firatcand

@firatcand source repo

28 skills
0 followers
6 hours ago last updated

▌
Brain · firatcand
Front door to the roster brain — the workspace's shared, append-only Postgres + object-storage memory. Use when the user asks to remember/record/look up team knowledge (competitors, posts, metrics, accounts, people) or to set up the brain. Routes to `roster brain <verb>` (init/doctor/ingest/save/get/event/link/merge/fs/record) and follows the brain-first protocol. Triggers on /brain or when a request is about persistent team knowledge in a roster workspace.

0
installs
▌
Inbox · firatcand
Conversational review of unread decisions in a roster workspace. Lists pending HITL items (roster/<function>/pending/ and <agent>/pending/), shows each in chat, collects approve/reject/defer by reply, and applies each via `roster review --approve/--reject <id>`. No TTY needed — this is the chat-native front door for `roster review`. Triggers on /inbox or when the user asks to review their inbox / pending decisions / HITL items.

0
installs
▌
Tasks · firatcand
Conversational task driver for a roster workspace. Translates natural prompts — what's ready? / work on N / I'm blocked / send for review / mark done / status update — into `roster task` verbs against the user's own tracker board (Notion v1). Never writes the tracker directly; every mutation goes through the CLI's state machine. Triggers on /tasks or when the user asks to list, claim, advance, block, or get a status report on their tracker tasks in a roster workspace.

0
installs
▌
Dreamer · firatcand
Reflection skill. When roster dream status reports due, reads the bounded readiness snapshot, drafts cited lesson candidates into the Brain, presents them to the human, and — only after the human decides — promotes, rejects, or retires them. The approved lesson becomes a file in the agent's playbook. Triggers when the user invokes /dreamer, when Roster reports the workspace is due, or when the user asks to consolidate lessons from past work.

0
installs
▌
Chief Of Staff · firatcand
Workspace maintenance for Roster workspaces. Uses deterministic roster scaffold/validate commands in v2 and quarantined legacy scripts only in v1. Triggers when the user asks to scaffold or audit a roster workspace, or invokes the /chief-of-staff slash command.

0
installs
▌
Second Opinion · firatcand
Get an honest second opinion on any artifact — writing, design docs, product specs, or code — from a DIFFERENT AI model in a fresh process. Builds a review brief and dispatches it via `roster second-opinion` to the codex/gemini/claude CLI (whichever differs from the current host), then renders the structured verdict. Triggers on /second-opinion or when the user asks for another model's take / a cross-model review / fresh eyes on a draft, plan, or diff.

0
installs
▌
Roster Orchestrator · firatcand
Bootstraps roster workspaces. On chat session start, surfaces unread decisions (HITL) as a single banner pointing at /inbox. On a scheduled fire, verifies the schedule is registered, resolves the agent's merged env, dispatches the named agent via the host tool's native subagent primitive, writes a run log + state.md entry, and exits. Reads roster/<function>/schedules.yaml plus pending items at both roster/<function>/pending/ (error class) and <function>/<agent>/pending/ (lesson class). Subscription-billed primitives only — never invokes the Claude CLI in headless print or API modes, nor the Anthropic SDK.

0
installs
▌
Fixture Dreamer · firatcand
Test-only reflection bridge that creates one cited lesson candidate when the fixture's durable status is due.

0
installs
▌
Fixture Docs Search · firatcand bundle
Fictional one-shot stdio JSON-RPC search over an embedded handbook corpus.

0
installs
▌
Fixture Ledger Lookup · firatcand bundle
Fictional command-line lookup over an embedded company ledger snapshot.

0
installs
▌
Roster 350 Fixture Learning Loop · firatcand
Test-only bridge for using controlled search and evidence adapters after interpreting a complete Roster plan.

0
installs
▌
Sorquith Search · firatcand bundle
Fictional one-shot stdio JSON-RPC conversation search over an embedded public-post corpus.

0
installs
▌
Torlvesk Tickets · firatcand bundle
Fictional command-line precedent lookup over an embedded vendor ticket archive.

0
installs
▌
SEO · firatcand bundle
Use when the user wants to get found in Google or AI engines (ChatGPT, Perplexity, AI Overviews) — keyword and content strategy, technical or content SEO audits, schema markup, link building, topical clustering, E-E-A-T, AI citation (AEO), or deciding whether SEO is even the right channel for their startup. Calibrated for early-stage, low-authority sites. Not for paid acquisition or channel-mix/CAC analysis (use channel-expert), or writing the page copy itself (use copywriter-skill).

0
installs
▌
Design · firatcand bundle
Use when a non-designer needs to audit a UI, generate a design spec (spacing, type scale, color tokens, grids), or build brand foundations (logo systems, palette and type pairing, brand guidelines). Covers the visual layer, UX/perceptual critique, and brand identity. For implementing the design in code (React/HTML/CSS), use frontend-design.

0
installs
▌
Devops · firatcand bundle
Use when the user needs to deploy, operate, secure, or scale running infrastructure — cloud architecture (multi-region, VPC, FinOps), CI/CD and deployment strategies, secrets/IAM/supply-chain security, observability and SLO alerting, SRE and incident response, Kubernetes vs ECS and autoscaling, Terraform/Pulumi/CDK, or platform engineering and DORA metrics. Also for generating runbooks, pipeline configs, Terraform modules, or Kubernetes manifests. For choosing the system's architecture or stack before it runs (monolith vs microservices, which database), use software-architect.

