Каталог навыков агентов

Performs pseudo-bulk differential gene expression analysis using DESeq2 or edgeR. Aggregates single-cell counts to sampl...

Extract programming-language-agnostic pseudocode from source code in any language, preserving control flow and logical s...

Use this skill when implementing complex logic, developing functions, or designing algorithms. The Pseudocode Programmin...

Converts pseudocode descriptions and algorithm specifications into complete, executable Java code. Use this skill when y...

Convert pseudocode, algorithm descriptions, or specifications into complete, executable Python code. Handles natural lan...

Analyzes pseudocode, algorithms, or code snippets to extract and document functional requirements and business specifica...

Apply GDPR-grade pseudonymization to clinical or personal text with OpenMed, keeping a separately-held re-linkage key so...

Plan-spec-implement workflow for structured development. Only use when explicitly directed by user or when mentioned in...

PageSpeed Insights API で代表ページを計測し、Core Web Vitals・Lighthouse スコアの しきい値違反と改善候補を出力する。`config/psi-urls.txt` の URL に対し mobil...

Evaluates the trade-off between file size reduction and image fidelity when encoding radio astronomy data using JPEG2000...

Project Support Officer - Interface to the organization's project management system. Manages project list (project-list....

Setup personal web app with pnpm workspace monorepo structure deployable to Cloudflare. Use when starting a new personal...

Run PostgreSQL queries and meta-commands via CLI

psql — PostgreSQL's interactive terminal client and SQL script runner (the `psql` command). Covers connection strings/UR...

Automatically validate and fix Moodle PHP code for PSR-12 compliance with Moodle-specific exceptions (lowercase_with_und...

Engineering principles for rigorous agent work, condensed from poteto's pstack Cursor plugin (github.com/cursor/plugins/...

Rigorous engineering mode for nontrivial work in this repo — a set of named principles plus the leaf skills that apply t...

Design caller-first, type-safe interfaces and contracts with pre-implementation checkpoints before writing internal code...

Compare concrete module and type designs for a nontrivial boundary or ownership change. Use for architectural design req...

Run competing implementation approaches in isolated git worktrees, evaluate them against a shared quantitative rubric, a...

Compare concrete candidates for the same task and synthesize the best result. Use only when the user explicitly requests...

Validate performance measurements and before/after claims. Use when benchmarking latency, throughput, query performance,...

Analyze what a change can break outside its diff and verify the critical safety assumptions. Use for impact analysis, sh...

Turn recurring, evidenced repository mistakes into enforceable structure. Use when asked to prevent repeated errors with...

Create and prove a project-local verification skill for a costly invariant or concurrency property that ordinary tests r...

Generate and prove a project-specific skill for driving real UI, CLI, API, or library behavior. Use when a project needs...

Design and execute an evidence-based workflow for a large migration or unusual multi-part task. Use when no narrower pro...

Conduct read-only runtime tracing and subsystem mental model generation without modifying code. Use when exploring unfam...

Trace how a subsystem works or where a responsibility belongs. Use for code walkthroughs, ownership questions, or unders...

Conduct rigorous multi-perspective diff interrogation and code review. Categorize all findings strictly into 'act on', '...

Perform an adversarial review with independent passes using the active chat model. Use when asked to challenge a diff, f...

Catch the user up on progress in the current chat since their previous message, including outcomes, remaining work, and...

Reconcile project-local formal verification with changed source, rerun it, and distinguish stale models or harnesses fro...

Audit a project's verification instructions and feature map against source and live behavior. Use when a verification sk...

Route an explicitly requested pstack engineering workflow through investigation, design, impact review, measurement, or...

Reconstruct recent working context from authorized chat history and current artifacts. Use for where did I leave off, ca...

On every task, read pstack's poteto-mode skill first and follow its routing instructions when applicable.

Refine a task's approach before executing it: identify the real goal, useful primary evidence, missing specification, an...

Keep a concise, append-only decision and evidence trail for long or multi-phase work. Use when the user needs to audit c...

Rigorous engineering orchestrator ported from Lauren Tan's pstack (poteto-mode): reads your task, picks one of 23 playbo...

Check a TLA+ state-transition model with TLC and explain its reachable states or a counterexample as a chart. Use for st...

Coordinate bounded parallel coverage over independent slices using the active chat model. Use only when the user explici...

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious che...

Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they...

Explain a change or subsystem plainly, connecting how it works with evidenced reasons. Use when the user wants understan...

Improve TypeScript domain types and input boundaries where casts, optional-field bags, duplicate schemas, or mixed seman...

Edit requested prose to remove vague claims, stock AI phrasing, filler, or dense wording while preserving meaning, evide...

Maintain local pstack adaptations against the official upstream: compare versions, apply useful compatible updates, and...

Conduct deep historical archaeology and architectural rationale investigation using Git blame, PR discussions, and RAG l...

Investigate historical reasons for code, architecture, thresholds, or regressions using cited evidence. Use when asked w...

Display human psychology dashboard with energy, focus, emotions, biases, and learning calibration. Use when user asks ab...

Emergent psychological affect system — processes events into mood, trauma, attachment, romantic, humor, social awareness...

Psychoedukation zu Depression, Angststörungen, PTBS, bipolarer Störung, Schizophrenie, ADHS und Borderline. Wissensvermi...

Continuous monitoring for psychological integration and stability

Provide empathetic emotional support with active listening and evidence-based techniques.

Analyzes events through psychological lens using cognitive psychology, social psychology, developmental psychology, clin...

