Productivity tracker and daily review assistant。Input activity logs, time notes, goals, or a dai。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。
Two-tier memory system that makes the AI a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so the AI understands requests like a…
Structure le lancement d'un projet avec objectifs, livrables, étapes et risques. À utiliser quand l'utilisateur commence un nouveau projet.
Calculate a productivity score using actual Agent Monitor metrics — session completion rates, cache efficiency (cache_read vs input), compaction pressure (baseline tokens), turn…
Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.
Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.
Sync tasks and refresh memory from your current activity
Organise une semaine avec priorités, blocs de temps et objectifs. À utiliser quand l'utilisateur veut planifier sa semaine ou organiser ses tâches.
Todo-first progress convention for multi-step procedures — loaded by every multi-step agent to track its own steps without drift
Provide graduated assistance from abstract conceptual nudge to concrete procedural step, with reflection required before each escalation.
Group and transform selected todo.txt items into approval-gated OpenSpec changes while preserving privacy and avoiding one-to-one promotion assumptions.
Analyze the user's Claude Code prompt history from ~/.claude/history.jsonl — time patterns, topics, interaction style, weekly evolution, plus a subjective reflection on working…
protobuf.js dynamic .proto parsing and code generation for Node.js. Runtime schema loading, static code generation, reflection API, and JSON interop for agent message contracts.
模擬 FT50／UTD24／ABS 3*-4* 頂尖商管期刊（AMJ、SMJ、JOM、JFE、JCF、CGIR）匿名審查委員，對完整論文草稿或投稿版本產出正式審稿報告（Summary of contribution／Major concerns／Minor issues／Questions to…
Generate Red Hat quarterly connection reports by aggregating accomplishments from Jira, GitHub, GitLab, Google Workspace (Docs, Slides, Calendar), and other sources into a…
Use when targeting Quarterly Journal of Economics (QJE) or deciding whether an economics manuscript fits this venue.
Close a working session by reflecting on outcomes and feeding structured data to CLI. CLI does all writes atomically; skill does inference reflection.
Use when targeting RAND Journal of Economics or deciding whether an industrial-organization manuscript fits this venue.
Cross-agent skills for Rarefriend personal CRM — search contacts, LinkedIn network, Google Calendar, Google Contacts, Microsoft Outlook email and calendar.
Reading Log — Reading Log — track books & reading habits. Personal daily-use tool for tracking and organizing your life. Use when you need Reading Log capabilities.
Create recurring focus time blocks on Google Calendar to protect deep work hours. — from ShadowTag-v2/shadowtagai-monorepo-v2
Query Google Calendar free/busy status for multiple users to find a meeting slot. — from ShadowTag-v2/shadowtagai-monorepo-v2
Orchestrate structured reflection — update target artifacts with learnings, distill knowledge across hypotheses, and maintain INDEX.md
Pattern for producing quality reflections after completing work. Required for all agent outputs.
Standalone routine skill for interval-triggered scheduled checks. Runs one due check, gates findings through reflection-judge + proposal-triage, applies state, and logs.
Guide an end-of-session reflection to capture learnings and feelings. Use when finishing a work session, after completing a challenging task, when wanting to consolidate what was…
個人のふりかえりを対話で伴走するコーチスキル。KPT（Keep/Problem/Try）を 「事象評価の4象限（価値×蓋然性）」と「根本的な帰属の誤り」というレンズで再解釈し、 成功を能力に紐付けすぎ／失敗を状況に紐付けすぎる認知バイアスを矯正しながら、 学習の指向性（偶然を実力に変える水平方向、行動を改善する垂直方向）を引き出す。…
Maintain a reflection practice — daily, weekly, quarterly — that turns experience into nameable, retrievable lessons.
Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them
Call a C# method by reflection — including private methods. Requires a method schema obtained via 'reflection-method-find'.
Find C# methods across every loaded assembly by name / type / parameters — including private methods.
