Comprehensive validation suite for Claude Code plugins, marketplaces, hooks, skills, and MCP servers. Includes 17 Python validators, 2 expert agents, and 190+ validation rules.
52 skills · 14 commands · 14 agents
High-accuracy skill activation (88%+) with AI-analyzed keywords, weighted scoring, synonym expansion, and three-tier confidence routing.
Plugin perfect-skill-suggester from marketplace emasoft-plugins in Emasoft/emasoft-plugins. Commands read from the repo's manifest — 9 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
pss-agent-archetypesUse when creating an agent that orchestrates several skills, choosing between ALL-IN-ONE, ONE-FOR-ALL and PLUGIN-OMNI, or deciding whether to preload skills into an agent's frontmatter. Covers the preload-vs-access distinction and the `fork` terminology trap. Trigger with /pss-make-agent.
pss-agent-tomlUse when creating .agent.toml profiles. Trigger with /pss-setup-agent. Loaded by pss-agent-profiler. AI selects elements, validates coherence.
pss-authoringUse when writing skills for PSS discovery or improving suggestion accuracy. Used by pss-agent-profiler. Trigger with /pss-authoring.
pss-benchmark-agentUse when running benchmark competitions or improving scoring accuracy. Used by pss-agent-profiler. Trigger with /pss-benchmark.
pss-cli-referenceUse when the user wants to query the PSS index, search/list/inspect elements, run lifecycle or history queries, build a plugin from a profile, or anywhere a `pss …` CLI command is needed. Loaded by pss-agent-profiler.
pss-design-alignmentUse when augmenting an .agent.toml with project requirements. Loaded by pss-agent-profiler. Trigger with /pss-change-agent-profile --requirements.
pss-usageUse when interpreting element suggestions or troubleshooting PSS. Used by pss-agent-profiler. Trigger with /pss-status.
text-categorization-improverUse when improving categorization, scoring, or matching accuracy via parallel experimentation. Used by pss-agent-profiler. Trigger with /text-categorization-improver.
/perfect-skill-suggester:pss-add-elementAdd a standalone element (skill, agent, command, hook, rule, MCP, LSP, output-style) to an existing plugin
/perfect-skill-suggester:pss-add-to-indexAdd or update a single element in the PSS index
/perfect-skill-suggester:pss-add-to-index:execution-protocol/perfect-skill-suggester:pss-added-sinceList PSS index entries installed since a given time. Useful after /cpv-manage to verify new installs got indexed
/perfect-skill-suggester:pss-change-agent-profileModify an existing .agent.toml profile with natural language instructions
/perfect-skill-suggester:pss-change-agent-profile:execution/perfect-skill-suggester:pss-get-descriptionGet element metadata (description, type, plugin) for skills, agents, commands, hooks, rules, MCPs, LSPs
/perfect-skill-suggester:pss-get-description:execution-protocol/perfect-skill-suggester:pss-make-agentGenerate an ALL-IN-ONE, ONE-FOR-ALL or PLUGIN-OMNI agent
/perfect-skill-suggester:pss-make-plugin-from-profileGenerate a Claude Code plugin from an .agent.toml profile
/perfect-skill-suggester:pss-reindex-skillsFull reindex of all 6 element types (skills, agents, commands, rules, MCP servers, LSP servers) using the deterministic Rust enrichment pipeline
/perfect-skill-suggester:pss-searchSearch the PSS CozoDB index for skills, agents, commands, rules, MCP or LSP servers by keyword or full-text query
/perfect-skill-suggester:pss-setup-agentProfile an agent with best-fit skills
/perfect-skill-suggester:pss-setup-agent:execution/perfect-skill-suggester:pss-statusShow PSS index status and test matching
/perfect-skill-suggester:pss-status:binary-status/perfect-skill-suggester:pss-status:execution-protocol/perfect-skill-suggester:pss-status:test-mode/perfect-skill-suggester:pss-status:verbose-and-cache/perfect-skill-suggester:pss-suggest-agents-offStop suggesting agents — silences PSS prompt suggestions
/perfect-skill-suggester:pss-suggest-agents-onSuggest AGENTS on every prompt (default mode); turns skill suggestions off
/perfect-skill-suggester:pss-suggest-skills-offStop suggesting skills — silences PSS prompt suggestions
/perfect-skill-suggester:pss-suggest-skills-onSuggest SKILLS on every prompt; turns agent suggestions off
pss-agent-profilerAnalyzes agent definitions and generates .agent.toml profiles. Uses Rust binary for candidate scoring + post-filtering for mutual exclusivity, stack compatibility, and redundancy pruning across all 6 element types.
sh "${CLAUDE_PLUGIN_ROOT}/bin/pss-hook-dispatch.sh"
uv run --quiet --script "${CLAUDE_PLUGIN_ROOT}/scripts/pss_hook.py" --warm-index &
uv run --quiet --script "${CLAUDE_PLUGIN_ROOT}/scripts/pss_fetch_binaries.py" --session-start
uv run --quiet --script "${CLAUDE_PLUGIN_ROOT}/scripts/pss_hook.py" --post-compact
Comprehensive validation suite for Claude Code plugins, marketplaces, hooks, skills, and MCP servers. Includes 17 Python validators, 2 expert agents, and 190+ validation rules.
52 skills · 14 commands · 14 agents
Expert agent plus 60 preserved Claude Code documentation chapters (mods, plugins, hooks, skills, subagents, marketplaces, settings) for creating, fixing, improving and evaluating Claude Code mods and plugins.
69 skills · 1 command · 2 agents
MCP server that offloads bounded LLM tasks from Claude Code to cheaper local (LM Studio, Ollama, vLLM, llama.cpp) or remote (OpenRouter) models. Profile-based configuration with ensemble mode, auto-batching, and secret scanning.
19 skills · 25 commands · 6 agents · hooks
Four-phase PR review pipeline and full codebase audit pipeline for Claude Code. PR review: code correctness swarm, claim verification, skeptical external review, security analysis with deduplication. Codebase audit: file inventory, grep triage, parallel discovery swarm, verification, gap-fill, consolidation, TODO generation, and optional fix loop.
5 skills · 11 commands · 1 agent
Automatically reviews and fixes Claude's code changes using a separate Claude instance in a git worktree after commits. Two-phase pipeline: code correctness (Phase 1) then functionality verification (Phase 2).
1 skill · 2 agents · hooks
Universal terminal-menu system for Claude Code plugins. Any agent invokes scripts/menu_write.py via Bash (~25ms) to render a JSON menu spec to a tempfile; a bundled Stop hook emits it as systemMessage at main-session turn end — the menu appears in the user terminal exactly when they can type a reply. No subagent fork, no extended-thinking overhead, no token cost to the orchestrator.
2 commands · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
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
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
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
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.