Skill Claude Code
Scaffolds a Claude Code / Cowork plugin bundle from a short YAML spec or from an existing agent definition''s.
not rated 43
+2 2d ago A SkillSpector: warn 159 tokens
original MIT
Skill Claude CodeCodex
Run a web task as a multi-step browser loop on MCPs you already pay for. No new runtime, no API double-billing, no new always-on MCP. Two v1 modes: monitor (watch a page, report a grounded diff) and QA (walk a site, check CTAs/links/schema, flag mismatches).
not rated 43
+2 2d ago A 206 tokens
original MIT
discover
27Skill Claude Code
Proactive skill and automation discovery. Scans 6 data sources (sessions, Linear, Slack, Gmail, Granola, Calendar).
not rated 43
+2 2d ago A 100 tokens
original MIT
experiment
28Skill Claude Code
Tracks structured experiments for content, messaging, and workflow iterations in a SQLite database. Logs hypotheses.
not rated 43
+2 2d ago A 121 tokens
original MIT
learn
29Skill Claude Code
Process raw source material (transcripts, docs, articles, competitor pages, meeting notes) into structured context.
not rated 43
+2 2d ago A SkillSpector: warn 74 tokens
original MIT
level
30Skill Claude Code
Assesses a Claude Code environment''s maturity on a fun 0-10 ladder calibrated to the 4-systems.
not rated 43
+2 2d ago A SkillSpector: pass 169 tokens
original MIT
Skill Claude Code
Scans skill-usage.jsonl + recall.db transcripts for opportunities to create new skills, deprecate unused ones, or formalize manual patterns into workflows. Detects three signal classes: repeated manual sequences not covered by existing skills, skills used <2× in 30 days (deprecation candidates), high-friction sessions…
not rated 43
+2 2d ago A SkillSpector: warn 136 tokens
original MIT
Skill Claude Code
Dynamically guides a person through cloning + setting up the claude-code-marketing-quickstart.
not rated 43
+2 2d ago A SkillSpector: warn 164 tokens
original MIT
runbook
33Skill Claude Code
Synthesizes documentation sources (SKILL.md files, MCP configs, code comments, client docs) into structured.
not rated 43
+2 2d ago A SkillSpector: warn 119 tokens
original MIT
steal
34Skill Claude Code
Systematically extracts and adapts reusable skills, frameworks, benchmarks, and patterns from external GitHub.
not rated 43
+2 2d ago A SkillSpector: pass 148 tokens
original MIT
wiki
35Skill Claude Code
Per-client-folder hygiene and semantic drift detection. Runs structured checks inside a single client engagement.
not rated 43
+2 2d ago A SkillSpector: pass 129 tokens
original MIT
batch-run
36Skill Claude Code
Fan out any skill across N entities in parallel. Takes a skill name + entity list (products, competitors, pages.
not rated 43
+2 2d ago A SkillSpector: pass 136 tokens
original MIT
Skill Claude Code
Orchestrates a Lane-3 client context engagement end to end — scaffolds the Pattern A client folder, drives the.
not rated 43
+2 2d ago A SkillSpector: pass 223 tokens
original MIT
orchestrator
38Skill Claude Code
Routing convention that maps user intent to the correct skill or multi-skill chain. Reads the skill-catalog.
not rated 43
+2 2d ago A 115 tokens
original MIT
premortem
39Skill Claude Code needs its repo
Imagine failure first to surface guardrails before plan execution or deliverable ship. Two modes: --plan (5 strategic domains for plan files in /.claude/plans/) and --output (5 execution domains for shippable deliverables like LinkedIn posts, AEO articles, landing-page-copy, proposals, positioning). Produces a ##…
not rated 43
+2 2d ago A SkillSpector: pass 209 tokens
original MIT
Skill Claude Code
Creates reusable AI prompts using a 7-section architecture (role, context, task, format, constraints, examples.
not rated 43
+2 2d ago A SkillSpector: pass 113 tokens
original MIT
Skill Claude Code
Orchestrates sales enablement asset creation by routing to dedicated sub-skills: /sales-deck for presentation.
not rated 43
+2 2d ago A 123 tokens
original MIT
Skill Claude Code
Designs multi-step AI workflows with chained prompts for Clay, AirOps, n8n, or other automation tools. Produces.
not rated 43
+2 2d ago A 118 tokens
original MIT
recall
43Skill Claude Code
Searches and recalls context from past Claude Code sessions via a SQLite FTS5 index with BM25 ranking. Produces.
not rated 43
+2 2d ago A SkillSpector: pass 124 tokens
original MIT
think
44Skill Claude Code
Temporal-trajectory-aware recall. Routes a question through a zero-LLM-cost intent classifier (temporal / knowledgeupdate / other). Temporal questions ("when did X last Y", "what changed since Z") get spliced answers from chronologically-sorted client history.md + goals/MMYY-NN-cycle.md + dated memory pages +…
not rated 43
+2 2d ago A SkillSpector: pass 190 tokens
original MIT
today
45Skill Claude Code
Generates a daily productivity briefing by chaining Gmail, Calendar, Linear, and Slack into a single actionable.
not rated 43
+2 2d ago A SkillSpector: pass 104 tokens
original MIT
weekly-plan
46Skill Claude Code
Orchestrates weekly planning by scanning client communications (Gmail, Slack, Granola, Calendar), checking Linear.
not rated 43
+2 2d ago A 118 tokens
original MIT
why-slow
47Skill Claude Code
In-session diagnostic for "why is Claude hanging / slow right now?" Reads recent startup-timing.
not rated 43
+2 2d ago B 93 tokens
original MIT
Skill Claude Code
Runs a structured workspace audit across 5 dimensions: root hygiene, client folder structure compliance, skill.
not rated 43
+2 2d ago A SkillSpector: pass 110 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: