architect-review
169Skill Claude CodeCodex
use when user ask to review spec.
not rated 9
+1 3d ago A 10 tokens
original MIT
Skill Claude CodeCodex
Distill topic-neutral stylistic mechanics from examples into one portable Writing Skill that can be applied to any subject.
not rated 8 1mo ago A 27 tokens
original MIT
spec-graph
171Skill Claude CodeCodex
Use this skill whenever the project uses spec-graph for managing requirements, decisions, phases, changes, interfaces, states, tests, and other semantic entities in a typed graph. Trigger when the user mentions spec-graph, or when the task involves any of: tracking requirements or decisions, planning development…
not rated 8 8d ago A 147 tokens
autoreview
172Skill Codex needs its repo
Run structured AI code review as an advisory closeout gate for local diffs, PR branches, or commits when the user asks for autoreview, Codex review, second-model review, or pre-ship validation.
not rated 8 5d ago A 46 tokens
original Apache-2.0
app-audit
173Skill Claude CodeCodex
Evidence-driven application audit protocol for security, authorization, privacy, concurrency, state integrity, reliability, performance, accessibility, visual consistency, responsive behavior, and release readiness. Use for incremental checks, pre-merge review, pre-launch audits, high-stakes deep audits, AI-generated…
not rated 7 1mo ago A 92 tokens
Email Composer
174Skill Claude CodeCodex
Draft professional emails for various contexts including business, technical, and customer communication. Use when the user needs help writing emails or composing professional messages.
not rated 7 today A 31 tokens
original MIT
Seashail
175Skill Claude CodeCodex
Trade crypto safely using a local Seashail MCP wallet boundary (spot, perps, NFTs, DeFi; policy-gated).
not rated 7 4mo ago A 31 tokens
original Apache-2.0
Skill Claude CodeCodex
Intent-aware destination verification for AI agents. Use before an agent opens a URL to assess destination risk, confirm task alignment, and obtain an explicit ALLOW or DENY decision before navigation.
not rated 6 4mo ago A 43 tokens
original Apache-2.0
viacheslav-tronko/claude-code-harness
Skill Claude Code
Pre-implementation blueprint for AI coding agents on legacy codebases. Use WHENEVER user asks HOW to implement, plan, or design — /howto.implement, /blueprint, "implementation plan / analysis / strategy / approach", "how to implement / add / build / refactor", pastes Jira / user story / RCA / SPEC asking "plan this"…
not rated 6 3mo ago A 105 tokens
original MIT
specflo-execute
178Skill Claude CodeCodex
Use at a specflo project's execute phase, when turning a validated plan.md into committed, verified code one task at a time. Triggers include "execute the plan", "start building", "work the next task", or specflo status showing the execute phase. Do NOT use before a plan has been validated, or for trivial fixes…
not rated 6
+1
changed yesterday A 78 tokens
llm-app-patterns
179hybridlabor-api/bdb-dev-optimized-agent-skills
Skill Claude CodeCodex
Production-ready patterns for building LLM applications, inspired by Dify and industry best practices.
not rated 6
+1 yesterday A 36 tokens
original Apache-2.0
appwrite-backend
180Skill Claude CodeCodex
Appwrite backend development and operations, including destructive account/data erasure and MCP server wiring for coding agents. Use for Appwrite SDK work; any Appwrite CLI command or failure must route through the CLI safety branch.
not rated 5
changed 4d ago A 48 tokens
original MIT
goal-oriented
181Skill Claude Code
MUST use for ANY user request. This is a rigid requirement that applies to all tasks and conversations.
not rated 5
+1 1mo ago A 24 tokens
original MIT
Skill Claude Code
Optional autonomy control plane — configure, plan, launch, monitor, recover, or stop local CLI-agent workers through SwarmVault's durable supervisor. Use for fit/budget-aware platform + model + reasoning-effort routing; a consistent pre-start/live/boundary/on-demand board with ticket drill-down; TOLD/MEASURED/EST…
not rated 5 1mo ago A 109 tokens
original MIT
capture-lessons
183Skill Claude Code
Ship and capture lessons workflow. Creates the PR, updates lessons learned, updates documentation, generates the sprint retrospective, and updates the backlog. Use at the end of a sprint cycle, or when the user says "ship", "capture", "lessons", "retro", "retrospective", "wrap up", or "done with this sprint". Also use…
not rated 5 2mo ago A 100 tokens
original Apache-2.0
AravindKurapati/claude-best-practices
Skill Claude Code
Researches computational pathology and health AI literature using HuggingFace Papers MCP and Exa web search. Use when user says "find papers on", "research", "what's the latest on", "literature review", "survey", or asks about methods like MIL, SSL, WSI analysis, attention-based pooling, patch embedding, weakly…
not rated 5 3mo ago A 167 tokens
Skill Claude CodeCodex
Author, review, and improve Botpipe workflows. Use when Codex is asked to create packaged or workspace-local Botpipe workflows, convert codebases into workflows, design provider-heavy producer/verifier steps, write Botpipe prompts/contracts, inspect Botpipe traces, or apply Codex CLI/gpt-5.5 workflow patterns.
not rated 5 5d ago A 72 tokens
original Apache-2.0
ai-harness
186Skill Codex
Use when designing, implementing, configuring, testing, or extending applications built with @purista/harness and its provider adapters, including agents, workflows, tools, skills, models, state, sandbox, telemetry, and custom adapter packages.
not rated 5 3d ago A 51 tokens
original Apache-2.0
deal-briefer
187violetfleming47/deal-intelligence
Skill Claude CodeCodex
Forensic deep dive on a single deal from the Deal Intelligence pipeline. On-demand only. Triggered by 'deep dive on [deal]', 'prep me for the [company] call', 'analyse [deal]', 'what's happening with [company]', or any request for a single-deal analytical deep dive backed by evidence from di tables.
not rated 5 3mo ago A 74 tokens
original MIT
babysit-pr
188Skill Claude CodeCodex
Resolve reviewer comments on a pull request or pasted feedback using a six-step evidence-grounded protocol. Use when asked to resolve review feedback, address reviewer comments, process PR comments, triage review feedback, apply review suggestions, handle code review feedback, decide which review comments to accept or…
not rated 5
changed today A 161 tokens
original Apache-2.0
Skill Claude Code
Resolve a GitHub repository in the security graph and list the CVEs recorded against it, confirming from the graph's dependency data which vulnerable versions are actually installed. Produces the finding set that a reachability review then judges against the source.
not rated 5 today A 54 tokens
original Apache-2.0
Skill Claude CodeCodex
Use when you've drafted or improved a skill locally and want to publish it to a shared pack — walks through validating the draft, finding the target pack, running the promote script, and reviewing the staged diff before it ships.
not rated 5 1mo ago A 51 tokens
original MIT
humanizer
191Skill Claude Code
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
not rated 5 6mo ago A 92 tokens
Skill Claude CodeCodex
Retrieves a company's most recent 8-K current report and its Exhibit 99.1 earnings press release text from SEC EDGAR via edgartools. Use whenever the task needs an official earnings press release, 8-K event items, or a transcript fallback when earningscall has no coverage for the ticker.
not rated 5 1mo ago A 72 tokens
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: