takt-task-builder
TAKTのtasks.yaml（タスクメタデータ）とタスクディレクトリ（.takt/tasks/{slug}/order.md）の 作成・編集を支援するスキル。TaskRecordスキーマに準拠したYAMLエントリの生成、 order.mdタスク仕様書の作成、ステータス遷移ルールの検証を行う。 references/taktにあるtaskスキーマ定義・ドキュメントを参照資料として活用する。 トリガー：「タスクを追加」「tasks.yamlを編集」「taktタスクを作成」 「タスク仕様書を書く」「order.mdを作成」「takt task」「タスクを定義」 「pendingタスクを追加」「GitHub Issueからタスク作成」
instrument-feature-flags
Add PostHog feature flags to gate new functionality. Use after implementing features or reviewing PRs to ensure safe rollouts with feature flag controls. Also handles initial PostHog SDK setup if not yet installed.
skill-name
One-sentence description of what this skill does and when to use it.
axiomatic-semantics
Define program meaning through logical assertions and proof rules (Hoare logic).
relational-parametricity-prover
Proves relational parametricity. Use when: (1) Proving abstraction boundaries, (2) Reasoning about polymorphism, (3) Free theorems.
pre-mortem
Imagine failure first to surface guardrails and feature mitigations.
geomaster
Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), vector and raster data operations, spatial statistics, point cloud processing, network analysis, and 7 programming languages (Python, R, Julia, JavaScript, C++, Java, Go) with 500+ code examples. Use for remote sensing workflows, GIS analysis, spatial ML, Earth observation data processing, terrain analysis, hydrological modeling, marine spatial analysis, atmospheric science, and any geospatial computation task.
garbage-collector-implementer
Implements tracing garbage collectors. Use when: (1) Building language runtimes, (2) Learning memory management, (3) Optimizing memory allocation.
test-battery
Fire-and-forget orchestrator test battery. Interactive wizard sets up a cron-driven orchestrator pipeline, triggers the first tick, and exits. Use '/gobby test-battery cleanup' to finalize after completion.
bubbaloop-physical-ai
Manage physical sensors, cameras, and actuators via the bubbaloop skill runtime. Query real-time sensor data, control node lifecycle, and monitor hardware health.
detectability-assessment
Assess whether infringement of proposed patent claims can be detected in products. Use when the user wants to evaluate claim enforceability or detectability.
contextual-equivalence
A skill for proving contextual equivalence between programs using operational semantics, bisimulation, and related techniques.
interprocedural-analysis
A skill for analyzing programs across function/procedure boundaries, enabling whole-program analysis.
bisimulation-checker
Checks bisimulation for process calculi. Use when: (1) Proving equivalence, (2) Compiler optimization, (3) Protocol verification.
notte-browser
Command-line interface for browser automation, web scraping, and AI-powered web interactions using the notte.cc platform.
comfyclaw
Run ComfyUI workflows via CLI. Use --list to discover workflows, --describe to see editable parameters (with live server values), --run to execute with --set @tag overrides, and --inventory to discover available models, LoRAs, and VAEs. No need to read workflow files directly.
playwright
Browser automation via Playwright CLI. Use when asked to test, screenshot, interact with, or automate a web page.
wave-ctx-security
Domain context for Three-layer defense system — permission enforcement (deny-first tool access control), input sanitization (prompt injection detection, risk scoring), path validation (traversal prevention, symlink rejection, Unicode homograph detection), sandbox isolation (Docker with full hardening, bubblewrap via Nix), credential scrubbing in audit logs, and curated subprocess environments.