0
installs
▌
Pricing · firatcand bundle
Use when a SaaS founder needs to set, audit, or redesign pricing — choosing a value metric, structuring tiers and packaging, setting price points, designing discounts, planning a price increase, or optimizing a pricing page. Also for monetization questions like free-to-paid conversion, expansion revenue, willingness-to-pay research, or per-seat vs usage-based. Not for which acquisition channels to use (use channel-expert) or the wording of the pricing page (use copywriter-skill).

0
installs
▌
Plg Skill · firatcand bundle
Use when a SaaS founder is deciding on or building a product-led growth motion — assessing PLG readiness, choosing freemium vs free trial vs reverse trial, defining activation and PQLs, designing self-serve onboarding and conversion triggers, building viral loops, or setting up PLG metrics (NRG, activation rate, TTV, NDR, CAC payback) and cohort analysis. Also for hybrid product-led-sales design and PLG-vs-sales-led GTM decisions. Not for paid acquisition channel mix (use channel-expert) or the mechanics of price points and tiers (use pricing).

0
installs
▌
Prospecting · firatcand
Use when the user needs to find, prioritize, or engage B2B prospects — defining an ICP, tiering accounts, building or enriching lists, reading buying signals, designing multi-channel cadences, cold calling, LinkedIn outreach, routing inbound leads, or diagnosing weak pipeline generation. Also for live prospecting coaching. Not for closing (use sales-skill), copy (use copywriter-skill), or CAC analysis (use channel-expert).

0
installs
▌
Sales Skill · firatcand bundle
Use when the user is working a B2B SaaS deal from qualified opportunity to closed-won — preparing discovery calls, structuring demos or POCs, handling a specific objection, qualifying with MEDDIC/MEDDPICC/SPICED, building mutual action plans, navigating negotiation or procurement, or reviewing pipeline health, forecast accuracy, and deal velocity. Not for finding or prospecting new leads (use prospecting) or upstream positioning (use product-position).

0
installs
▌
Product Spec · firatcand bundle
Use when the user needs to scope, write, or audit a product spec — a PRD, feature spec, user stories, acceptance criteria, or a "spec this out"/"break this into stories"/"definition of done" request — or wants an existing spec reviewed for gaps and anti-patterns. Triggers whenever a feature idea needs to become structured requirements that align a team on what to build. For the analytics behind success metrics, use data-analysis; for the technical design, use software-architect.

0
installs
▌
Data Analysis · firatcand bundle
Use when the user needs to design, run, or audit product or GTM analytics — metric hierarchies and north stars, funnels, cohort retention, churn, pipeline velocity, forecasting, lead scoring, NRR, A/B tests, or analytical SQL — or uploads a dataset to analyze. Triggers on questions like "why did activation drop", "is this metric meaningful", "review my dashboard", or "what should I measure". For writing the spec that defines a feature's success metrics, use product-spec.

0
installs
▌
Channel Expert · firatcand bundle
Use when a B2B SaaS founder needs to choose, prioritize, or rebalance customer acquisition channels — deciding outbound vs inbound, paid vs PLG, where to put marketing budget, or sanity-checking CAC, LTV:CAC, and payback. Also for channel-specific playbooks (cold email, LinkedIn, paid social, community, partnerships) and channel-mix audits. Not for closing tactics (use sales-skill) or copy (use copywriter-skill).

0
installs
▌
Motion Picture · firatcand bundle
Use when planning, auditing, or speccing a video's motion and visual craft: shot lists, storyboards, color scripts, transitions, easing, kinetic typography, pacing, retention, or animation principles. Triggers: 'video plan', 'shot list', 'storyboard', 'color script', 'motion spec', 'fix the pacing', 'explainer/demo/brand video'. For the spoken words themselves, use script-writer-skill; for in-code UI motion, use frontend-design.

0
installs
▌
Copywriter Skill · firatcand bundle
Use when the user needs to write, rewrite, review, or critique commercial copy meant to drive a reader toward action — landing pages, hero sections, headlines, email (cold outreach, nurture, promo, launch), CTAs, microcopy, product descriptions, value propositions, ads, or taglines. Also for copy audits, clarity checks, conversion reviews, or choosing a framework (AIDA, PAS, BAB, FAB, 4U's). Applies even when the user just says "write me an email" or "review this page." Not for channel/budget strategy (use channel-expert) or pricing structure (use pricing).

0
installs
▌
Product Position · firatcand bundle
Use when a B2B SaaS product needs upstream positioning or messaging clarity — defining who it's for, the category, competitive alternatives, differentiation, value props, strategic narrative, or a messaging hierarchy. Triggers include "my messaging isn't working," "we sound like everyone else," repositioning, or auditing an existing positioning doc. Use before homepage, deck, or sales-narrative work. Not for writing the final copy (use copywriter-skill) or running the sales process (use sales-skill).

0
installs
▌
Software Architect · firatcand bundle
Use when the user is deciding, reviewing, or second-guessing a software architecture or tech-stack choice — monolith vs microservices vs serverless vs event-driven, backend language, database type, caching, CQRS/event sourcing, polyglot, or a migration like Strangler Fig. Triggers on "should I use microservices", "which database", "tech stack for", "system design", or "architecture review". For how to deploy, operate, and scale that design (CI/CD, cloud, Kubernetes, IaC), use devops.

0
installs
▌
Script Writer Skill · firatcand bundle
Use when the deliverable is spoken words to be performed on camera or into a mic: video and podcast scripts, hooks, and CTAs for short-form (TikTok, Reels, Shorts), YouTube long-form, or podcast episodes. Triggers: "write me a reel about X", "I need a hook for my video", "script a 60-second video", "draft a podcast episode", "turn this idea into a script". For motion/timing/shot specs rather than the words, use motion-picture.

0
installs

28 published skills