agent-knowledge
Manage permanent product knowledge, anti-patterns, distillation, and minimalism in agent-managed projects.
Skill by RbrtMrlsIII
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/rbrtmrlsiii-agent-knowledge
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-knowledge
What's inside
- Skill name
agent-knowledge- Description
- Manage permanent product knowledge, anti-patterns, distillation, and minimalism in agent-managed projects. Use when reading or updating PRODUCT-KNOWLEDGE.md, checking for repeated mistakes, distilling findings, enforcing max-10 findings rule, or when the user mentions anti-patterns, knowledge lifecycle, distillation, or minimalism.
- License
- unknown
- Instructions
- 66 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from RbrtMrlsIII/ToolKit
- 0.519score
agent-census
RbrtMrlsIII
Run and interpret the universal census inventory tool that counts tabs, UI screens, components, 3D models, routes, endpoints, data models and cleanliness…
SkillBFreshness: BClaude Code +9 - 0.519score
agent-continuity
RbrtMrlsIII
Enforce continuity reading order, timestamped session logging, and the mandatory file-update protocol across agent sessions.
SkillBFreshness: BClaude Code +9 - 0.519score
agent-orucavea
RbrtMrlsIII
Apply the O-R-U-C-A-V-E-A execution discipline (Observe Record Understand Classify Align Validate Endorse Advance) and its 9-step inner loop for any…
SkillBFreshness: BClaude Code +9 - 0.516score
dynamic-skill-resolution
RbrtMrlsIII
Resolve the smallest sufficient reusable skill bundle from project, task, runtime, governance, and capacity context without granting authorization.
SkillBFreshness: BClaude Code +9 - 0.515score
agent-structure
RbrtMrlsIII
Apply or scaffold the canonical agent toolkit structure with 6 core files, skills, scripts, .agent machine state, and docs layout.
SkillBFreshness: BClaude Code +9 - 0.513score
backend-first-clarifier
RbrtMrlsIII
Universal gate requiring backend authority clarification before a project moves from idea into implementation.
SkillBFreshness: BClaude Code +9 - 0.513score
knowledge-promotion
RbrtMrlsIII
Classify and promote validated lessons into reusable Toolkit knowledge without importing consumer-specific authority.
SkillBFreshness: BClaude Code +9 - 0.512score
canonical-integrity
RbrtMrlsIII
Protect canonical knowledge structures from unexplained deletion or section loss.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 2
- Last commit (this folder)
- Sep 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/RbrtMrlsIII/ToolKit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from RbrtMrlsIII
- 0.552score
seat-shell-hierarchy
RbrtMrlsIII
Seat Shell Hierarchy v1 — first in-machine parent open path for TeamAi 3D Hero.
SkillBFreshness: B★ 2Claude Code +9 - 0.552score
workspace-ring
RbrtMrlsIII
Concentric Ring Map R0–R2 presentation (workspace core, backend display, setup/config).
SkillBFreshness: B★ 2Claude Code +9 - 0.519score
agent-census
RbrtMrlsIII
Run and interpret the universal census inventory tool that counts tabs, UI screens, components, 3D models, routes, endpoints, data models and cleanliness…
SkillBFreshness: BClaude Code +9 - 0.519score
agent-continuity
RbrtMrlsIII
Enforce continuity reading order, timestamped session logging, and the mandatory file-update protocol across agent sessions.
SkillBFreshness: BClaude Code +9 - 0.519score
agent-orucavea
RbrtMrlsIII
Apply the O-R-U-C-A-V-E-A execution discipline (Observe Record Understand Classify Align Validate Endorse Advance) and its 9-step inner loop for any…
SkillBFreshness: BClaude Code +9 - 0.516score
dynamic-skill-resolution
RbrtMrlsIII
Resolve the smallest sufficient reusable skill bundle from project, task, runtime, governance, and capacity context without granting authorization.
SkillBFreshness: BClaude Code +9
Cite this page
agent-knowledge skill. Agent Mart. https://agentmart.dev/skills/rbrtmrlsiii-agent-knowledge (last updated 2026-10-24)