@skills · Owner
Agent skills by pskoett
66 skills indexed from github.com/pskoett. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.
- self-improving-agent · Skill · 720 stars
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Cl
- self-improving-agent · Collection · 720 stars
- .agents · Collection · 273 stars
- context-surfing · Skill · 273 stars
Monitors context window health during large, long-running, multi-session, or explicitly context-sensitive work. Uses bounded external anchors, one cold-con
- context-surfing · Skill · 273 stars
Monitors context window health during large, long-running, multi-session, or explicitly context-sensitive work. Uses bounded external anchors, one cold-con
- context-surfing · Skill · 273 stars
Monitors context window health throughout a session and rides peak context quality for maximum output fidelity. Activates automatically after plan-intervie
- control-session-orchestrator · Skill · 273 stars
Control-plane workflow for coordinating multi-agent, multi-session project work from a single Codex, GitHub Copilot, or agent-app control session. Use this
- control-session-orchestrator · Skill · 273 stars
Control-plane workflow for coordinating multi-agent, multi-session project work from a single Codex, GitHub Copilot, or agent-app control session. Use this
- eval-creator · Skill · 273 stars
[Beta] Creates permanent eval cases from promoted learnings and runs regression checks against them. Turns failures into test cases that prevent silent reg
- eval-creator · Skill · 273 stars
[Beta] Creates permanent eval cases from promoted learnings and runs regression checks against them. Turns failures into test cases that prevent silent reg
- eval-creator-ci · Skill · 273 stars
[Beta] CI-only eval regression runner using gh-aw (GitHub Agentic Workflows). Runs all eval cases in .evals/ on a schedule or per-PR, reports pass/fail res
- eval-creator-ci · Skill · 273 stars
[Beta] CI-only eval regression runner using gh-aw (GitHub Agentic Workflows). Runs all eval cases in .evals/ on a schedule or per-PR, reports pass/fail res
- intent-framed-agent · Skill · 273 stars
Frames coding-agent work sessions with explicit intent capture and drift monitoring. Use when a session transitions from planning/Q&A to implementation for
- intent-framed-agent · Skill · 273 stars
Frames coding-agent work sessions with explicit intent capture and drift monitoring. Use when a session transitions from planning/Q&A to implementation for
- intent-framed-agent · Skill · 273 stars
Frames coding-agent work sessions with explicit intent capture and drift monitoring. Use when a session transitions from planning/Q&A to implementation for
- learning-aggregator · Skill · 273 stars
[Beta] Cross-session analysis of accumulated .learnings/ files. Reads all entries, groups by pattern_key, computes recurrence across sessions, and outputs
- learning-aggregator · Skill · 273 stars
[Beta] Cross-session analysis of accumulated .learnings/ files. Reads all entries, groups by pattern_key, computes recurrence across sessions, and outputs
- learning-aggregator-ci · Skill · 273 stars
[Beta] CI-only learning aggregation workflow using gh-aw (GitHub Agentic Workflows). Scans .learnings/ files on a schedule, groups entries by pattern_key,
- learning-aggregator-ci · Skill · 273 stars
[Beta] CI-only learning aggregation workflow using gh-aw (GitHub Agentic Workflows). Scans .learnings/ files on a schedule, groups entries by pattern_key,
- mcp-builder · Skill · 273 stars
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use w
- plan-interview · Skill · 273 stars
Ensures alignment between user and Claude during feature/spec planning through a structured interview process.
- plan-interview · Skill · 273 stars
Ensures alignment between user and Codex during feature/spec planning through a structured interview process. Use this skill when the user invokes /plan-in
- plan-interview · Skill · 273 stars
Ensures alignment between user and Claude during feature/spec planning through a structured interview process. Use this skill when the user invokes /plan-i
- plugin · Collection · 273 stars
- pre-flight-check · Skill · 273 stars
[Beta] Session-start scan that surfaces relevant learnings, recent errors, and eval status before work begins. Bridges the outer loop back into the inner l
- pre-flight-check · Skill · 273 stars
[Beta] Session-start scan that surfaces relevant learnings, recent errors, and eval status before work begins. Bridges the outer loop back into the inner l
- pskoett-ai-skills · Collection · 273 stars
- self-healing · Skill · 273 stars
Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, the
- self-healing · Skill · 273 stars
Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, the
- self-healing-ci · Skill · 273 stars
CI-only self-healing workflow using gh-aw (GitHub Agentic Workflows) for active runtime recovery on pull requests and scheduled runs. When a CI check fails
- self-healing-ci · Skill · 273 stars
CI-only self-healing workflow using gh-aw (GitHub Agentic Workflows) for active runtime recovery on pull requests and scheduled runs. When a CI check fails
- self-improvement · Skill · 273 stars
Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...',
- self-improvement · Skill · 273 stars
Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...',
- self-improvement · Skill · 273 stars
Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude (''No, that''s wrong...'
