plugin skills

1,477 tagged plugin, measured the same way as everything else here.

Browse within: dsh 122deepseek-harness 118dsh-plugin 115dsh-skill 114knowledge-management 69skill 65opencode 56marketplace 54sdlc 51aisecurity 50cybersecurity 50ai-development 47ai-collaboration 44epistemology 44

click-to-fix

313

johnkozaris/web-interact-plugin

Skill Claude CodeCodex

Part of web-interact

Click any element in the browser to trace it back to its source code component. The user visually clicks an element in their browser, and the CLI returns metadata (component name, source file, line number) that you use to locate and open the code. Trigger phrases: "click to fix", "inspect element", "find component"…

not rated 2 5mo ago A 117 tokens original MIT

mode

314

johnkozaris/web-interact-plugin

Skill Claude CodeCodex

Part of web-interact

Show or switch the web-interact browser engine between default (Playwright) and assistant (Patchright). Use when the user asks to change browser mode, enable stealth/assistant mode, or check which engine is active.

not rated 2 5mo ago A 46 tokens original MIT

Hook Development

315

timgranlundmarsden/claude-agent-flow

Skill Claude CodeCodex

Part of agent-flow

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDEPLUGINROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop…

not rated 2 3mo ago A 117 tokens

timgranlundmarsden/claude-agent-flow

Skill Claude CodeCodex

Part of agent-flow

Convert a Claude Code session JSONL log into an enriched visualiser JSON file for docs/public/logs/. Runs logconverter.py for the base structure, then enriches with correct agent models, brainstorming Q&A (question events), adversarial loop transitions, parallel timing, and a story-focused title/subtitle.

not rated 2 3mo ago A 68 tokens

Skill Development

317

timgranlundmarsden/claude-agent-flow

Skill Claude CodeCodex

Part of agent-flow

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

not rated 2 3mo ago A 63 tokens

auto-recall

318

hydra-db/hydradb-claude-code

Skill Claude CodeCodex

Part of hydradb

Retrieve relevant HydraDB context when answering would benefit from prior conversations, workspace docs, project decisions, team conventions, or user preferences not fully present in the current chat. Use proactively for substantive project questions or when continuity may matter.

not rated 2 6d ago A 49 tokens original Apache-2.0

setup

319

hydra-db/hydradb-claude-code

Skill Claude CodeCodex

Part of hydradb

Configure the HydraDB Claude Code plugin for the current workspace. Use when the user wants to enable HydraDB memory, fix configuration, or create a workspace config file.

not rated 2 6d ago A 35 tokens original Apache-2.0

status

320

hydra-db/hydradb-claude-code

Skill Claude CodeCodex

Part of hydradb

Deprecated alias for /hydradb:doctor. Inspect HydraDB plugin configuration, active settings, and sync state. Prefer /hydradb:doctor; this still works.

not rated 2 6d ago A 37 tokens original Apache-2.0

claude-daily

321

longyunfeigu/claude-daily

Skill Claude CodeCodex

Use when the user wants a daily report, session card, work recap, AI coding activity summary, or PRD-compliant Compound Daily ingestion payload covering local AI coding sessions (Claude Code + Codex CLI). The skill drives the full 6-step pipeline (prepare → generate → emit → upload) end-to-end inside a single Claude…

not rated 2 23d ago A 75 tokens original Apache-2.0

Guard Rules

322

hex/claude-guard

Skill Claude CodeCodex

Part of claude-guard

This skill should be used when a command is blocked by claude-guard, when the response contains "BLOCKED by claude-guard", when the user asks "why was my command blocked", "what commands are blocked", "guard rules", "safety rules", or when Claude is about to execute a potentially dangerous command. Covers git force…

not rated 2 1mo ago D 190 tokens original MIT

conversation-recall

323

danilop/claude-total-recall

Skill Claude CodeCodex

Part of claude-total-recall

Searches past Claude Code conversations using semantic search. Activates when recovering context after compaction, finding discussions from previous sessions, discovering cross-project preferences, or when user says "recall", "remember", "how did we". Delegates to subagent for background context gathering.

