shwetank

shwetank/bettersense

Plugin Claude Code

Opinionated Claude Code skills and agents for AI PMs, Engineering Managers, TPMs, and senior ICs leading without authority.

shwetank/bettersense

Instructions file

Claude Code instructions for shwetank/bettersense, covering claude.md, what this repo is, repo structure, plugin file formats and installation mechanics.

shwetank/bettersense

Plugin Claude Code

Opinionated Claude Code skills + agents for AI PMs, engineering managers, TPMs, and senior ICs. Run /bettersense:start to get oriented.

shwetank/bettersense

Agent

Use when an AI prototype is being scaled toward production and the user needs reliability, cost-efficiency, and clean separation between probabilistic and deterministic logic. Trigger for system design, guardrail design, fallback strategy, or when the question is "how do we run this in production?".

shwetank/bettersense

Agent

Use when coaching individual contributors on career development, growth planning, and skill-building — particularly for ICs navigating promotion paths, skill gaps, or role transitions. Distinct from report-career-architect (which builds growth plans for the user's direct reports) and coaching-mode (which is for…

shwetank/bettersense

Agent

Use when translating metrics, data, or analytical findings into a compelling narrative for stakeholders. Trigger when the user has data but struggles to frame it into a story, when presenting results to non-technical audiences, or when metrics need context and meaning. Distinct from the-translator (which focuses on…

shwetank/bettersense

Agent

Use when a PM or team needs structured opportunity discovery before committing to build — separating validated user needs from assumed ones, mapping evidence to gaps, and reaching informed conviction on what's worth pursuing. Trigger when the user says "we're thinking about building X", "users keep asking for Y", "I…

shwetank/bettersense

Agent

Use when the user needs to design an evaluation system for an LLM or ML feature — golden datasets, metrics, LLM-as-judge rubrics, regression suites, or production sampling strategies. Trigger when the question is "how do I measure if this is good?" or when shipping an AI feature without a clear eval in place.

shwetank/bettersense

Agent

Use to write internal or external explanations of how an AI feature works — sales enablement, customer-facing help docs, exec briefings, support runbooks, FAQ, security/legal review materials. Trigger when the user says "I need to explain X to [audience]", "write a how-it-works doc", "draft an FAQ for…", or when…

shwetank/bettersense

Agent

Use when planning a go-to-market launch for an AI feature or product — sequencing, audience segmentation, messaging calibration, and launch readiness gates. Trigger when the user asks "how do we launch this?", "what's our GTM strategy for the AI feature?", or needs a phased rollout plan that accounts for AI-specific…

shwetank/bettersense

Agent

Use during or after an AI-feature incident — model regression, sudden hallucination spike, eval drop, guardrail bypass, cost or latency anomaly, customer-reported wrong answer that escalated. Triggers on "we have a regression in…", "the model started…", "users are reporting…", or post-incident reviews. Complements the…

shwetank/bettersense

Agent

Use after any significant engineering incident to facilitate a blameless postmortem — timeline reconstruction, root cause analysis, systemic vs individual distinction, and action item discipline. Trigger when the user says "we had an incident", "we need to run a postmortem", "the outage is over — now what?", or "how…

shwetank/bettersense

Agent

Use for multi-team, multi-month technical program management — dependency mapping across teams, risk gates per launch phase, adopting orphaned cross-team problems, designing rollout plans with go/no-go criteria, drafting status comms for different audiences, framing escalations. Trigger when the user is running a…

shwetank/bettersense

Agent

Use to review production prompts, system prompts, or agent instructions the way a senior engineer reviews code. Trigger when the user shares a prompt and asks "is this good?", when iterating on a struggling LLM feature, or proactively before any prompt ships to production.

shwetank/bettersense

Agent

Use proactively before launch and during maintenance of an AI feature to find failure modes the user hasn't thought of. Trigger when reviewing prompts, agent tool wiring, or LLM-facing endpoints for prompt injection, data exfiltration, jailbreaks, or out-of-distribution failures.

shwetank/bettersense

Agent

Use proactively in early-stage AI product discovery when the user has a vague or ambiguous problem and hasn't yet decided whether AI is the right solution. Trigger phrases include "we should add AI to…", "users are complaining about…", or any new feature pitch where the problem is fuzzier than the proposed solution.

shwetank/bettersense

Agent

Use to cluster raw qualitative data — interview notes, support tickets, NPS verbatims, sales call transcripts, user feedback — into themes, jobs-to-be-done, and prioritized insights. Trigger when the user dumps unstructured user-voice data and asks "what does this tell us?" or "what should we do with this?".

shwetank/bettersense

Agent

Use when facilitating a team retrospective or post-mortem after a project, incident, or sprint. Trigger for structured retros that produce action items, not just conversation. Distinct from the-incident-responder (real-time incident management) and the-postmortem-facilitator (blameless postmortem after infrastructure…

shwetank/bettersense

Agent

Use to review engineering RFCs, design docs, technical proposals, or architecture write-ups the way a senior staff engineer would. Trigger when the user shares a doc and asks for a review, when an EM needs a second opinion before approving a proposal from their team, or when the user wants a structured critique before…

shwetank/bettersense

Agent

Use for pre-development feasibility and prototyping of an AI feature. Trigger when the user wants to validate whether an LLM or ML approach actually works before committing engineering resources — building rapid prototypes, golden datasets, or eval baselines.

shwetank/bettersense

Agent

Use when a team needs to define reliability targets for a service — SLOs, error budgets, and the monitoring setup that makes those commitments real rather than aspirational. Trigger when the user says "what SLOs should we have for this?", "how do we set reliability targets?", "we need to define our error budget", or…

shwetank/bettersense

Agent

Use when the user has a validated problem and needs to turn it into a written product spec or PRD. Trigger phrases include "draft a PRD for…", "write a spec on…", "I need a one-pager on…", or naturally after the-reducer has produced a Problem Definition. Also use when reviewing an existing spec for gaps.

shwetank/bettersense

Agent

Use for recurring operational status reporting — weekly/monthly status updates, stakeholder updates, leadership reports on an ongoing workstream. Trigger phrases include "help me write my weekly status update", "draft a monthly report for leadership", "what should I put in my stakeholder update?", "status email that…

shwetank/bettersense

Agent

Use when the user needs to convert technical AI results (eval metrics, latency numbers, failure modes, model trade-offs) into business-language updates for executives, stakeholders, or investor demos. Trigger for demo prep, exec summaries, post-incident comms, or when an AI-technical result must land with a…