Agent Instructions
codexMaintain project AGENTS.md guidance and find or apply selected refactoring changes in AI agent instructions.
4 skills
Design trustworthy agent evaluations and use Harbor's official task, Exec and publishing workflows.
Plugin harbor in shpoont/codex-marketplace. Commands read from the repo's manifest — yesterday.
harbor-agent-testingCreate, run and review repeatable Harbor tests of agent behavior. Preserve project acceptance criteria, reuse validated execution recipes and report clear results.
official-create-adapterOfficial Harbor Create Adapter workflow, packaged with local safeguards. Scaffold a new Harbor benchmark adapter by running `harbor adapter init` and then guide implementation using the Adapters Agent Guide as the authoritative spec.
official-create-taskOfficial Harbor Create Task workflow, packaged with local safeguards. Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, verifier design (pytest vs Reward
official-harbor-execOfficial Harbor Exec workflow, packaged with local safeguards. Use when working with Harbor''s `harbor exec` CLI workflow: compiling files, directories, or globs into Harbor tasks; running map jobs; configuring artifacts and existence-only verification; using map-reduce; writing or reviewing ExecCon
official-publishOfficial Harbor Publish workflow, packaged with local safeguards. Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry. Applies to Harbor Hub tasks and datasets; plugin-marketplace publication uses
official-rewardkitOfficial Harbor Reward Kit workflow, packaged with local safeguards. Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward score.
official-upload-parity-experimentsOfficial Harbor Upload Parity Experiments workflow, packaged with local safeguards. Create or reuse Hugging Face dataset PRs for `harborframework/parity-experiments` and upload Harbor parity/oracle result folders efficiently with sparse checkout, raw git pushes, and Git LFS. Creation and uploads req
Maintain project AGENTS.md guidance and find or apply selected refactoring changes in AI agent instructions.
4 skills
Generate local speech with Kokoro and recognize recorded speech with Whisper.
2 skills
Operate ChatGPT conversations with native chat tools and browser UI for model and research gaps.
1 skill
Choose expert perspectives for Codex and manage their personal installations while preserving existing roles and local edits.
1 skill
Monday's dry, sarcastic conversation style with the complete archived persona and seven examples.
1 skill
Organize related emails, understand what needs attention, and turn messages into action, with you approving the changes.
1 skill
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
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
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
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.