Skill Claude Code
Load when you investigate with a human waiting: share your read and ask the next question while the evidence comes in, instead of going silent until it is complete.
not rated 2
changed yesterday A 38 tokens
2Stars on the repository
27Mods indexed here, across every type
todayLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
goal-writing
02Skill Claude CodeCodex
Load when turning intent into an executable goal for an agent, delegated run, work item, experiment, or handoff. Use to define outcome, evidence, constraints, anti-goals, stop conditions, and reporting shape before work begins.
not rated 2
changed yesterday A 50 tokens
Skill Claude CodeCodex
Use when grilling should be grounded primarily in project artifacts. Loads /grill, checks project vocabulary and prior decisions first, and spawns bounded explorers when the answer should come from docs.
not rated 2
changed yesterday A 43 tokens
Skill Claude CodeCodex
Use when grilling should be grounded in evidence. Loads /grill, then checks the plan, terms, and assumptions against project artifacts first and primary sources when needed.
not rated 2
changed yesterday A 39 tokens
grill
05Skill Claude CodeCodex
Use in conversation to stress-test a plan or direction. Interviews the human in rounds, asking every question that is ready with a recommended answer, until no decision is left open.
not rated 2
changed yesterday A 38 tokens
handoff
06Skill Claude Code
Use when the next phase belongs to a different interactive lead: writes a transition brief, runs applicable pre-phase checks, and hands off to a new interactive session.
not rated 2
changed today A 35 tokens
Skill Claude CodeCodex
Load when a report, doc, or explanation runs past one screen, or will be browsed rather than read: choose the form for each beat (prose, diagram, table, mockup), put the answer first and depth behind it.
not rated 2
changed yesterday A 53 tokens
Skill Claude CodeCodex
Use before acting on human instructions: separate what they said from what they meant.
not rated 2
changed yesterday A 20 tokens
Skill Claude CodeCodex
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
not rated 2
changed today A 32 tokens
llm-writing
10Skill Claude CodeCodex
Load before you write a commit message, PR body, changelog entry, issue, report to the user, doc, README, AGENTS.md or .context/ page, KB page, or prompt: choose plain words, write for the reader's context, and strip default LLM phrasing.
not rated 2
changed yesterday A 64 tokens
Skill Claude CodeCodex
Load after writing, moving, or linking markdown pages or Mermaid diagrams, before committing them: validates links, the KB link graph, and diagram syntax.
not rated 2
changed today A 33 tokens
qi-layer
12Skill Claude CodeCodex
Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or a Claude-specific CLAUDE.md: keep intent docs minimal and load-bearing.
not rated 2
changed yesterday A 36 tokens
Skill Claude CodeCodex
Load on agents that make durable changes to a project's files, so the colocated AGENTS.md and .context/ docs stay true for the next cold agent.
not rated 2
changed yesterday A 36 tokens
reflect
14Skill Claude Code
Use when the user invokes it before you report: checks you delivered what they needed, not only what they literally asked, and routes knowledge capture.
not rated 2
changed yesterday A 31 tokens
shared-dao
15Skill Claude CodeCodex
Load when a concept has two names, a name has two meanings, or you are about to coin a term: resolve it early, one name per concept, in the project's vocab files.
not rated 2
changed yesterday A 42 tokens
Skill Claude CodeCodex
Use when a workspace has changes from other agents: safe orientation, preserving unfamiliar files.
not rated 2
changed yesterday A 21 tokens
Skill Claude CodeCodex
Load when the human wants something to browse rather than read: an HTML page that explains or presents information, with its delivery.
not rated 2
changed yesterday A 29 tokens
Skill Claude CodeCodex
Load when work must survive compaction or crashes or be shared with other agents: findings, decisions, and artifacts go in the work directory, not in context.
not rated 2
changed today A 36 tokens
zoom-out
19Skill Claude Code
Use when orienting in an unfamiliar area: fans out parallel explorers across structure, knowledge, and history, then synthesizes one orientation map.
not rated 2
changed yesterday A 31 tokens
correct
20Skill Claude Code
Use when the human wants the mistakes agents keep repeating fixed for good. Works the KB corrections register: fixes each recurring class at the strongest level that holds (remove the wrong way, an automated check, a tool permission, a written rule last), proves each fix on a real past mistake, and updates the…
not rated 2
changed yesterday A 65 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: