Skill rating

Verify a claim before repeating it — the independent-sources test (three citations of one press release is one source), the provenance trace to the original, and the confidence grading that separates

Simulate defending your study or protocol before an ethics committee — the consent-comprehension probe, the vulnerable-participant challenge, the minimal-risk fight, the data-retention question you di

Structure a PM's weekly review and planning session. Use when doing a weekly PM review, writing a weekly update, preparing for Monday planning, or reviewing sprint health. Produces a shareable weekly

Decode a franchise offering before you sign away a decade — the earnings claims and their absence, the territory that is not exclusive, the renewal terms that expire your equity, the mandatory-supplie

Simplify code that works — remove speculative abstraction, dead flexibility, and needless indirection while keeping behaviour identical and verified. Use after a feature lands ('now simplify it'), whe

Clean a messy dataset methodically — the profiling pass that finds what's actually wrong (dupes, format drift, phantom spaces, mixed types), the fix order that doesn't corrupt while correcting, and th

Assesses pre-launch readiness across every function and produces an explicit Go / Conditional Go / No-Go recommendation. Use when preparing for any product or feature launch, running a pre-launch revi

Write the right reply to a customer review — positive, negative, or mixed. Use when asked to respond to a review, reply to a bad/1-star review, handle online reviews, or write review-response template

Read your team's messages the way opposing counsel would in litigation discovery — prevention training that makes communication hygiene visceral. Use when asked how would our Slack look in discovery,

Read your marketing claims, landing page, or ad copy the way a consumer-protection investigator would (FTC/ASA framing) and draft the inquiry letter they could send. Use when asked to check my marketi

Audit a spreadsheet before trusting it — the error hunt (hardcoded overrides, broken ranges, silent unit mixes), the fragility map (what breaks when rows are added), and the load-bearing-formula revie

Audit the beneficiary designations that quietly override wills — the account-by-account sweep, the life-event triggers that make them stale, and the coordination check against actual intentions. Use w

Review a bill of materials for cost, risk, and supply exposure — cost rollup, top-10 cost drivers, single-source and EOL risk, MOQ vs forecast mismatch, cost-down candidates, and tariff/logistics sens

Coach a statement of purpose or personal essay to admission strength — structural diagnosis, specific feedback, and revision plans on YOUR draft; the words stay yours. Use when asked to review my pers

Generate and evaluate names for a product, feature, or release. Use when asked to name a product/feature/company, brainstorm naming options, or choose between name candidates. Produces a shortlist of

Design a scoring rubric and LLM-as-judge prompt to evaluate the quality of an AI feature's output. Use when asked to create an eval rubric, define quality dimensions, build an LLM judge, or decide how

Audit a content library, docs site, or blog for AI-generated filler that's eroding trust and search performance — and triage what to fix, rewrite, or delete. Use when asked to find slop in a content l

Review a pull request or diff like a thoughtful senior engineer — prioritized, kind, and focused on what matters. Use when reviewing code, giving PR feedback, or asked to 'review this change'. Produce

Audit a dataset for the quality problems that silently break analysis — missingness, duplicates, outliers, type and range errors, consistency, and freshness — and produce a prioritised fix list. Use w

Triage an incoming insurance claim: check the coverage trigger against policy wording, band severity and complexity, screen for fraud indicators, set a first-pass reserve range, and route with an SLA.

Explain a contract clause in plain English — what it means, who it favours, the realistic risk, and what to negotiate. Use when asked what a clause means, to decode legal language, explain a term in a

Execute a written plan with discipline — verify each step before advancing, surface deviations instead of improvising around them, and keep a visible execution log. Use when working through a plan (yo

Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define quality metrics for an AI feature, or build a

Stress-test a plan, strategy, PRD, or launch by simulating hostile expert personas who attack it from every angle. Use when asked to red-team, stress-test, pre-mortem, pressure-test, play devil's advo

Diagnose a slow SQL query and produce a concrete optimization plan. Use when asked to optimize SQL, speed up a slow query, reduce a query's cost/scan, fix a timeout, or review a query plan. Produces a

