Skill Claude Code
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea"…
Skill Claude CodeCodex
Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
Skill Claude CodeCodex
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until 95% confidence about the underlying intent. Use before any plan/spec exists when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user…
Skill Claude CodeCodex
Defines the Verification Contract that keeps a multi-agent run honest — dispatcher-owned acceptance assertions, a parity/touchpoint inventory for "behave like X" requests, structured upward returns, and a requirement-regression reset. Use when orchestrating specialists through a dispatcher (agent-hub), when a "make X…
Skill Claude CodeCodex
Makes Claude Code a first-class peer in the local coms agent pool — discover pi colleagues, ask or delegate to them mid-task, and answer their inbound questions. Use when running inside a bridged herdr pane (a coms-claude-bridge is attached), when a task would benefit from asking a running pi peer (researcher…
Skill Claude CodeCodex
Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.
Skill Claude CodeCodex
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, when parallel work is possible, or when the user wants to grill a plan before implementation.
Skill Claude CodeCodex
Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
Skill Claude CodeCodex
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, only exist as a vague idea, or need to be grilled before planning.
Skill Claude CodeCodex
Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
Command Claude Code
Install/status the Hermes liaison or turn its Telegram askuser bridge on/off.
Command Claude Code
Inspect or safely install the fail-closed Hermes watchdog.
Command Claude CodeOpenCode
Install/status the Hermes liaison or turn its Telegram askuser bridge on/off.
Command Claude CodeOpenCode
Inspect or safely install the fail-closed Hermes watchdog.
Skill Claude CodeCodex
Drafts deterministic Agent Fleet workflows by adapting the nearest existing flow and proving the draft compiles and dry-runs. Use when creating or changing a just flow workflow or translating an operator request into agent phase prompts.
Skill Claude CodeCodex
Connect a ChatGPT Desktop or Android conversation to an existing Agent Fleet Pi session for instructions, bounded monitoring and on-demand summaries. Use when the user asks to connect to Fleet, send a Pi instruction, inspect progress or resynchronize the selected session.
Skill Claude CodeCodex
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or…
Skill Claude CodeCodex
Sets up repository AI rules from the packaged Fleet catalogue — discover target evidence, propose semantic adaptations, grill unresolved decisions one question at a time, then diff, apply, and verify. Use for initial .ai/rules setup and repeated additions or updates via an optional change request.
Command Claude Code
Use when a change needs an evidence-backed list of affected areas and verification priorities. Inputs: requested change or pending diff; optional ref/range if supported by the target VCS. An invocation does not authorize writes or external actions.
Command Claude Code
Use when reviewing a selected documentation scope for consistency. Inputs: requested files or documentation area; optional accepted decision or change to check against. This command is read-only and authorizes no external actions.
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: