法律
法律文档生成与合规
gcp-audit-logs
BagelHole
Configure GCP Cloud Audit Logs for compliance. Set up log routing and BigQuery analysis. Use when auditing GCP activity.
constitution-enforcer
nahisaho
Validates compliance with 9 Constitutional Articles and Phase -1 Gates before implementation. Trigger terms: constitution, governance, compliance, validation, constitutional compliance, Phase -1 Gates, simplicity gate, anti-abstraction gate, test-first, library-first, EARS compliance, governance validation, constitutional audit, compliance check, gate validation. Enforces all 9 Constitutional Articles with automated validation: - Article I: Library-First Principle - Article II: CLI Interface Mandate - Article III: Test-First Imperative - Article IV: EARS Requirements Format - Article V: Traceability Mandate - Article VI: Project Memory - Article VII: Simplicity Gate - Article VIII: Anti-Abstraction Gate - Article IX: Integration-First Testing Runs Phase -1 Gates before any implementation begins. Use when: validating project governance, checking constitutional compliance, or enforcing quality gates before implementation.
agent-memory-discipline
davepoon
"Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service."
brain-in-the-fish
fabio-rovai
Universal document evaluation engine — evaluate any document against any criteria using cognitively-modelled AI agents with ontology-grounded scoring
hiring
whawkinsiv
"Use this skill when the user needs to hire a developer, find a technical contractor, vet engineering talent, manage freelancers, write a job brief, decide between hiring and contracting, or bring on their first technical team member. Covers contractor sourcing, vetting, management, and the founder-developer working relationship for non-technical founders."
legal
whawkinsiv
"Use this skill when the user needs to form a business entity, choose between LLC and C-Corp, create Terms of Service, write a Privacy Policy, or handle legal compliance. Covers entity selection, legal documents, contracts, and compliance for solo-founded SaaS."
next-feature
eas4ai
After a commitment is Done, take the waiting items or a new request, trace and cite each change's blast radius, revise or add Draft requirements with the developer, and run the shared spec-phase tail to the next start. Runs from Done only.
internal-comms
Prat011
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
email-best-practices
novuhq
Use when building email features, emails going to spam, high bounce rates, setting up SPF/DKIM/DMARC authentication, implementing email capture, ensuring compliance (CAN-SPAM, GDPR, CASL), handling webhooks, retry logic, or deciding transactional vs marketing.
wcag-accessibility-audit
mastepanoski
Comprehensive web accessibility audit using WCAG 2.1/2.2 guidelines. Evaluate compliance across 4 POUR principles (Perceivable, Operable, Understandable, Robust) with A, AA, AAA conformance levels.
guided-goal
davepoon
Turn a rough objective into a bounded, verifiable completion contract, confirm it, then execute it with a finite attempt cap. Use when the user wants autonomous work but the outcome, proof, scope, or stopping point is still vague.
feedback
davepoon
Turn post-task feedback—even blunt or angry feedback—into an evidence-based, approval-gated improvement plan for the agent/user workflow. Use after agent work goes wrong, misses expectations, creates friction, or should improve in future. Never mutate during the feedback turn.
fastai
G1Joshi
fast.ai deep learning library. Use for practical deep learning.
know-your-customer
JoelLewis
"KYC requirements: CIP, CDD, beneficial ownership, essential facts, customer profiling, ongoing monitoring, enhanced due diligence."
Modernizing Apache Beam DoFns
apache
Apache Beam is a unified programming model for Batch and Streaming data processing.
adding-new-metadata
apache
Guide on how to add and propagate new metadata fields in Apache Beam's WindowedValue, extending protos, windmill persistence, and runner interfaces to avoid metadata loss.
gentle-ai-skill-registry
Gentleman-Programming
"Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path."
lemur-strategy
Senpi-ai
LEMUR v1.0.0 — Pre-IPO Perpetual (IPOP) trend follower on Hyperliquid XYZ. Auto-discovers IPOPs via the trade.xyz funding signature (1% funding multiplier = ~100x smaller funding rates) + leverage cap (≤5x pre-listing). Today: xyz:SPCX. Auto-expands when trade.xyz lists more IPOPs. Long OR short on 4h trend + Smart Money agreement. Moderate DSL — Discovery Bounds throttle velocity so positions don't snap as fast as normal perps.
cuckoo-strategy
Senpi-ai
CUCKOO v1.0.0 — Copy-the-Copiers (meta-strategy follower). Auto-discovers the top strategies by realized performance (discovery_get_top_strategies), pulls each one's current positions, and trades the asset + direction the top performers agree on most — performance-weighted, so a stronger strategy gets more say (capped so one outlier can't dominate). Because the strategies it follows are themselves copy/algo strategies, Cuckoo copies the copiers. Distinct from Remora (operator-picked whales) and the individual trader- followers. NEW archetype #14. Let-winners-run DSL with a staleness cap.
hawk-strategy
Senpi-ai
HAWK v1.0.0 — 4h Breakout Buyer / Breakdown Seller. LONG when price breaks above the 7-day high AND Senpi Smart-Money is > 55% long. SHORT when price breaks below the 7-day low AND SM is > 55% short. Universe: BTC, ETH, SOL. Asymmetric DSL — Phase 1 max_loss 8% (failed breakouts get cut fast) but Phase 2 wide "let winners run" ladder (T0 +10% / lock 0); a real breakout can run far. hard_timeout 24h.
jaguar-strategy
Senpi-ai
JAGUAR v4.0.0 — Striker (rank-jump detector), senpi_runtime_helpers migration. Plumbing-only flip from openclaw-CLI subprocess + mcporter subprocess + cron-driven self-executing scanner to in-process SenpiClient + long-lived producer_daemon + helpers-native push_signal. Thesis preserved verbatim from v3.7: violent FIRST_JUMP signals, rank-jump ≥ 10, MIN_SCORE 9, conviction-scaled leverage (10x apex / 7x conviction), 15m velocity hard gate, $3M day-notional liquidity floor, XYZ ban, one-amazing-trade-per-day discipline. Risk policy: max 3 entries/day when day is RED, unlimited when GREEN (cap losers, ride winners).
subtree-upstream-governance
hushh-labs
Use when changing optional-mirror coordination, subtree sync policy, or maintainer-only subtree governance between consent-protocol and hushh-research.
agent-orchestration-governance
hushh-labs
Use when changing repo-scoped Codex custom agents, subagent concurrency or depth, delegation policy, or handoff verification rules in hushh-research.
backend-runtime-governance
hushh-labs
Use when changing backend route placement, service boundaries, runtime ownership, or backend docs/tests alignment.