Navigate the mind from curiosity about behavior to clinical research.

Analyzes human mental health and psychological behavior, supports identifying common psychological problem tendencies th...

心理咨询 / 心理治疗(临床实践者视角 — 接案与评估 / 个案概念化 / 主流流派技术(CBT 与第三浪潮 / 精神动力 / 人本存在 / 家庭系统 / 创伤治疗) / 伦理边界与危机干预 / 督导与个人成长 / 执业形态与经营 — 涵盖...

Query the PsyTAR psychiatric adverse-reaction corpus. Use when the user asks about patient-reported ADRs, withdrawal sym...

Use this skill when the user wants to the platinum searcher - a code search tool similar to ag and ack.

Autonomous pentest campaign driver. Runs a scoped engagement end to end with no operator approvals - the deterministic d...

This skill should be used when the user asks about "prompt_toolkit Application", "app.run", "run_async", "asyncio", "eve...

This skill should be used when the user asks about "prompt_toolkit Buffer", "Document", "cursor position", "text manipul...

This skill should be used when the user asks about "prompt_toolkit completion", "Completer", "WordCompleter", "FuzzyComp...

This skill should be used when the user asks about "prompt_toolkit key bindings", "KeyBindings", "keyboard shortcuts", "...

This skill should be used when the user asks about "prompt_toolkit layout", "HSplit", "VSplit", "Window", "Float", "Floa...

This skill should be used when the user asks about "prompt_toolkit Style", "styling", "colors", "formatted text", "HTML...

This skill should be used when the user asks about "prompt_toolkit Validator", "validation", "input validation", "Valida...

Automates PTO request workflows including approval routing, balance tracking, and team coverage analysis. Checks for con...

Use PTS (Pivotal Token Search) to find the tokens, sentences and latent concepts that change whether a language model so...

Use when creating a new monthly ProductTank SF event in Linear - creates event project from PRO-60 template with calcula...

Generate ProductTank SF event status reports by synthesizing Linear issues, Gmail threads, and past conversations. Use w...

Use when uploading sponsor logos to ProductTank SF Google Drive - downloads image from URL (handles Cloudflare), validat...

Price-to-win lens using GSA CALC+, BLS OEWS, and incumbent USASpending award patterns for a pursuit. Use when user asks...

PTY gotchas (SIGWINCH, ConPTY, OSC, DA filter, coalescing). Load when touching src-tauri/src/modules/pty/ or anything th...

Καθοδηγεί πτυχιακή ή διπλωματική εργασία Πληροφορικής σε ελληνικό πανεπιστήμιο, από την επιλογή θέματος και το χρονοδιάγ...

Provision and drive a `pu` box — an Incus container used as a clean Linux host for CI, builds, and evidence capture. Use...

让你的 AI 不敢摆烂。用大厂 PUA 话术穷尽一切方案。触发条件：(1) 任务失败 2+ 次或反复微调同一思路; (2) 即将说'我无法解决'、建议用户手动操作、未验证就归因环境; (3) 被动等待——不搜索、不读源码、只等指示; (4)...

强化高能动性和高压闭环执行的行为技能。适用于连续失败、原地打转、空口完成、 把问题甩给用户、没搜就猜、修完就停等场景，也支持手动通过 /pua 进入核心模式。

Forces exhaustive problem-solving with corporate PUA rhetoric. Trigger on: task failed 2+ times, about to give up, sugge...

Forces high-agency exhaustive problem-solving with corporate PUA pressure. Triggers on user frustration, repeated failur...

Use for PUA/try-harder productivity coaching when the user expresses frustration, repeated failure, quality complaint, p...

> 强化高能动性和高压闭环执行的行为技能。适用于连续失败、原地打转、空口完成、 把问题甩给用户、没搜就猜、修完就停等场景，也支持手动通过 /pua 进入核心模式。

PUA/PIP 式 agent skill — 用企业 PUA 话术 / Performance Improvement Plan 督促 AI 不摆烂、不放弃、主动解决问题。支持 Claude Code、Codex CLI 等。

Put your AI on a Performance Improvement Plan. Forces exhaustive problem-solving with Western big-tech performance cultu...

Performance-coaching mode for repeated failures, passive behavior, completion-quality issues, or explicit try-harder req...

お前のAIを詰めろ。日本企業の詰め文化と体系的デバッグ方法論で全ての手段を尽くさせる。トリガー条件：(1) タスク失敗2回以上または同じアプローチの微調整ループ; (2)「解決できません」と言おうとする・手動対応を推奨・未検証で環境を原因帰...

日本語の生産性コーチングモード。明示的な依頼、反復失敗、受け身、検証不足、品質不満のときに、構造化トラブルシューティングと証拠ベースの完了確認を促す。

PUA KPI alias for Codex. Codex subcommand mapping for Claude Code /pua:kpi style usage; invoke with $pua-kpi.

PUA Loop — guided iterative development with recurring checks, completion evidence, and pause/abort markers. Use only wh...

PUA off alias for Codex. Codex subcommand mapping for Claude Code /pua:off style usage; invoke with $pua-off.

PUA on alias for Codex. Codex subcommand mapping for Claude Code /pua:on style usage; invoke with $pua-on.

PUA P10 alias for Codex. Codex subcommand mapping for Claude Code /pua:p10 style usage; invoke with $pua-p10.

PUA P7 alias for Codex. Codex subcommand mapping for Claude Code /pua:p7 style usage; invoke with $pua-p7.