agent instructions skills

10 tagged agent instructions, measured the same way as everything else here.

terminal-management

01

nirholas/auto-kill-terminal

Skill Claude CodeCodex

Teaches AI agents to properly manage VS Code terminal lifecycle — always use background terminals and kill them after commands complete. Prevents zombie terminal accumulation in GitHub Codespaces and VS Code.

20 15d ago A 0 tokens

bootstrap-botfile

02

listfold/botfile

Skill Claude CodeCodex

Drive the botfile CLI to manage AI-agent skills, instructions, and commands. Use when asked to sync, plan, adopt, or check the status of agent components managed by botfile.

16 2mo ago A 43 tokens original Apache-2.0

echo

03

listfold/botfile

Skill Claude CodeCodex

Repeat the user's message back verbatim, and nothing else.

16 2mo ago A 14 tokens original Apache-2.0

goal-to-prototype

04

tonyfadel23/skill-inspector

Skill Claude CodeCodex

Transform a high-level goal into a validated prototype with market research, multi-angle analysis, and iterative refinement. Use when the user says "build me a prototype", "turn this idea into reality", "goal to prototype", "validate this concept", or "research and build".

2 5mo ago A 60 tokens original MIT

build-my-skill

05

tonyfadel23/skill-inspector

Skill Claude CodeCodex

Build custom skill trees with advanced orchestration and emit valid SKILL.md files. Use when the user says "build a skill", "create a skill tree", "build my skill", "design a workflow", "create a pipeline", "skill tree builder", or wants to create an agentic workflow with sub-agents, gated checks, improvement loops…

2 5mo ago A 82 tokens original MIT

check-my-skills

06

tonyfadel23/skill-inspector

Skill Claude CodeCodex

Scan, parse, and visualize the instruction flow of every skill in a project. Use whenever a user says "check my skills", "audit my skills", "what are my skills doing", "show me the skill graph", "skill inspector", "debug my skill", or wants to understand how their SKILL.md files actually propagate instructions. Also…

2 5mo ago A 114 tokens original MIT

agents-doctor

07

ItsHege/agents-md-doctor

Skill Claude CodeCodex

Validate AGENTS.md and related agent instruction files with the published agents-doctor CLI. Use when the user asks to check, lint, verify, explain, audit, fix, release-check, or compare AGENTS.md, CLAUDE.md, GEMINI.md, agent instruction inheritance, tool profiles, context fidelity, instruction graphs, GitHub…

2 28d ago A 93 tokens original MIT

less-is-more

08

oddyblue/Less-Is-More-Skill

Skill Claude CodeCodex

Architecture-first, reduction-first workflow for code changes, debugging, refactoring, and cleanup. Use to trace the owning path, prefer no edit and subtraction before additions, replace obsolete behavior instead of layering around it, keep scope closed, refute your own diagnosis and fix before believing them, verify…

2 22d ago A 75 tokens original MIT

close-books

09

srmackey/insitu

Skill Claude CodeCodex

Close the day's ledger. Run from the checkout as /close-books.

0 yesterday A 17 tokens original MIT

close-hatch

10

srmackey/insitu

Skill Claude CodeCodex

Close the hatch at end of watch.

0 yesterday A 12 tokens original MIT