verify-docs
Verify documentation claims against actual code, finding and fixing stale or incorrect docs. Audit docs for token efficiency — cut what strong LLMs already know, keep local specifics and gotchas. Use when asked to review docs, trim docs, or check docs are accurate.
info-gathering
>
mcp-design
Design an MCP server tool surface for an AI agent. Starts from common workflows, derives tool schemas, audits for completeness and safety. Use when designing a new MCP server or redesigning an existing one.
forgejo
Inspect Forgejo repositories through the REST API and web endpoints, especially Actions CI, task/run metadata, logs, package registry tags, haku-state CI, and Flux/image rollout debugging. Use when diagnosing Forgejo Actions failures, missing logs, branch badge state, package/image publish gaps, or when endpoint shape is unclear.
pave
>
readback
>
reverse_engineer
Systematic binary reverse engineering toolkit. Extract source code, understand functions, document protocols, compare versions. Uses strings, symbols, disassembly, and differential verification.
session_logs
Discover and analyze Claude Code session logs from ~/.claude/projects, including finding the current session and extracting tool calls, user messages, and conversation history
update_deps
>
knowledge_hygiene
Audit documentation, notes, runbooks, wiki-style knowledge bases, prompts, comments, UI/help copy, and other natural-language information systems for SSOT drift, duplication, stale claims, unclear ownership, and maintenance gaps. Produce prioritized, evidence-backed improvement suggestions with stable shorthand IDs like A, B, C so the user can choose what to execute.
ikea-3d-models
>-
ground-skill
>
branch_splitter
Split a large branch with many changes into independent, reviewable PRs. Use when preparing a messy development branch for code review, when asked to "split this into PRs", "make this reviewable", "break this up", or when a branch does too many unrelated things. Produces a DAG of branches/PRs that can be reviewed and merged independently.
props_evaluator
Operate the live props cluster as evaluator — fetch credentials from k8s, call the API at props.allegedly.works, trigger critic/grader runs, and inspect results.
debug_agent_traces
Debug props agent traces. Read LLM request/response history, parse tool calls, and "speak with dead" — resurrect a past agent conversation to ask follow-up questions about its decisions.
narrow_matchability
Propose narrowing of grader match_file_restriction for unrestricted TP/FP occurrences in a specimen. Produces verifiable, link-rich output that lets the user confirm each restriction is correct.
anipy-cli
This skill should be used when the user asks to play, watch, stream, search, download, or binge anime; continue watching or check anime history; install, setup, configure, update, or fix anipy-cli; change video player or set anime quality; troubleshoot anime playback issues; or mentions anipy-cli by name. Triggers on "play anime", "watch frieren", "stream one piece dubbed", "download anime episodes", "binge naruto 1-10", "show anime history", "next episode", "continue watching", "change player to mpv", "set quality to 1080", "anipy-cli not working", "player not found", "anipy-cli", "anime from terminal".
suno
This skill should be used when the user wants to compose songs for Suno AI, write lyrics, create style prompts, or generate Suno metatags. Supports J-pop, K-pop, EDM, ballads, rock, and Latin genres, plus album/EP composition, variations, and song continuations. Also handles reference-based composition ("like YOASOBI", "in the style of Aimer") and J-pop tier presets ("anisong", "mainstream", "doujin"). Triggers on "write a song", "Suno prompt", "Suno metatags", "style of music", "song lyrics", "Suno AI", "acoustic version", "create an album", "extend this song", "like [artist]", "in the style of", "/suno", "anisong", "doujin", "negative prompting", "ad-libs".
kana-review
>-
project-creator
|
create-skill
Use when creating a new skill or updating an existing skill
frontend-design
Use when the user asks to build web components, pages, or applications that need distinctive, production-grade frontend interfaces with high design quality
handoff-to-worktree
Use when explicitly asked to hand a task to a new Pi agent in a newly created Herdr-managed Git worktree.
herdr
Use when the user explicitly mentions Herdr, asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent, or asks to create, open, list, remove, or otherwise manage a Git worktree. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.
handoff
Use when explicitly asked to compact the current Pi session into a local handoff document that a fresh agent can use to continue the work.
playwright
Reference skill for browser automation: web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
plan
Use when turning a clarified implementation request, feature idea, bugfix, refactor, workflow change, or design discussion into an execution-ready plan that a fresh coding agent can implement autonomously, especially before running /goal.
test-driven-development
Use when implementing a feature or bugfix that involves writing meaningful application logic
diagnose
Use when debugging bugs, failures, exceptions, flaky behavior, regressions, or performance problems where the cause is not already proven.
manage-scheduled-tasks
Use when creating, editing, validating, manually running, or debugging Pi scheduled task Markdown files managed by the scheduled-tasks extension.
agent-engineering
Use when designing, building, debugging, or reviewing AI coding agent harnesses — single-agent shape (tools, prompts, context, hooks, model selection) or multi-phase workflows (orchestration, subagents, verifiers, ticket-to-PR pipelines). Covers model-specific guidance for Claude 4.x and GPT-5.x families, and platform-specific patterns for Claude Code, the Claude Agent SDK, and Pi. Invoke when the user asks about harness design, scaffold patterns, agent loops, subagent orchestration, verification strategy, context compaction, plan/implement/verify pipelines, or how a particular model changes harness choices.
review
Use when reviewing code changes, a working tree, branch, commit range, pull request, patch, or implementation against acceptance criteria. Prepares evidence, runs deterministic checks, invokes the saved review workflow, and presents its findings.
challenge
Use when stress-testing a concrete plan, proposal, design, architecture decision, or implementation approach before implementation. Challenges material assumptions, failure modes, alternatives, and evidence gaps; use review for completed changes.
clarify
Use when requirements, scope, product behavior, edge-case policy, acceptance criteria, or design intent are fuzzy and need an interview before planning or implementation.
create-html-artifact
Use when the user asks to create or polish a standalone HTML artifact such as an HTML report, interactive explainer, visual plan, dashboard, slide deck, diagram, prototype, or throwaway HTML tool.
create-jira-ticket
Use when creating a Jira ticket to plan upcoming work. Guides ticket drafting with clear structure, self-contained context, and testable acceptance criteria, then creates the ticket via the available Jira/Atlassian broker tool.
hook-manager
>-
plugin-manager
>-
memento
>-
aida
This skill routes /aida commands to appropriate handlers - configuration,
skill-manager
>-
expert-registry
>-
knowledge-sync
>-
knowledge-curator
>-
permissions
>-
agent-manager
>-
claude-md-manager
>-
reclaim-tasks
Manage tasks in Reclaim.ai calendar scheduling app. Use when creating, updating, listing, completing, or deleting Reclaim tasks, or working with calendar scheduling, task priorities, time blocking, or task duration management.
conport-memory
Access Context Portal (ConPort) as persistent project memory via MCPorter. Load/update project context, log decisions and progress, track patterns. Use PROACTIVELY at session start to load context and throughout work to log decisions. Combats AI amnesia across sessions.
mcporter
Use when you need to access MCP servers without installing them directly in Claude Code. MCPorter provides CLI access to any MCP server via npx, enabling tool discovery, direct calls, and ad-hoc connections. Use for accessing external MCP capabilities like browser automation, API integrations, or any MCP-based tooling.
Page 1267 of 1714 · 85671 results
