Skills Reference

Auto-generated; do not hand-edit. Regenerate with sb skills docs-write.

SecondBrain skills are filesystem-backed SKILL.md bundles used as procedural memory. The registry routes by frontmatter first, then loads body text and linked rules/ files only when a skill is selected.

Skill	Version	Trust	Safety	Description
artifact-generation	1.0.0	local	standard	Use when creating polished deliverables such as reports, docs, decks, spreadsheets, diagrams, templates, or packaged handoff artifacts from source material and task requirements.
codex-prompting	1.0.0	local	read_only	Use when improving Codex-style task prompts, AGENTS.md instructions, review briefs, subagent handoffs, or implementation requests so they are precise, scoped, testable, and safe for coding agents.
context-refinery	1.0.0	local	read_only	Use when refining agent context: compressing long notes, extracting durable facts, separating signal from noise, preparing task briefs, or identifying what context should be carried into a new session.
doc-writer	1.0.0	local	standard	Assists with writing and improving project documentation including READMEs, architecture docs, API references, and user guides. Use when the user wants to write docs, update a README, document an API, or create a user guide.
frontend-design	1.0.0	local	standard	Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
internal-comms	1.0.0	local	standard	A set of resources to help write internal communications using common company-friendly formats. Use this skill whenever the user asks to draft internal communications such as status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, or project updates.
mcp-builder	1.0.0	local	standard	Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
repo-maintenance	1.0.0	local	standard	Use when maintaining a local repository: checking status, triaging stale generated assets, refreshing indexes, running focused validation, or preparing a small reviewable maintenance change.
skill-creator	1.2.0	local	standard	Guides the user through creating a new SecondBrain skill folder with valid SKILL.md frontmatter, explicit activation boundaries, replayable eval cases, a machine-readable creation brief, explicit tool/safety contracts, structured instructions, and optional scripts/references/assets directories. Use when the user wants to create a new skill, build a skill, write a SKILL.md, or scaffold a skill pack from scratch.
skill-optimizer	1.4.0	local	standard	Guides validation-gated improvement of an existing SecondBrain skill using scored rollout evidence, deterministic evidence-to-edit proposals, bounded add/delete/replace edits, materialized candidate artifacts, rejected-edit memory, durable run state, Antahkarana-backed gate outcomes, and protected slow-update guidance. Use when the user wants to optimize a skill, evolve a SKILL.md, improve skill performance, or turn replay failures into a better reusable skill artifact.
webapp-testing	1.0.0	local	standard	Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

artifact-generation

Use when creating polished deliverables such as reports, docs, decks, spreadsheets, diagrams, templates, or packaged handoff artifacts from source material and task requirements.

Field	Value
Version	1.0.0
Trust level	local
Safety class	standard
Required tools	-
Triggers	create an artifact, generate a report, build a deliverable, package this handoff
Negative triggers	debug a runtime failure, only answer a factual question
Examples	Create a polished report, deck outline, spreadsheet, diagram, template, or handoff package from provided material.
Tests	sb skills validate --path skills --strict
Performance	{"notes":"Best when source material, target audience, and output format are known."}
Path	/opt/SecondBrain/skills/artifact-generation

codex-prompting

Use when improving Codex-style task prompts, AGENTS.md instructions, review briefs, subagent handoffs, or implementation requests so they are precise, scoped, testable, and safe for coding agents.

Field	Value
Version	1.0.0
Trust level	local
Safety class	read_only
Required tools	-
Triggers	improve this codex prompt, write agent instructions, draft an implementation brief, make this prompt testable
Negative triggers	write application code only, summarize a meeting transcript
Examples	Rewrite a coding-agent task prompt with scope, constraints, acceptance criteria, and verification commands.
Tests	sb skills validate --path skills --strict
Performance	{"notes":"Best for precise coding-agent prompts, handoffs, and repo instructions."}
Path	/opt/SecondBrain/skills/codex-prompting

context-refinery

Use when refining agent context: compressing long notes, extracting durable facts, separating signal from noise, preparing task briefs, or identifying what context should be carried into a new session.

Field	Value
Version	1.0.0
Trust level	local
Safety class	read_only
Required tools	-
Triggers	refine this context, compact these notes, prepare a task brief, extract durable facts
Negative triggers	generate UI art, deploy a service
Examples	Turn a long thread, note set, or context pack into a concise brief with facts, open questions, and next actions.
Tests	sb skills validate --path skills --strict
Performance	{"notes":"Best for context compaction, salience filtering, and handoff briefs."}
Path	/opt/SecondBrain/skills/context-refinery

doc-writer

Assists with writing and improving project documentation including READMEs, architecture docs, API references, and user guides. Use when the user wants to write docs, update a README, document an API, or create a user guide.

Field	Value
Version	1.0.0
Trust level	local
Safety class	standard
Required tools	-
Triggers	write documentation, update the README, document this, create a user guide, write API docs, improve the docs
Negative triggers	delete docs, remove documentation
Examples	Write or improve a README, API reference, user guide, architecture note, or changelog.
Tests	sb skills validate --path skills --strict
Performance	{"notes":"Best for documentation drafting, structure review, and stale reference cleanup."}
Path	/opt/SecondBrain/skills/doc-writer

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Field	Value
Version	1.0.0
Trust level	local
Safety class	standard
Required tools	-
Triggers	design a frontend page, build a landing page, improve this ui styling, create a react component ui, make this interface look better
Negative triggers	backend only change, cli only task
Examples	Design or improve a frontend page, dashboard, React component, HTML layout, or web app UI.
Tests	sb skills validate --path skills --strict
Performance	{"notes":"Best when paired with local UI inspection and responsive screenshot checks."}
Path	/opt/SecondBrain/skills/frontend-design

internal-comms

A set of resources to help write internal communications using common company-friendly formats. Use this skill whenever the user asks to draft internal communications such as status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, or project updates.