- self-improvement-ci · Skill · 273 stars
CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and quality signals from pull request checks,
- simplify-and-harden · Skill · 273 stars
Post-completion self-review for coding agents that runs simplify, harden, re-verification, and micro-documentation passes on non-trivial code or high-impac
- simplify-and-harden · Skill · 273 stars
Post-completion self-review for coding agents that runs simplify, harden, and micro-documentation passes on non-trivial code changes. Use when: a coding ta
- simplify-and-harden · Skill · 273 stars
Post-completion self-review for coding agents that runs simplify, harden, re-verification, and micro-documentation passes on non-trivial code or high-impac
- simplify-and-harden-ci · Skill · 273 stars
CI-only Simplify & Harden workflow for pull requests using gh-aw (GitHub Agentic Workflows). Runs headless scan-and-report checks for simplify/harden/docum
- skill-creator · Skill · 273 stars
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's cap
- skill-pipeline · Skill · 273 stars
Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct combination of skills at the right depth. Implements two fe
- skill-pipeline · Skill · 273 stars
Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct combination of skills at the right depth. Implements two fe
- skill-tester · Skill · 273 stars
Validates all interactive skills in this repo against the Agent Skills spec, project conventions, and structural requirements. Runs quick_validate.py, chec
- skill-tester-ci · Skill · 273 stars
Validates all CI skills in this repo. Checks Agent Skills spec compliance, gh-aw workflow compilation, permission correctness, and structural conventions.
- skills · Collection · 273 stars
- skills · Collection · 273 stars
- skills · Collection · 273 stars
- verify-gate · Skill · 273 stars
Runs project compile, test, and lint commands between implementation and quality review. Gates simplify-and-harden behind machine verification. If checks f
- verify-gate · Skill · 273 stars
Runs project compile, test, and lint commands between implementation and quality review. Gates simplify-and-harden behind machine verification. If checks f
- agent-plugin · Collection
- context-surfing · Skill
Monitors context window health during large, long-running, multi-session, or explicitly context-sensitive work. Uses bounded external anchors, one cold-con
- control-session-orchestrator · Skill
Control-plane workflow for coordinating multi-agent, multi-session project work from a single Codex, GitHub Copilot, or agent-app control session. Use this
- eval-creator · Skill
[Beta] Creates permanent eval cases from promoted learnings and runs regression checks against them. Turns failures into test cases that prevent silent reg
- eval-creator-ci · Skill
[Beta] CI-only eval regression runner using gh-aw (GitHub Agentic Workflows). Runs all eval cases in .evals/ on a schedule or per-PR, reports pass/fail res
- intent-framed-agent · Skill
Frames coding-agent work sessions with explicit intent capture and drift monitoring. Use when a session transitions from planning/Q&A to implementation for
- learning-aggregator · Skill
[Beta] Cross-session analysis of accumulated .learnings/ files. Reads all entries, groups by pattern_key, computes recurrence across sessions, and outputs
- learning-aggregator-ci · Skill
[Beta] CI-only learning aggregation workflow using gh-aw (GitHub Agentic Workflows). Scans .learnings/ files on a schedule, groups entries by pattern_key,
- plan-interview · Skill
Ensures alignment between user and Claude during feature/spec planning through a structured interview process. Use this skill when the user invokes /plan-i
- pre-flight-check · Skill
[Beta] Session-start scan that surfaces relevant learnings, recent errors, and eval status before work begins. Bridges the outer loop back into the inner l
- self-healing · Skill
Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, the
- self-healing-ci · Skill
CI-only self-healing workflow using gh-aw (GitHub Agentic Workflows) for active runtime recovery on pull requests and scheduled runs. When a CI check fails
- self-improvement · Skill
Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...',
- simplify-and-harden · Skill
Post-completion self-review for coding agents that runs simplify, harden, re-verification, and micro-documentation passes on non-trivial code or high-impac
- skill-pipeline · Skill
Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct combination of skills at the right depth. Implements two fe
- skills · Collection
- verify-gate · Skill
Runs project compile, test, and lint commands between implementation and quality review. Gates simplify-and-harden behind machine verification. If checks f