not rated 2 7mo ago A 60 tokens original MIT

customize

324

bouob/claude-statusline

Skill Claude CodeCodex

Part of claude-statusline

This skill should be used when the user asks to customize claude-statusline appearance, or mentions: change theme, switch theme, bar style, separator, statusline colors, dracula, nord, catppuccin, hide segment, show segment, rate-limit settings, rainbow settings, responsive.

not rated 2 1mo ago A 63 tokens original MIT

speech-setup

325

jason-c-dev/claude-code-speak

Skill Claude CodeCodex

Configure or change Claude Speech — install deps, set the Deepgram API key, pick a voice and a mode (A/B/C), regenerate hooks.json, smoke test.

not rated 2 4mo ago C 38 tokens original MIT

furniture

326

LuisEnVilla/furniture-designer-plugin

Skill Claude CodeCodex

Part of furniture-designer

Professional furniture design assistant. Use when the user wants to design furniture, validate structural integrity, generate bills of materials, optimize panel cuts, get assembly instructions, consult assembly specifications, or build 3D models in FreeCAD. Triggers on keywords like "design", "furniture", "cabinet"…

not rated 2 5mo ago A 157 tokens original MIT

look-at

327

mbailey/show-me

Skill Claude CodeCodex

Part of show-me

Observe what the user is currently viewing (screen context). Use when the user says "look at my screen" or you need to verify what they're viewing.

not rated 2 13d ago A 34 tokens original MIT

show-me

328

mbailey/show-me

Skill Claude CodeCodex

Part of show-me

Visual context sharing. LOAD when user says "show me", "open in browser", or "look at".

not rated 2 13d ago A 25 tokens original MIT

flush

329

ogham-mcp/ogham-superpowers-bridge

Skill Claude CodeCodex

Part of superpowers-memory

Manually flush the superpowers-memory staging buffer. Orchestrator-only defensive safety valve before branch close; independent of the automatic N=3 / branch-finish cadence. Surfaced as /superpowers-memory:flush.

not rated 2 3mo ago A 46 tokens

superpowers-memory

330

ogham-mcp/ogham-superpowers-bridge

Skill Claude CodeCodex

Part of superpowers-memory

Orchestrator-only bridge to Ogham durable lessons for the superpowers subagent pipeline. Use ONLY from the orchestrator/controller (never a subagent) to recall per-task lessons before dispatch and to flush captured lessons. Exposes two verbs - recall and flush.

not rated 2 3mo ago A 58 tokens

trrrrrryg/dsh-visual-skin

Skill Claude CodeCodex

Open and orchestrate the local DeepSeek Harness Skin Studio, co-design a structured DSH theme through MCP or JSON CLI, show live preview in the independent web UI, and safely apply or restore only after the human confirms in that visible UI. Use when the user asks to design, preview, change, inject, install, repair…

not rated 2 3d ago A 98 tokens original MIT

wejob

334

WeJob-IT/WeJob-MCP

Skill Claude CodeCodex

Part of wejob

Use WeJob to search public jobs, formations, and company profiles. Trigger when the user asks for WeJob data, jobs/offres, formations, companies/entreprises, or career discovery on WeJob.

not rated 1 1mo ago A 45 tokens original MIT

analyze-spending

335

bankstatemently/plugins

Skill Claude CodeCodex

Part of bankstatemently

Use when the user asks to categorize spending, group by merchant or category, rank top merchants, or show monthly trends on converted statements. Do not use for first-time PDF conversion, period reconciliation, or benchmark scoring.

not rated 1 4d ago A 48 tokens original MIT

benchmark-accuracy

336

bankstatemently/plugins

Skill Claude CodeCodex

Part of bankstatemently

Use when the user asks to convert and score a published Bankstatemently benchmark statement. Do not use for ordinary user-statement conversion, spending analysis, or reconciliation.

not rated 1 4d ago A 37 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: