Comentaris
Comentaris i anotacions del codi
portfolio-analyst
Kosmos-7
Analyste personnel pour décisions d'investissement. Score consistant des titres (qualité + valorisation + timing + analystes, scoring v3), discipline de vente anti-disposition, frameworks de décision (pre-mortem, second-level thinking, base rates), détection de biais cognitifs. Pour questions du type "dois-je acheter X", "j'hésite sur Y", "le marché va...", "j'ai vendu trop tôt", "fais-moi un point sur mon portefeuille". Triggers FR/EN multiples — voir section dédiée.
coding-standards
Sylla-BV
This skill should be used when the user asks about "Python coding standards", "Python code style", "type hints", "type annotations", "Optional vs union", "T None", "mypy", "black", "isort", "flake8", "ruff", "Pydantic models", "ConfigDict", "async patterns", "asyncio", "structlog", "error handling in Python", "Python naming conventions", "snake_case", "reviewing a Python PR", "does this pass Python code review", "BaseHarvester", "Dramatiq actors", "pydantic-settings", "pytest conventions", or wants to know whether code follows Sylla's Python data-engine repository standards.
academic-paper
lovits
"12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, audit my rebuttal, check my response draft, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見, 評估回覆, 논문 작성, 초록 작성, 논문 수정, 논문 계획을 도와줘, 심사 의견 반영, 답변서 점검, AI 사용 고지."
explain-diff
alex-jordan547
"Create a rich self-contained HTML explanation of a code change, diff, branch, commit, PR, or worker implementation. Use when the user asks to explain code changes, wants to understand what an agent changed, needs a reviewable handoff artifact, or when an orchestrator/worker is asked to invoke /explain-diff for a substantial change."
dependabot-merge
shoji9x9
Dependabot が作成した PR のレビューとマージを gh で標準化するスキル。PR URL / PR 番号で 1 件、--all または無指定で open な全 Dependabot PR を対象にする。CI 成功の確認 → 更新内容（changelog/release notes）からマージ影響の確認 → 判断を PR コメントに記録 → 問題なければマージ、までを進める。特に 0.x（<1.0）依存はマイナー更新でも破壊的変更があり得るため影響を確認してから扱う。「Dependabot の PR をマージして」「依存更新 PR を確認してマージ」「dependabot-merge」「dependabot の PR を全部見て」や、--all を伴う依頼で必ず発動する。依存更新 PR を 1 件ずつ影響判断してからマージする。
feishu-inout
kristencacogenic360
Read/write Feishu/Lark cloud documents, send/search messages, manage calendar/meetings, operate bitable (multi-dimensional tables), and manage group chats via the official Remote MCP service and Open APIs. Works with Claude Code, Cursor, Codex, OpenCode, OpenClaw, and other AI coding agents. Trigger this skill when the user mentions Feishu, Lark, cloud docs, read/search/create documents, messaging, sending messages, meeting, calendar, bitable, multi-dimensional table, 多维表格, 日历, 会议, create group, 创建群, or provides a Feishu/Lark document URL.
explaining-code
odewahn
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"
orchestrator-dispatch-loop
simnova
The CEO-side board loop — plant a RED, probe it, commit, dispatch, verify, integrate, close. Exact signatures and the traps that cost real time. Read before dispatching or harvesting a slice; the worker-side contract is delegated-worker-contract.
mission-control
ggaegule-commits
Kanban-style task management dashboard for AI assistants. Manage tasks via CLI or dashboard UI. Use when user mentions tasks, kanban, task board, mission control, or wants to track work items with status columns (backlog, in progress, review, done).
secpal-pr-review
SecPal
Process completed review feedback for one named SecPal repository and pull request after an explicit remediation request, or handle explicitly named fixed-thread resolution-only requests after the findings were validated, committed, and pushed. Do not use for generic review, PR creation, review requests, CI-only debugging, ordinary implementation, or merge-only work.
codebase-guard
0xlic
"Identify, use, and maintain guard: comments in a codebase. Use when an agent reads guard comments while exploring code, when a user correction after model misunderstanding should become a trusted code fact, or when existing guard facts conflict with code changes or user requirements."
ponytail
SnipeBoss
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.
incident-response
OldBoy405
How this team handles a production incident issue — what to establish before proposing a fix, and what an agent may and may not do on its own.
data-visualization
nachopalmeri
"Data visualization with chart selection, color theory, and annotation best practices. Covers chart types (bar, line, scatter, heatmap), axes rules, and storytelling with data. Use for: charts, graphs, dashboards, reports, presentations, infographics, data stories. Triggers: data visualization, chart, graph, data chart, bar chart, line chart, scatter plot, data viz, visualization, dashboard chart, infographic data, data presentation, chart design, plot, heatmap, pie chart alternative"
cleanup
YashuLanki
Use when asked to clean up the repo — remove dead files, folders, docs, config constants, imports, or stale doc sections left behind by earlier work. Also for "what's dead in here?", "tidy this up", or after a large refactor.
garrul-cli
adbertram
Use this skill for service operations only. DO NOT use this skill for CLI implementation lifecycle work such as creating, testing, updating, troubleshooting, validating, removing, or documenting the CLI tool itself; delegate those tasks to cli-tool-expert. MANDATORY: Execute Garrul operations using the garrul CLI tool. CLI interface for Garrul. Triggers: garrul, garrul cli
Music Listener
naohainezha
If the user is sharing their own music, be encouraging but honest.
session-closeout
lexijamesesq
Triggers when the user says "Close out this session for [project]", "Session closeout", "Close this session", or similar closeout phrases. Also triggers on "/session-closeout".
gaia-triage
gaia-research
Triage the Gaia issue backlog and skill-batch intake queue. Use this skill when someone asks to: "triage issues", "clean up the issue tracker", "review the backlog", "close stale issues", "process the intake queue", "review skill-batches", "evaluate draft skill proposals", "approve or reject pending skills", "is this issue still valid?", "what's clogging the backlog?", "run a triage pass", or /gaia-triage. Covers two workstreams: (1) GitHub issue lifecycle — identifying resolved, stale, or need-more-info issues and acting on them via gh CLI; (2) skill-batch intake — evaluating draft proposals in registry-for-review/skill-batches/ and routing them toward promotion or rejection. This is the gatekeeping step before new skills enter the canonical registry; and (3) a cross-repo triage sweep — sizing, P0-P4 prioritization, umbrella/epic synthesis, and assignment across every gaia-research org repo, on the one headquarters tracker.
Morning Brief
Atrium-Hermes
Priority-driven daily briefing — the 3 things to focus on today, why now, and what moved
code-review-and-quality
8-Sync-Dev
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
unreal-shots-and-look
michaelkocandrle
Visual verification and look tuning of the packaged Unreal game - Tools/Shots.ps1 screenshot presets (Tools/Shots/.json, shot fields, -Package/-Keep/-Width 1920 -Height 1080), contact sheets, measure_look.py / measure_flicker.py, live console tuning (space.Post, space.Sun, space.Sky, space.ShipMat, space.Kit, space.KitLight), scene light/grade/exposure, performance measurement (perf_* presets, stat unit, Unreal Insights) and UE 5.8 rendering traps (Nanite+TSR smear, translucency sorting, TSR ghosting, Custom node, auto exposure). Load whenever you change anything visible, need screenshots, tune lighting/materials/post process, or measure FPS.
sflow-epic-publish
ashokraj2011
Preview and apply the exact approved Jira and Git Story publication plan with lineage properties, comments, specifications, and branch receipts.
ponytail
8-Sync-Dev
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.