* を除く）が 20 以上になった場合のみ実行。 時間ベースの /loop では起動しない（変化の無い日に raw ログを汚す副作用を避けるため）。
Product-research (选品) desk (Busabase App-in-Skill) for a cross-border e-commerce seller. The agent sweeps trend sources — Amazon BSR movers, TikTok viral product videos, Temu/AliExpress rising items, Google Trends terms, competitor new launches — and files product candidates with margin cards (landed cost, fees, breakeven ACOS) and competition reads; Kelly verdicts them develop / watch / drop, and develop items become sourcing and listing briefs handed to kelly-listing. Use when the user invokes $kelly-picks or /kelly-picks, or asks for 选品, product research, a product sourcing radar, BSR movers, TikTok viral products, a margin calculator, breakeven ACOS, competition reads, or product candidate triage.
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 board (Busabase App-in-Skill) that runs a fixed suite of mock test cases against a baseline vs candidate agent version and surfaces rubric-scored regressions before a release. Use when the user invokes $kelly-agent-eval or /kelly-agent-eval, wants to review agent-version regressions, compare baseline vs candidate quality, triage a release, or record a release approve/block decision. Deterministic mock rubric scores only — not a real LLM-judge call, and it never deploys anything.
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。
Busabase App-in-Skill review queue that scores candidate SME financing deals (revenue-based/RBF-style credit) with a deterministic, fully auditable rule-based rubric — never an LLM or API call. Use when the user invokes $kelly-deal-scorer or /kelly-deal-scorer, wants to review a deal-underwriting queue, score financing candidates, compute a composite score breakdown, see a suggested revenue-share rate range, or record approve/send-back/reject decisions for a private-credit or RBF-style lending pipeline.
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 Busabase-backed sandbox desk for scoring and triaging course-instructor ("讲师") candidates found on a recruiting-style platform. Use whenever the user invokes $kelly-instructor-sourcing or /kelly-instructor-sourcing, wants a lightweight instructor candidate tracker, needs to score sourcing-platform leads against a three-axis rubric (background endorsement, expertise depth/breadth, teaching-service ability) before reaching out, or wants to log a WeChat add without building a live-connected outreach tool. Three subcommands - setup, criteria, review - plus the desk itself. v1 is sandbox-only — every dataset is deterministic mock data, it never connects to a real sourcing-platform or messaging account, and it never sends a message or automates a WeChat add - that stays entirely human-performed outside the app.
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。
MUST USE when 01_intent/creative_brief.yaml and 03_analysis artifacts exist and the user asks to choose clips, extract candidate segments, run triage, or build 04_plan/selects_candidates.yaml. Use before /blueprint whenever selects are missing, and re-run when the brief or analysis 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。
Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts during endpoint invocations. Use when the user says "my endpoint is failing", "show me the logs for endpoint X", "what error did endpoint Y produce", "why did endpoint Z return no rows", "is this endpoint hitting cache", or "check the last N runs". Focused on a single named endpoint's runtime log entries, not project-wide auditing or query 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。
Identify drug repurposing candidates via target-based, compound-based, and disease-based strategies. Combines drug-target-disease network reasoning with mechanism rationale, clinical-trial precedent, and patent/regulatory feasibility. Use for hypothesis-generating repurposing for orphan diseases, finding existing drugs for new indications, and prioritizing candidates by evidence and feasibility.
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。
Reads a CARLA Leaderboard results.json — per-route driving score, route completion, infraction penalty and the infraction lists — explains how the score was computed for that leaderboard version, and rescores an existing result under the other version's rules (2.0 multiplicative vs 2.1 additive) without re-running anything. Also diffs two runs and merges sharded result files. Use when the user asks "what did I score", "why is my score low", "did my agent pass", "why don't my scores match the leaderboard", or hands over a results.json.
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。
Reads and summarises ScenarioRunner output — the criteria pass/fail tables from --output/--file, the machine-readable --json and --junit result files, and the criteria JSON written alongside a --record recording — and runs the metrics module (metrics_manager.py) to compute custom measurements over a recorded run offline, without the simulator. Use when the user asks "did the scenario pass", "why did it fail", "summarise these results", "compare these runs", or wants distance/speed/lane metrics from a recording.