Field	Value
Version	1.0.0
Trust level	local
Safety class	standard
Required tools	-
Triggers	write a status update, draft a leadership update, create a 3p update, write an internal newsletter, draft an incident update
Negative triggers	external marketing copy, public press release
Examples	Draft a 3P update, leadership update, newsletter, FAQ, incident report, or project status note.
Tests	sb skills validate --path skills --strict
Performance	{"notes":"Best for concise internal formats with clear audience and status context."}
Path	/opt/SecondBrain/skills/internal-comms

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Field	Value
Version	1.0.0
Trust level	local
Safety class	standard
Required tools	-
Triggers	build an mcp server, create mcp server, implement mcp tools, integrate an api with mcp, design mcp tool schema
Negative triggers	use an existing mcp server, only configure mcp client
Examples	Design, build, or evaluate an MCP server for an external API or local tool surface.
Tests	sb skills validate --path skills --strict
Performance	{"notes":"Best when the target API contract and expected agent workflows are available."}
Path	/opt/SecondBrain/skills/mcp-builder

repo-maintenance

Use when maintaining a local repository: checking status, triaging stale generated assets, refreshing indexes, running focused validation, or preparing a small reviewable maintenance change.

Field	Value
Version	1.0.0
Trust level	local
Safety class	standard
Required tools	-
Triggers	maintain this repo, refresh generated assets, triage repo health, prepare a maintenance change
Negative triggers	redesign the product, write marketing copy
Examples	Check repository health, identify stale assets, and propose a small maintenance diff.
Tests	sb skills validate --path skills --strict
Performance	{"notes":"Best for scoped local maintenance with explicit verification commands."}
Path	/opt/SecondBrain/skills/repo-maintenance

skill-creator

Guides the user through creating a new SecondBrain skill folder with valid SKILL.md frontmatter, explicit activation boundaries, replayable eval cases, a machine-readable creation brief, explicit tool/safety contracts, structured instructions, and optional scripts/references/assets directories. Use when the user wants to create a new skill, build a skill, write a SKILL.md, or scaffold a skill pack from scratch.

Field	Value
Version	1.2.0
Trust level	local
Safety class	standard
Required tools	-
Triggers	create a skill, new skill, build a skill, scaffold skill, write a SKILL.md, make a skill pack
Negative triggers	optimize an existing skill, tune an existing skill, delete skill, remove skill, uninstall skill
Examples	Create a new skill folder with SKILL.md and eval cases. Scaffold an optimizer-ready skill pack from a workflow description.
Tests	sb skills validate --path skills --strict pytest -q tests/skills/test_skill_creator_scaffold.py tests/skills/test_skills_cli_lifecycle.py
Performance	{"notes":"Best for creating validated procedural skills with explicit triggers, eval splits, and capability contracts."}
Path	/opt/SecondBrain/skills/skill-creator

skill-optimizer

Guides validation-gated improvement of an existing SecondBrain skill using scored rollout evidence, deterministic evidence-to-edit proposals, bounded add/delete/replace edits, materialized candidate artifacts, rejected-edit memory, durable run state, Antahkarana-backed gate outcomes, and protected slow-update guidance. Use when the user wants to optimize a skill, evolve a SKILL.md, improve skill performance, or turn replay failures into a better reusable skill artifact.

Field	Value
Version	1.4.0
Trust level	local
Safety class	standard
Required tools	-
Triggers	optimize a skill, improve skill performance, evolve a SKILL.md, tune this skill, turn replay failures into skill edits, record skill optimization in Antahkarana, propose skill edits from evidence, build candidate skill artifact
Negative triggers	create a brand new skill from scratch, uninstall a skill, optimize model weights
Examples	Draft a validation-gated plan for improving an existing skill from replay evidence.
Tests	sb skills validate --path skills --strict pytest -q tests/skills/test_skill_optimizer_plan.py tests/skills/test_skill_optimizer_run.py tests/skills/test_skill_evidence.py tests/skills/test_skill_patching.py tests/skills/test_skill_selection_gate.py tests/skills/test_skill_antahkarana_bridge.py tests/skills/test_skills_cli_lifecycle.py
Performance	{"notes":"Best when the skill has scored rollouts, replay cases, or benchmark evidence."}
Path	/opt/SecondBrain/skills/skill-optimizer

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Field	Value
Version	1.0.0
Trust level	local
Safety class	standard
Required tools	-
Triggers	test this web app, automate browser testing, verify ui behavior, playwright test for local app, debug frontend with browser automation
Negative triggers	write unit tests only, backend api test only
Examples	Use Playwright to inspect, test, debug, or screenshot a local web application.
Tests	sb skills validate --path skills --strict
Performance	{"notes":"Best for browser-visible behavior after a local server is running."}
Path	/opt/SecondBrain/skills/webapp-testing