Audit any document against its own sources — every factual claim extracted and graded as evidenced, partially evidenced, unsupported, or contradicted, with the exact source line that supports or fails

Plan a new manager's first 90 days — first-time or new-to-team — as listen/decide/move phases: the 1:1 listening tour with real questions, the early-judgment traps, the quick-wins filter, and the 30/6

Write a clear pull-request description that gets reviewed fast and merged with confidence. Use when opening a PR, summarizing a change for review, or asked to write a PR/merge-request description. Pro

Analyse a finished A/B test and write the readout — the result, whether it's statistically and practically significant, what it means, and the ship/no-ship call. Use when asked to analyse experiment r

Decode HOA covenants (CC&Rs) and the fee structure before you buy into them. Use when someone asks 'what do these HOA rules actually mean', 'decode these CC&Rs', 'is this HOA going to be a problem', o

Decode a job description to find what they actually want beneath the buzzwords. Use when asked to analyse a job description, decode a JD, assess fit for a role, or figure out what a posting really mea

Analyze competitors and create competitive landscape documentation with feature matrices, positioning maps, and strategic recommendations. Use when asked to analyze competitors, create competitive ana

Diagnose and rewrite an underperforming LLM prompt so it produces reliable, well-structured output. Use when asked to improve a prompt, fix a prompt that gives inconsistent or wrong results, reduce ha

Audit whether the organisation's AI spend actually paid — measured against baselines, not vendor math or vibes. Use when a CFO asks what the AI tools returned, when renewing AI contracts, when consoli

Diagnose a bug systematically instead of guessing — reproduce, isolate, form hypotheses, and test them to root cause. Use when debugging, chasing a defect, an intermittent failure, or 'why is this hap

Audit spending to find leaks — recurring subscriptions, creep, and cuttable costs — ranked by impact. Use when asked to cut expenses, review subscriptions, find where money is going, or free up cash.

The strongest possible case AGAINST what you just wrote — argued to win, not to check a box. Use when a document is about to ship and everyone around it already agrees: the twin writes the opposition'

Pull the single most shareable quote out of a testimonial, review, interview, or long text and format it as a clean quote card. Use when asked to make a pull-quote, testimonial graphic, or 'quote card

Structure a clinical encounter into a clean SOAP note. Use when asked to write a SOAP note, document a patient encounter, turn visit notes into clinical documentation, or structure subjective/objectiv

Audit a knowledge base / help center for coverage, accuracy, and findability. Use when asked to audit a help center, review KB health, find documentation gaps, reduce ticket volume with better docs, o

Answer 'is this site down or is it just me' properly — curl status/timing diagnostics, DNS cross-check, and TLS certificate reads, assembled into a where-it's-broken diagnosis. Use when asked is this

Produce a structured churn analysis that separates avoidable from unavoidable churn. Use when investigating why customers are leaving, identifying at-risk segments, calculating net revenue retention,

Write a clear pull-request description that gets reviewed fast and merged with confidence, from a git diff, branch summary, or commit list. Use when opening a PR, summarizing a change for review, docu

Execute and monitor stock trades for openclaw.ai workflows using Questrade's browser platform with Yahoo Finance cross-checks. Use when Codex is asked to prepare or review Questrade Web order tickets,

Guide users to configure local Chanjing credentials safely via local commands only, and validate local token status when needed.

Interpret routine health checkup reports and lab results in plain Chinese, highlighting abnormal items, likely meaning, urgency, follow-up questions, and practical next steps. Use when the user shares

Review agentic software-development plans and release readiness for Codex, GitHub, and ClawHub work. Use when a user asks for scoped delivery planning, implementation review, public-surface checks, or

[Didoo AI] Analyzes Meta Ads campaign performance in depth — metrics, funnel, trends, and anomalies. Use when user wants to understand how a campaign is performing, identify weak points, or get data b

Auditory intelligence for AI agents. Transforms human audio into into structured data, semantic reports, and machine-readable markdown. Use when you need market intelligence, crypto alpha, speaker-att

QA and peer review agent. Reviews output from other agents before delivery. Use when: (1) content from Scribe needs review before posting, (2) research from Scout needs validation before acting on it,