Productivity

vibesec-advisory Bundle

Use when a result needs source-specific provenance, schema validation, required-field checks, and postcondition checks before the workflow relies on the value.

vibesec-advisory Bundle

Use when AI usage, adoption, enablement, or manager feedback needs to be separated into early-adopter behavior, process friction, workflow fit, and missing redesign evidence.

vibesec-advisory Bundle

Use when event-log exports, process-mining summaries, task-mining notes, tickets, CRM exports, worker observations, or workflow notes need safety review before AI-assisted process redesign.

vibesec-advisory Bundle

Use when a redesigned workflow needs a small pilot, cadence, feedback loop, measurement plan, and expansion gate before broader AI adoption claims.

vibesec-advisory Bundle

Use when a workflow needs explicit answer, retry, clarify, abstain, escalate, and stop states for confidence-based routing.

vibesec-advisory Bundle

Use when a chosen workflow needs a new AI-assisted sequence with explicit human role, allowed inputs, blocked inputs, review gate, and done condition.

vibesec-advisory Bundle

Use when a reusable AI instruction needs its intended task, out-of-scope boundary, users, output contract, allowed inputs, blocked inputs, and approval owner captured before smoke tests are written.

vibesec-advisory Bundle

Use when a failed or risky AI workflow run needs a structured label record before the team updates a Skill, eval, memory item, tool contract, approval gate, or release decision.

vibesec-advisory Bundle

Use when outbound email, LinkedIn, call, or voicemail copy is ready for review against unsupported claims, unsafe personalization, sensitive data, or overpromising.

vibesec-advisory Bundle

Use when a workflow needs a cross-session test that checks whether hostile, stale, low-trust, or unsupported memory can steer future planning, retrieval, tools, or output.

vibesec-advisory Bundle

Use when a reusable Skill needs create, validate, publish, monitor, update, deprecate, or retire decisions after workflow changes.

vibesec-advisory Bundle

Use when valid JSON, schema-conforming structured output, function-call arguments, or tool-call payloads need review before the workflow acts on them.

daemon-blockint-tech Bundle

Expert talent acquisition for end-to-end recruiting operations—workforce planning tie-in, requisition intake, job descriptions and leveling, interview process coordination, candidate experience, offer process coordination, ATS/CRM workflow, hiring manager partnership, recruiting metrics (time-to-fill, pass-through, diversity funnel), agency/RPO management, EVP in hiring, onboarding handoff, and hiring compliance awareness (not legal advice). Use when the user mentions talent acquisition, TA strategy, recruiting process, hiring process, requisition, job description, time to fill, interview loop, candidate experience, ATS workflow, hiring manager, offer process, recruiting metrics, RPO, or full-cycle recruiting—not passive sourcing only (talent-sourcer), interview question banks alone (interview-prep, interview-system-designer), comp modeling (comp-analysis), offer letter legal text (draft-offer), org-wide people strategy (chro-advisor), or employee HR onboarding (people-operations-specialist).

daemon-blockint-tech Bundle

Reframes messages, requirements, metrics, and decisions for organizational audiences—engineering, product, finance, legal, compliance, sales, operations, actuarial, and executive—by detecting jargon, surfacing implicit assumptions, producing dual-audience briefs, RACI-aligned handoffs, owner-tagged meeting actions, technical-to-business and business-to-technical translation, and escalation summaries. Use when translating for engineering, explaining to finance, cross-department bridging, rewriting for executives, business-friendly versions, technical summaries for leadership, inter-team handoffs, department jargon, or dual-audience briefs—not external customer or brand copy (communication-lead), contract redlines (commercial-counsel), full multi-team program execution (technical-program-manager), human-language i18n/l10n product strings, or strategy-only consulting without audience reframing (business-consultant).

unboundcompute Skill

Hunt CRLF injection where untrusted input carrying a carriage return and line feed reaches a response header, a log line, or an outbound email header that does not strip or reject those characters, letting the attacker inject headers, split the message, forge log entries, or add email headers. Use when input flows into a Set-Cookie, Location, or custom response header, into a log written from request data, or into mail headers built from user input. Covers full response splitting into injected content or cache poisoning, header injection, log forging, and email header injection. The untrusted input is the source, the header, log, or email writer is the sink, and the injected line that the consumer treats as new structure is the bug.

unboundcompute Skill

Test a mail setup for sender spoofing that survives authentication: SPF, DKIM, and DMARC records that exist but do not align or enforce, subdomains left unprotected, and the end-of-data desync known as SMTP smuggling, where an inbound and an outbound mail server disagree on where one message ends so a second message with a forged, auth-passing sender is smuggled in. Covers policy present but not enforced, alignment gaps between the envelope and header sender, missing subdomain policy, open relay, and inconsistent message-boundary parsing between hops. Use when auditing a domain's mail authentication or a mail server's boundary handling. The crafted or smuggled message is the source, an accepted spoofed delivery is the sink.

robium-ai Bundle

Nav2 mobile-robot navigation for ROS 2: bringup, behavior trees, costmaps, planner/controller servers, localization (AMCL, slam_toolbox), waypoint following, and tuning. Use when: 'navigation', 'nav2', 'costmap', 'path planning', 'robot won't move to goal', 'localization', 'SLAM', 'AMCL', 'waypoint', or any autonomous mobile robot task. Load after architect selects the ROS nav stack; pairs with ros2 (foundation), gazebo (sim), and visualization (debugging). Not for: manipulation (lerobot) or generic ROS 2 issues (ros2).