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。
Help job seekers use Otameshi Tenshoku to prepare profiles and applications, clarify trial conditions, plan learning visits or paid trial work, and reflect on the experience. Use when a candidate wants to apply for, prepare for, negotiate the scope of, or review an otameshi work experience; do not use to predict whether they will be hired or to judge their aptitude, to state fees, contract terms, or service conditions from memory, or to submit an application, update a profile, or send a message on their behalf. Employer-side requests belong to the employer skills (trial-work-design, trial-listing-draft, applicant-reply and others).
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。
Check, from the employer's side, what has been put in writing before a paid Otameshi Tenshoku assignment starts under gyomu-itaku: item by item whether the deliverable, delivery date, fee and how it is calculated, payment due date, who pays, out-of-scope work, revision limits, company support, rights, confidentiality and termination are stated in a contract, purchase order or email rather than in chat or by word of mouth, count the days from delivery to payment, and find pay tied to satisfaction or hiring, unpaid or unlimited revisions and one-sided termination. Use when a hiring manager, recruiter or small-business owner is about to offer terms to a candidate, has been asked by a candidate what is still unwritten, or needs the conditions written for a platform contract screen; do not use to judge whether the terms are lawful or the fee fair, to compute withholding or consumption tax, for employment contracts, or to sign, send or conclude the contract on the user's behalf.
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 what an employer will have a candidate do during an Otameshi Tenshoku trial: turn a business problem into a bounded paid assignment or an unpaid learning visit, with scope, completion criteria, candidate hours, company staff hours, duration, compensation and change conditions, and check the planned cost against the budget. Use when a hiring manager, recruiter or small-business owner wants to decide what work to offer, how much time it takes, what it costs, or how to adjust a plan when materials are late or the scope grows; do not use to write the public listing (trial-listing-draft), to reply to applicants (applicant-reply), to state market rates, legal, tax or service conditions from memory, or to post, contact or contract on the user's behalf.
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。
Turn vague preferences about employers into criteria that can actually be used to choose between them: for each one, what would have to be seen to confirm it, whether it comes from firsthand experience or from an untested assumption, whether it is a must, a nice-to-have, or something to avoid, and which pairs of criteria pull against each other while both being treated as required, then test the set against real candidates. Use when a new graduate is working out what to select employers on, when someone who has decided to move needs criteria for where to apply, or when a stated axis like "a place I can grow" needs to be made checkable; do not use to recommend an industry, job, or employer, to score or rank candidates, or to judge someone's stated preferences.
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。
Rank and prioritize neoantigen/epitope candidates by likely T-cell response using NeoFox feature annotation, PRIME2.0, BigMHC-IM, the Łuksza/Balachandran fitness model (agretopicity + foreignness), and pVACtools tiering. Encodes the field's hard truths that immunogenicity is the least-solved layer (dedicated scores ~AUROC 0.6-0.7, modest PPV), that scores are valid only for RANKING within one patient (never absolute go/no-go or cross-patient), that DAI has anchor-inflation and WT-denominator traps, and that stacking weak correlated scores into one number is a red flag. Use when ordering a candidate list for a vaccine. Binding lives in mhc-binding-prediction; calling in neoantigen-prediction.
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。
Nominates and assesses CRISPR off-target sites genome-wide. Enumerates candidate sites by mismatch and bulge tolerance with Cas-OFFinder/CRISPRitz, ranks them with the published CFD score (SpCas9-only, relative ranker) or MIT/CRISTA/energy models, runs variant-aware screening against gnomAD/individual genomes (CRISPRme), and frames the empirical genome-wide discovery assays (GUIDE-seq, CIRCLE-seq, CHANGE-seq, DISCOVER-seq, Digenome-seq) and high-fidelity nuclease choice (HiFi Cas9, Sniper-Cas9, eSpCas9, SpCas9-HF1). Use when assessing guide RNA specificity, choosing among candidate guides, screening a therapeutic guide against population variation, or planning empirical off-target validation. Distinguishes predicted vs detected vs validated. On-target activity scoring and deaminase (Cas-independent) base/prime-editor off-targets are separate skills.
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。