Skill reviews

Text the user's phone when a long-running task, agent turn, or scheduled job finishes — via @sendblue/cli for outbound, optionally wired to a Claude Code Stop hook for automatic fi

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's `dos verify` and `dos commi

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• 24 mutating operations with no state check

Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only ba

• 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

Send and receive iMessage, SMS, and RCS from application code via the Sendblue HTTP API — text, media, group messages, send styles, reactions, typing indicators, status callbacks,

• 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

Send iMessage and SMS from the shell via the @sendblue/cli npm package — outbound sends, contact management, and account setup with no API client or webhook server required.

• 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
• The response is described with custom markup (5 tags): a typed call is more reliable

Run autonomous multi-step research with Google's Gemini Deep Research Agent: kick off a query, poll progress, and collect a cited report for market analysis or literature reviews.

• 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

Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching.

• 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

Use Xquik for X data workflows: tweet search, user lookup, follower export, media downloads, monitors, webhooks, REST API, MCP, SDK setup, and approval-gated account actions.

• 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

Text Claude from your phone — set up the njerschow/textme daemon so inbound iMessages drive a Claude Code session on your laptop, with voice notes, image input, code execution, and

• 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
• Does not say what the result is

Diagnose and optimize Agent Skills (SKILL.md) with real session data and research-backed static analysis. Works with Claude Code, Codex, and any Agent Skills-compatible agent.

• 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

Mechanical implementation invariants for frontend design: token architecture, typography hierarchy, loading order, FOUT prevention, chrome stability, motion timing, color semantics

• References files that are not bundled: ../design-spatial/SKILL.md
• 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

Companion to atlas-contract. Auto-invoked by its Final Audit on caught drift; also use after Post Reviews or user requests to record a mistake. Distills drift into WHEN/DON'T/INSTE

• 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

Apply Fable-inspired discipline to Codex work: inspect first, track goals and findings, ground conclusions in evidence, verify before completion, and adapt Claude/Fable prompt guid

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Audit a live web page in five phases (catalog, click, trace, classify, report) to identify mock data, hardcoded values, LLM-generated metrics, and broken endpoints. Outputs a markd

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

125+ agent skills for Longbridge Securities — real-time quotes, charts, fundamentals, portfolio analysis, options, and more for HK/US/A-share/SG markets. Trilingual: Simplified Chi

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the process needs to start
• Says nothing while it works

Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from you

• 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
• Does not say what the result is

Upload and download GitHub user-attachments (screenshots, PDFs, zips, videos) from the terminal; use when asked to attach or embed a file in a PR, issue, or comment, or download an

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

Zero-knowledge SSH ops CLI — server health checks, docker/systemd control, log tailing, Postgres introspection, and declarative deploys, without ever exposing credentials to the ag

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Linear process with no failure handling

Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper tiers before you trust t

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Says nothing while it works

Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Compare AI agent-made UI variants locally in a real app, then keep one and clean up unused temporary code.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Stop ineffective AI coding repair loops with stable failure fingerprints, a three-attempt budget, real-path proof, negative controls, and tested rollback.

• 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
• Does not say what the process needs to start

Audit a deployed web app for secrets exposed to the browser: hardcoded API keys/tokens in JS, secrets in HTML meta/attributes/comments, publicly reachable source/config/deploy file

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (3 tags): a typed call is more reliable
• Does not say what the result is

Convert Markdown documents into narrated MP4 videos with synchronized visuals and voice narration.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start