claude

Instinct

Marketplace meta tooling: skill creation, writing for agents, context budgeting, skill scouting, component auditing, and linting. Marketplace maintenance, not user workflow execution (B-7).

0 on GitHubby Colton Beardenv0.1.0MITupdated 1 month agocore
/

Plugin instinct from marketplace awakened in coltonbearden/awakened. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (6)

  • auditing-components

    Audit a skill, command, agent or hook for unsafe behaviour by first listing everything it depends on or invokes, then checking each item against the marketplace's hard-reject, conditional and injection rules, and returning a fail-closed PASS or FAIL. Use before merging or installing a component, whe

  • context-budget

    Estimate how much of the context window the always-loaded configuration consumes — agents, skills, rules, MCP tool schemas and the CLAUDE.md chain — and rank the components worth trimming or lazy-loading. Use when sessions feel sluggish or lose quality early, after adding several skills, agents or M

  • linting-components

    Lint an authored skill, command or agent against the marketplace's frontmatter schema, naming rules, Markdown standard, section template and trigger-description rule, scoring it on a fixed pass/fail scorecard and separately judging whether its description would fire on the right situations. Use afte

  • skill-scout

    Search the skills already installed locally, in enabled plugin marketplaces and — when the tools exist — on GitHub and the web before a new skill is written, then vet and rank the candidates. Use when the user asks to create, build or fork a skill, asks whether a skill for some workflow already exis

  • writing-for-agents

    Edit the prose of any document an agent will execute — a CLAUDE.md, a rules file, a skill body, a plan — so the agent takes the same path every run: sharpen pointers, rank material by how soon it is needed, end every step on a checkable completion criterion, prune no-ops. Use when writing or revisin

  • writing-skills

    Author or revise a SKILL.md so it fires on the right situations and changes agent behaviour when it does — shape the trigger description, fill the repository's skill template, and prove the skill against a baseline run before it ships. Use when creating a new skill, editing an existing one, or check

Slash commands (2)

  • /instinct:learn-eval

    Extract one reusable pattern from the current session, gate it through an overlap check and a Save / Improve / Absorb / Drop verdict, decide project versus user scope, and write it as a skill only after the user confirms. Use after solving a non-obvious problem worth keeping, or at the end of a sess

  • /instinct:skill-create

    Derive a project-conventions skill from the local git history — commit-message conventions, files that change together, hot files and test placement — and write it to the project's skills directory after the user confirms. Use when onboarding an agent to an established repository, or when a team's h

View source on GitHub

More from coltonbearden/awakened

All 9 plugins →

Bankai

claude

Specialist subagents with restricted tool allowlists: research, exploration, debugging, review, planning, documentation, and synthesis agents, plus the skills that dispatch them. Every subagent in Awakened lives here (B-6).

7 skills · 27 agents

0

Core engineering workflow: planning, implementation discipline, test-driven development, systematic debugging, verification before completion, and git workflow guidance. The stable baseline - it depends on no agents, memory infrastructure, or project-specific tooling (B-1).

18 skills · 9 commands

0

Domain

claude

Project-scoped structural context: codebase onboarding, code maps, documentation upkeep, conventions, domain modeling, and CLAUDE.md scaffolding. Structural context only; it stores no history (B-4).

7 skills · 2 commands

0

Sharingan

claude

Code review and analysis: review discipline, production audit, architecture inspection, AI-debt detection, and security-oriented review. Analysis and review only - implementation stays outside this plugin (B-2).

7 skills · 1 command

0

Kaioken

claude

Session management and momentum: save and resume sessions, handoffs, checkpoints, and focused asides. Session momentum only - it duplicates no planning, debugging, or review system (B-5).

1 skill · 4 commands

0

Rinnegan

claude

Persistent temporal memory: file-based decision history, session context, searchable project notes, and recall across sessions. No daemons, workers, databases, or services (B-3).

3 skills · 2 commands

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

obsidian

claude

Claude Skills for Obsidian

6 skills

kepano/obsidian-skills 51,587

Maintain Instinct?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins9 plugins