Forward-looking hardware refresh planning: combining warranty expiration, EOL/EOS timing, and device age from whatever RMM and documentation platforms are connected into…
Build a fully-interactive 3D character-selector experience powered entirely by `vg generate`. Generates stylized characters (FLUX.2 / GPT-Image-2), rigged animated GLBs (Meshy…
Turn a shortlist into a conflict-free day-by-day calendar once AWS publishes session times, accounting for Las Vegas walking and shuttle time between venues.
Schedule future reminders (subscriptions, renewals, one-off dates) via Calendar or email — finish the install, do not ask the user to import files.
The reflection and iterative improvement layer, managing project and session retrospectives.
Review and maintain the knowledge base — find stale entries, orphan entries without connections, missing links between related entries, and generate topic summaries.
Use when conducting sprint retrospectives, project post-mortems, weekly reviews, quarterly reflections, after-action reviews (AARs), team health checks, process improvement…
Mid-conversation reflection skill that pauses execution and zooms out from detail-mode to honestly reassess direction, assumptions, and bias.
Use when deciding what belongs in the journal-hosted Internet Appendix vs. the main paper for a The Review of Financial Studies (RFS) manuscript, and how to structure it.
Use when planning an RSS (Robotics: Science and Systems) campaign end to end — the late-January abstract/paper/supplement cascade, the invited-rebuttal window, late-April…
Use when an author asks "which journal should I send this to?" or needs the best resubmission target after a reject.
Use when choosing between submission sequences rather than between single venues — "should I try the top journal first, or start one rung down?", or when a tenure/job-market clock…
Use after a rejection, or when switching target journals, to turn a manuscript framed for one venue into one framed for another.
Executes a 'focus on OBJ' action on a specific object based on the outcome of a prior conditional evaluation.
When the user sends a screenshot via Telegram, parse it using Gemini (fast, default) with automatic Claude fallback when confidence is low.
Orchestrates a professional Git commit workflow including hygiene checks, documentation parity (SDD), project state tracking (CHANGELOG, TODO, Session Memos), and post-commit…
Ground a sizing estimate in this repo's ACTUAL recent git throughput (commits/day, and merges-as-PRs/day) instead of "this feels like weeks".
Checks recurring and event-based secretarial, governance, register, meeting, beneficial-ownership, share-capital, accounts, audit, charge, director, key-managerial-personnel, and…
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently.
Use after producing a deliverable and before handoff to run a fixed-rubric self-critique and revise cycle. Reduces hallucination and drift.
Read prose sequentially with structured reflections to simulate the reading experience
Access Jewish calendar data and Shabbat times via Hebcal API. Use when building apps with Shabbat times, Jewish holidays, Hebrew dates, or Zmanim.
Use when targeting 《上海经济研究》(Shanghai Journal of Economics — 上海社会科学院经济研究所主办的经济学月刊, 1982 年创刊, CSSCI) or deciding whether a Chinese econ manuscript fits this venue.
A philosophy library for AI agents. Browse books, read chunk by chunk, share reflections, and engage with other AI minds.
Use when targeting SIAM Journal on Computing (SICOMP) or deciding whether a theoretical-computer-science manuscript fits this foundational algorithms-and-complexity venue.
Use to model the SIGGRAPH / SIGGRAPH Asia Technical Papers review pipeline and calibrate expectations, covering the single 6-point score scale, the primary/secondary/tertiary…
Use when auditing an ACM SIGGRAPH / SIGGRAPH Asia Technical Papers submission for Linklings readiness, covering the two-step form-then-upload deadline, the acmart (>=2.16) format…
Use before committing a project to SIGGRAPH / SIGGRAPH Asia / TOG, to decide whether the contribution is graphics-shaped and which venue and track fit, routing among SIGGRAPH,…
Use when planning a SIGMOD project calendar under the PACMMOD round system, covering round selection and hopping, backward planning from abstract and paper cutoffs, the feedback…