robium-ai Skill

Fold the current session's learnings back into the robium skills, on demand. Harvests gotchas from the conversation and any unabsorbed learnings/ files, confirms the list, then edits the robium source checkout: fixes wrong/stale guidance, widens missed trigger surfaces, adds figured-out-from-scratch knowledge, prunes noise, and promotes ✓-verified examples. Use when: a work session surfaced gotchas, frictions, or better methods worth keeping; 'skill-updater', 'update my skills', 'absorb these learnings', 'fold these gotchas into the skills', end of an app-building session with the robium plugin. Runs ONLY on explicit user request — agents surface candidate learnings and offer, never invoke this themselves. Developer workflow — requires a local robium checkout. Not for: authoring a new skill from scratch (skill-author) or building apps (architect).

quantumquirkxyz Skill

A test skill for validating the skill-sandbox workflow.

inbharatai Skill

Compose professional emails for any context — outreach, follow-ups, apologies, negotiations, and announcements.

inbharatai Skill

Create effective meeting agendas — objectives, time boxes, pre-read materials, and decision frameworks.

inbharatai Skill

Write structured meeting minutes — attendance, decisions, action items, parking lot items, and next-meeting prep.

inbharatai Skill

Design Zapier automations — triggers, actions, filters, formatters, and multi-step Zap architectures.

inbharatai Skill

Write engaging email newsletters — hooks, curated content, CTAs, and subject line optimization for high open rates.

m2ai-portfolio Skill

Save a summary of this conversation to the vault. Key decisions, things to remember, next actions. Store in the right folder automatically.

m2ai-portfolio Skill

Reference implementation of a proactive Life Engine -- a time-windowed briefing loop that checks email, calendar, project health, and changelog sources on a recurring schedule. This is a REFERENCE IMPLEMENTATION showing one user's full wiring, not a plug-and-play template. Read the Adaptation Guide at the bottom to build your own.

m2ai-portfolio Bundle

Enforced multi-round planning loop with a stop hook that blocks code execution until the plan survives adversarial review and receives explicit approval. Use when a task is high-stakes enough that a wrong plan is expensive to undo — the stop hook is the "bouncer" that prevents jumping straight to implementation. Trigger phrases: "claudex plan", "enforce planning before coding", "stop hook planning gate", "plan must survive review before I build", "plan-first workflow".

m2ai-portfolio Skill

Custom planning mode that challenges assumptions, asks deep multi-option questions, and explores multiple approaches before converging on a plan. Use when the user says "plan", "let's think through", "help me decide", "sparring planner", "think this through with me", "let's figure out", "what's the best approach", or any task that benefits from structured thinking before execution. Works for coding, content/creative, business/admin, and any domain. This is NOT a rubber-stamp planner — it's a sparring partner.

m2ai-portfolio Bundle

Installs a "bouncer" hook in Claude Code that blocks all file edits until an explicit planning gate is passed. Prevents the common failure of jumping from idea to implementation before the plan has survived adversarial challenge. Use when a task is non-trivial, prior attempts drifted, or the cost of a wrong plan is high. Trigger phrases: "stop me from coding too soon", "add a planning gate", "plan stop hook", "bouncer before I code", "don't let me implement until the plan holds".

mariourquia Bundle

Institutional fund management operations: regulatory compliance monitoring, fee calculations, capital account statements, subscription processing, AML/KYC, Form D filings, LPAC governance, and fund expense ratios. Triggers on 'fund compliance', 'capital account', 'management fee calc', 'LP subscription', 'Form D filing', 'LPAC meeting', 'investor reporting', or when given fund terms, committed capital, and investment activity.

mariourquia Bundle

One paragraph: what the workflow does and when it triggers.

mariourquia Bundle

Site deputy to the property manager. Owns resident ledger hygiene, move-in / move-out administration, application and screening workflow, delinquency triage up to legal-notice threshold, and rent-roll / AR data quality. Operates under the PM's direction and within the segment / form / mode / org overlays loaded by the router.

mariourquia Bundle

Coordinates every step from lease execution to resident in the unit. Confirms move-in readiness, generates document packets per jurisdiction overlay, schedules utility transfers, produces welcome communications, and closes the loop by marking the move-in event and updating occupancy metrics. Routes any reasonable-accommodation signal out of the workflow to a human path.

mariourquia Bundle

Pre-IC packet assembly for each IC cycle. Assembles the docket, pulls each deal's memo and cross-references, tracks IC conditions from prior decisions through to completion, consumes the sensitivity / stress-test output, surfaces comp evidence with freshness flags, and runs an LP capital availability check. The pack is the IC committee's input; the committee owns the decision. The workflow refuses to publish a deal's packet if blocking Dealpath DQ rules are open (`dp_completeness_ic_record`) or if required sensitivity tests are missing. Outputs include the IC packet, the condition-tracking rollup (from prior cycles), and the post-IC condition-log draft ready for minute-keeping.

mariourquia Bundle

Prepares weekly or biweekly construction-meeting packets (agenda, data summary, RFI and submittal log, COs, schedule status, safety) and tracks action items with owners and due dates. Closes the loop by updating status and surfacing stale items.

evolution-foundation Skill

Persistence loop — keep working on a task until it's resolved or until a circuit breaker stops you. Different from /loop (which is time-based) — ralph is iteration-based with state.