Skill reviews

Work down the cost of a prescription systematically — the generic and therapeutic-alternative conversation, discount programs vs insurance math, pharmacy price variance, and manufa

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• No condition that starts the skill

Build a community management playbook for a brand's social media channels. Use when asked to create guidelines for managing comments, DMs, and community interactions, define a mode

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill
• 7 mutating operations with no state check

Respond to a brand or executive impersonation incident — deepfaked executives, cloned support lines, fake apps, spoofed domains, or AI-generated scam content wearing your name. Use

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill

Run or document a security incident response — contain, eradicate, recover, and learn. Use when responding to a breach/compromise/security incident, writing an IR plan or runbook,

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Build a staff shift schedule that matches coverage to demand while hitting a labor-cost target. Use when asked to build a shift schedule, staff a rota, plan coverage for a restaura

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Write a STRIDE-based threat model for a service or feature. Use when asked to produce a threat model, document security risks, identify attack vectors, assess a service's security

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill
• Linear process with no failure handling

Run a rigorous candidate reference check that surfaces real signal. Use when asked to prepare or conduct reference calls for a job candidate, design reference questions, or build a

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Get your security deposit back — the move-out documentation that wins disputes before they start, the itemized-deduction challenge, the demand-letter ladder, and the small-claims d

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• No condition that starts the skill

Structure a product data analysis, metric deep-dive, funnel analysis, or cohort study. Use when asked to analyse product metrics, investigate a drop in conversion, explain a data c

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• No condition that starts the skill

Convert a git log, commit list, or release notes into a polished, user-facing changelog. Use when writing release notes, generating a CHANGELOG.md entry, or documenting what change

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Design a voice AI agent for phone or in-app conversations — call flows, interruption handling, escalation to humans, and the metrics that catch a bad voice experience. Use when ask

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• 2 mutating operations with no state check

Run meetings that actually decide — the pre-read-then-decide format, the options-on-the-table rule, the decider named before debate starts, and the recorded-or-it-didn't-happen clo

• References files that are not bundled: ../decision-journal/SKILL.md, ../proposal-skeleton/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 2 referenced file(s) missing: ../decision-journal/SKILL.md, ../proposal-skeleton/SKILL.md

Write a feature flag management guide and lifecycle playbook for a service or team — covering flag taxonomy, creation checklist, rollout strategy, monitoring requirements, cleanup

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill
• 12 mutating operations with no state check

Diagnose a tangled git situation and give the exact, safe commands to fix it. Use when asked to undo a commit, recover lost work, fix a bad merge or rebase, resolve a detached HEAD

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Run the pre-flight checklist before an agent touches an inbox — the read-vs-send permission line, the injection-in-email-body threat, the send-guard rules, and the blast-radius lim

• References files that are not bundled: ../injection-spotter/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill

Triage the user's REAL inbox through the Gmail connector — not a framework they run by hand. Use when asked to clear my inbox, get me to inbox zero on the actual account, triage my

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• 10 mutating operations with no state check

Draft a clear, plain-language privacy policy tailored to what a product actually collects and does with data. Use when asked to write a privacy policy, draft a data-protection noti

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Design an MCP server for a product — the tool surface, auth model, and safety boundaries that make it genuinely usable by AI agents. Use when asked to spec an MCP server, expose a

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• 4 mutating operations with no state check

Decide which of your recurring rituals to put on autopilot — and which to keep manual. Use when asked what to automate, how to set up recurring AI runs, which reports or briefings

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Says nothing while it works

Install the weekly review that keeps work from managing you — the 30-minute Friday ritual: close the week's loops, sweep the capture points, choose next week's big three before the

• References files that are not bundled: ../email-triage-system/SKILL.md, ../task-triage-matrix/SKILL.md, ../unblock-protocol/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill

Flip Claude’s default from validation to adversarial critique. Use when you are about to make a high-stakes decision, commit to a plan, or pitch something you have not stress-teste

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 9 mutating operations with no state check
• Says nothing while it works

Replace ad-hoc interruptions with office hours that actually get used — the slot design (cadence, length, format), the routing rules that tell people what goes there vs. what shoul

• References files that are not bundled: ../faq-builder/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill

Draft email replies that match the sender's register — formality, length, directness, and emoji-tolerance read from their message, so the reply lands as native instead of off-key.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Write an operational runbook for a service, incident type, or deployment procedure. Use when asked to write a runbook, create an ops guide, document an operational procedure, or pr

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• 12 mutating operations with no state check

Generate a prioritised compliance checklist for GDPR, SOC 2, ISO 27001, FCA, HIPAA, or other frameworks with a gap analysis. Use when asked for a compliance checklist, gap analysis

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling