← All skill packs

Security & Agent Automation Skills

Skill pack
7 skills0 selected
rcdelfinSkills in this pack

Apply analogical reasoning to problems — find structural parallels across domains, ask the 4 core questions, detect when analogies break. Use when stuck on novel problems or when domain-specific tools aren't sufficient.

English

Use when fixing or building a ClickUp card ID (e.g. GYMED-100) end-to-end, including branch, verification, and MR review.

English

Ingest source content (ClickUp cards, meeting notes, transcripts, specs) into the project's governed local knowledge base. Dynamically locates the wiki (prefers docs/wiki/), then obeys the wiki's own AGENTS.md for structure and rules. Trigger: 'ingest into the wiki', 'add to wiki', 'capture this card/note locally', or any workflow that needs to persist a source doc locally before working on it.

English

Perform a PR-scoped security audit on a small to medium code change (1-20 files, additive endpoint, schema change, refactor). Produces a structured findings table with confidence scores, no false positives, and a clean verdict. Trigger only when the user explicitly asks for a "security audit", "security review", "vulnerability check", "is this safe to ship", or "OWASP check" of recent changes. NOT for greenfield threat modeling, full-codebase reviews, or infrastructure audits — those need heavier tooling. NOT for proactive scanning while writing code.

English

Dynamic skill router — discovers available SKILL.md metadata, matches the current task to the smallest relevant skill set, and loads those skills before acting. Trigger proactively at the start of non-trivial tasks or whenever the available skill catalog may have changed.

English

Lightweight change planning — produces a self-contained four-artifact plan (proposal, specs, design, tasks) and, on archive, folds delta specs into a system-wide source of truth. Stores changes under plans/ / when available, adapting to coexist with other content; otherwise under docs/tweaks/ /. Standalone: no CLI, no schema, no tool integrations. Use when you want OpenSpec-style change planning without installing @fission-ai/openspec. Trigger words: tweak, plan change, proposal, design doc, RFC, change doc, scaffold feature, change set.

English

MR Review — ревью чужого Merge Request с публикацией threads в GitLab. Используй когда просят отревьюить MR коллеги по ссылке или ID (fetch diff → /go-review → публикация замечаний).

Russian

Includes Analogical Thinking, Clickup Tweak Workflow, Local Wiki, and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills7CategorygeneralStars0

What’s included

Analogical Thinking

Apply analogical reasoning to problems — find structural parallels across domains, ask the 4 core questions, detect when analogies break. Use when stuck on novel problems or when domain-specific tools aren't sufficient.

Clickup Tweak Workflow

Use when fixing or building a ClickUp card ID (e.g. GYMED-100) end-to-end, including branch, verification, and MR review.

Local Wiki

Ingest source content (ClickUp cards, meeting notes, transcripts, specs) into the project's governed local knowledge base. Dynamically locates the wiki (prefers docs/wiki/), then obeys the wiki's own AGENTS.md for structure and rules. Trigger: 'ingest into the wiki', 'add to wiki', 'capture this card/note locally', or any workflow that needs to persist a source doc locally before working on it.

Security Audit Light

Perform a PR-scoped security audit on a small to medium code change (1-20 files, additive endpoint, schema change, refactor). Produces a structured findings table with confidence scores, no false positives, and a clean verdict. Trigger only when the user explicitly asks for a "security audit", "security review", "vulnerability check", "is this safe to ship", or "OWASP check" of recent changes. NOT for greenfield threat modeling, full-codebase reviews, or infrastructure audits — those need heavier tooling. NOT for proactive scanning while writing code.

Skill Orchestration

Dynamic skill router — discovers available SKILL.md metadata, matches the current task to the smallest relevant skill set, and loads those skills before acting. Trigger proactively at the start of non-trivial tasks or whenever the available skill catalog may have changed.

Tweak

Lightweight change planning — produces a self-contained four-artifact plan (proposal, specs, design, tasks) and, on archive, folds delta specs into a system-wide source of truth. Stores changes under plans/ / when available, adapting to coexist with other content; otherwise under docs/tweaks/ /. Standalone: no CLI, no schema, no tool integrations. Use when you want OpenSpec-style change planning without installing @fission-ai/openspec. Trigger words: tweak, plan change, proposal, design doc, RFC, change doc, scaffold feature, change set.

Mr Review

MR Review — ревью чужого Merge Request с публикацией threads в GitLab. Используй когда просят отревьюить MR коллеги по ссылке или ID (fetch diff → /go-review → публикация замечаний).

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.

Try it with your agent

After installation, start with a request like:

Example request
Use the Analogical Thinking skill to help with my task.
Ask me for the context you need before getting started.

Requirements & license

  • A coding agent that can access your project files and install skills.
  • Your agent checks each skill’s instructions, dependencies, and permissions during setup.
  • Reported license for the skills shown: MIT. The author’s terms apply.