分析
分析、报表与可视化
spec-execute-plan
nu1nux
Review an implementation plan and execute tasks in batches with checkpoints and reporting.
image-routing
8-Sync-Dev
Use this skill on EVERY read request AND before dumping large context, to decide between text and image representation. Apply whenever the AI is about to open a PDF, screenshot a URL, review a UI, inspect a long git diff, process diagrams, OR dump a big graph / call-tree / dependency map as text. First self-check your own modality (can you see images?), then consult the decision table. Picking wrong wastes tokens — but image is NOT always cheaper (see the honest economics below).
ui
MGallo-Code
Michael's UI workflow and rules. Use for any change someone can see (building, changing, mocking or reviewing a UI, page, component, review page, chart or rendered document), from the start of the work through to calling it done.
gen-ctx-kline
samuerio
"Generate multi-symbol context K-line charts at a target timestamp and report output artifacts."
dry-ssot-text
YasuakiOmokawa
Consolidates duplicated reader-facing procedures when a canonical document and in-scope documents are identified, while preserving audience-specific differences.
codex-completion-report
CatPope
Codex가 코드 구현·수정·테스트·논문 재현 같은 실무 작업을 완료할 때마다 로컬 완료 보고서를 작성한다. 사용자가 별도로 "보고서"라고 말하지 않아도, 완료라고 보고할 독립 작업 단위가 생기면 적용한다.
Visualization & Interpretability
sovr610
This skill should be used when the user asks to "visualize activations", "plot spike rasters", "show attention heatmaps", "visualize workspace", "plot reasoning traces", "create t-SNE embeddings", "interpret model decisions", "visualize HTM patterns", "show neuromodulator levels", "plot training curves", "create activation maps", "visualize feature maps", "explain predictions", "debug model behavior visually", or needs guidance on visualization, interpretability, or explainability tooling for the brain_ai system.
conversation-summary
SjB
Save the current conversation as a comprehensive report note in your Obsidian vault, following OKF v0.1 conventions.
recipe-diagrams
SjB
"Recipe diagrams: convert any recipe into a high-resolution Cooking for Engineers-style PNG process-flow table with aligned ingredient streams, preparation branches, joins, temperatures, timings, and finish steps. Use when the user asks for a recipe diagram."
gonol-build
The-Interdependency
Cross-repository construction, review, replay, and continuation discipline for gonols. Load this when realizing gonol or affixiation geometry in UCNS; when constructing character, word, morphology, definition, punctuation-function, or recursive gonols in EDCM; when deciding whether a relation belongs inside a gonol; or when promoting a completed gonol to atomic participation at another scale. Do not load for unrelated geometry, ordinary prose editing, or EDCM measurement that consumes already-closed gonols without changing their construction. Resolve METAPAT semantic authority, UCNS geometric authority, and EDCM text-domain authority separately; never restore historical gonal-morphology, omega/phi/psi, bone/flesh, or carrier-LCM language rules.
structured-delivery
janjaszczak
Provide structured outputs (plan/report/checklist/table) optimized for readability and reuse. Use when user requests a plan, report, checklist, template, or when high-risk requires explicit verification steps.
wake
polycode-public
Come out of cool-down and resume normal work. Thin by design; the revival notes live beside the rules they undo, in the cool-down skill. Invoke when the operator lifts cool-down in their own words.
factset-earnings-insight-pdf-extractor
hulkbai-beep
Convert one or more weekly FactSet Earnings Insight PDFs into correctness-first, normalized, validated, observation-traceable JSON snapshots and a historical SQLite database with typed Phase 3 views. Use after Phase 1 downloads new Earnings Insight PDFs, or when backfilling, validating, rebuilding, or reprocessing local FactSet Earnings Insight files. Do not use for downloading PDFs, market-regime scoring, investment recommendations, portfolio construction, or dashboards.
deep-research
kangnam7654
"Use when the user needs thorough research on a topic — technology comparisons, trend analysis, competitor research, best practices survey, or any question requiring multiple sources. Produces a structured report with citations.\n\nExamples:\n- \"/deep-research React vs Vue 2025\" → Launch deep research on framework comparison\n- \"이 기술 스택 조사해줘\" → Launch deep research\n- \"경쟁사 분석 해줘\" → Launch deep research on competitors"
improve-codebase-architecture
possibilities
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
generate-analytics-reports
olakai-ai
Generate analytics reports from Olakai data using CLI commands. AUTO-INVOKE when user wants: usage summaries, KPI trends, risk analysis, ROI reports, efficiency metrics, agent comparisons, token usage reports, cost analysis, compliance reports, or any analytics without using the web dashboard. TRIGGER KEYWORDS: olakai, analytics, reports, usage summary, KPI trends, risk analysis, ROI, efficiency, agent comparison, token usage, cost analysis, metrics report, dashboard data, CLI analytics, terminal report, compliance, usage report, event summary, performance metrics, AI usage stats. DO NOT load for: setting up monitoring (use olakai-add-monitoring), troubleshooting (use olakai-troubleshoot), or creating new agents (use olakai-create-agent).
tooljoy-us-lite
zionLyl
"🔧 ToolJoy US Lite — Free real-time quotes(yfinance) + basic technicals(RSI/MACD/SMA50)."
repo-issue-triage
spboyer
Automate GitHub issue and PR triage by cross-referencing open issues against pending PRs, merged PRs, and the current main branch to produce an actionable report with close/keep recommendations. Includes PR health monitoring. USE FOR: triage issues, issue checkup, PR status, close stale issues, issue audit, what can we close, outstanding issues, issue report, cross-reference PRs and issues, repo health check, sprint planning. DO NOT USE FOR: creating issues (use GitHub directly), fixing bugs (use coding skills), or PR code review (use code-review agent).
html-comms
crodris
Readable HTML documents about the work, published to a private link. Use when the user wants a plan, spec, write-up, findings, summary, report, comparison, or set of UI mocks to read outside the terminal, even when the word "plan" never comes up, or says "HTML" with no other context. Not for HTML that ships in the product.
stack-update
The-Interdependency
Fail-closed update protocol for The-Interdependency/stack. Load this when a stack change adds, moves, extracts, graduates, renames, removes, or changes the authority, relation, source identity, or placement of a participant, research workspace, libs pin, BASE record, stack manifest entry, or architecture description; when stack-manifest.json, STACK_MANIFEST.md, README.md, or research BASE.json files may drift from one another; or when validating that a structural stack change is complete before commit or merge.
line-chart-generator
zxhfighter
Generate line charts and time-series visualizations using matplotlib. Use when users need to create line charts for price trends, stock data, performance metrics, or any time-series data. Supports annotations, reference lines, and customization of chart dimensions.
react-vite
Alicoder001
React + Vite SPA development patterns including project setup, configuration, and optimization. Use for building single-page applications with Vite bundler.
product-changelog
nachopalmeri
"Product changelog and release notes that users actually read. Covers categorization, user-facing language, visuals, and distribution. Use for: release notes, changelogs, product updates, feature announcements, versioning. Triggers: changelog, release notes, product update, version notes, what's new, feature announcement, product changelog, update log, release announcement, version release, product release, ship notes"
prompt-evaluator
Sunhao25
Comprehensive evaluation framework for system prompts and AI assistant prompts.