Product & Planning

lucaswall Bundle

Reviews all frontend elements (UI, UX, accessibility, visual design, responsiveness, performance, visual QA from screenshots) using an agent team with 4 domain-specialized reviewers. Creates Linear issues in Backlog state for findings. Use when user says "review frontend", "check UI", "review UX", "audit accessibility", "check responsive", or "review screens". Falls back to single-agent mode if agent teams unavailable.

lx-wnk Skill

Obsidian vault access via Local REST API using curl — read, search, create, or update notes in the knowledge base. Trigger on ANY of these: user mentions "obsidian", "vault", "knowledge base", "my notes", or "note" in a save/lookup context; user asks to "save", "persist", "document", "note down", or "look up" information; phrases like "note this down", "add this to my knowledge base", "search my notes", "check if I have notes on X", "create a note"; CLAUDE.md says to search or store in Obsidian before/after tasks — do it proactively; starting a task where prior context might exist → search first; mid-task discovery of a non-obvious insight, gotcha, root cause, or workaround → save it; finishing a task with decisions or learnings worth remembering → persist it; something written to CLAUDE.md or project docs → also save it for cross-project search.

anmarhani Skill

Requirements phase — a clarifying, options-first stakeholder interview that removes confusion and assumptions (not a relentless grilling) and produces a validated SRS + per-feature specs with EARS acceptance criteria and ISO 25010 NFRs. Use to start a new project's requirements, gather/analyze/specify/validate requirements, stress-test a plan, or mine requirements from an existing codebase (brownfield). Also handles requirement changes after validation.

autocss-com Skill

Cross-session continuity and backlog/process rules — how project state, outstanding work, and documentation survive between sessions. Covers the session handoff, PROGRESS.json as the single backlog source, the GitHub Issues/Projects mirror, documentation maintenance, and the next-phase prompt. Use at the start and end of every session, and whenever tracking or handing off work.

bongsuchoi Bundle

Clarify materially ambiguous product, feature, workflow, or brownfield improvement requests into an approved task contract, or synthesize an already-resolved conversation into that contract without restarting discovery. Use when the user asks for an interview, requirements, a specification, help deciding what to build, asks you to grill or stress-test an idea, plan, or design, or when unresolved goals, constraints, non-goals, acceptance criteria, or product decisions would materially change the result. Do not use for a narrow already-specified edit, pure diagnosis, or a decision already settled by project rules.

bongsuchoi Bundle

Find, inspect and summarize local coding-agent sessions across Codex, Claude, OpenCode, Senpi and supported transcript stores. Use for exact session recall, prior-work evidence, child-session discovery and transcript lookup.

danielc000 Skill

The operating doctrine for the Loom Platform Auditor — a scheduled, read-mostly transcript reviewer with three narrow daemon-local writes. Load at the start of any platform-audit session to scan recent session transcripts across projects for Loom bugs, agent friction, vague skill/prompt instructions, and recurring prompts worth saving as presets — filing structured, deduped findings onto the Platform backlog and emitting preset suggestions. Your agent prompt supplies the cadence/scope specifics; this is the cross-project HOW.

haochenhust Bundle

Rigorous problem-analysis methodology for any substantive decision — housing, education, medical, career, investment, tech/architecture, debugging, research, life choices. Governs HOW Claude works (process), not the output format. Forces deep investigation (specific numbers/cases, not vibes), stakeholder mapping, main-contradiction + transition analysis, staged strategy, worst-case wargaming, concentrated main attack, and concrete next-step actions. Triggers — /mma slash command, 用马哲/毛选/矛盾分析/实事求是/一分为二 keywords, or proactively for any weighty judgment task.

kromatic-innovation Skill

Canonical body structure and quality gate for filing a GitHub issue an agent can build from cold. Use whenever a persona files work to the backlog rather than doing it now.

mehdiforoozandeh Skill

Test whether the user's mental model still matches work that already exists — code the agent wrote, a PRD, a plan, a document tree — usually because they delegated it, skimmed it, or were away while it was built. Derives a tree from the artifact, then asks one multiple-choice question at a time: general framing first, then hard into the decision points, with distractors drawn from the alternatives actually rejected, or from the conventional choice this artifact departed from. Every wrong answer is triaged — did the agent drift from the user's intent (→ punch list), or is it a gap in the user's knowledge (→ explained)? Needs an artifact that already exists: for a subject nothing was built for use `tutor`, and for a plain re-orientation with no questions asked use `catchup`. Triggers: /quiz-me, "quiz me on what we built", "test me on this plan", "grill me on the code you wrote", "do I actually understand what we built", "am I still in sync with what you wrote", "I approved that without reading it".

neotherapper Skill

Use when the user wants a whole learning path rather than one lesson — "I want to become an AI engineer", "give me a roadmap for X", "show me the curriculum", "what should I learn next", "show the learning tree", "/paidagogos:path". Also use when the user asks what a curriculum covers, which concepts feed which, or what resources exist for a topic already in a curriculum. Renders a curriculum as an interactive tree in the browser and routes individual concepts to paidagogos:micro for teaching.

northseadl Bundle

Web scraper with SPA/JavaScript rendering, page interaction, and JS execution. Two-tier engine (HTTP → Playwright browser). Smart discovery, batch fetch, interactive content extraction, OpenAPI parsing. Use when read_url_content fails, SPA rendering needed, or page interaction required.

liyong-labs Bundle

One-pass directory + document + file reorganization — git mv renames, tmp archiving, script sorting, debug artifact cleanup, document classification and archiving (MRD/PRD/ARCH/DESIGN/TEST/RESEARCH), env.md/deploy.md sync. Triggers: directory reorganization, file archiving, tmp cleanup, document classification, README, templates, env, deploy, git mv, file reorganization, archive

umputun Skill

Update project CLAUDE.md with strategic knowledge discovered during this session — or CLAUDE.local.md when the discovery is per-developer/per-checkout and that file already exists. Defers to any project- or user-defined memory-placement guidance instead of overriding it. Use when user says "learn", "save knowledge", "update claude.md", "capture learnings", or at end of significant work sessions. Also used by commit skill for pre-commit knowledge capture.

umputun Skill

Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being fixed now. Owns the item format and the create-then-delete lifecycle.

kenmulford Bundle

Generate a Project+ style weekly project status report as .docx — executive summary, RAG with trend vs prior week, accomplishments, upcoming, risks vs issues (distinguished), asks, metrics, and dependencies. Use whenever a user needs to produce a status report, weekly update, steering committee update, stakeholder update, or "where are we" document. Triggers include "status report", "weekly status", "exec update", "sponsor update", "RAG status", "this week's update". Enforces never-invent discipline and structural consistency across reporting weeks so stakeholders can scan the same sections in the same order every time.

kenmulford Bundle

Generate a Project+ style Stakeholder Engagement Plan as a .docx, with a stakeholder register, power/interest grid, current-vs-desired engagement levels, and a communication plan per stakeholder. Use whenever a user needs to plan how to manage, communicate with, or influence project stakeholders — triggers include "stakeholder engagement plan", "stakeholder register", "stakeholder analysis", "power/interest grid", "communication plan", "stakeholder management", "SEP". Enforces Project+ engagement-level vocabulary and prevents fabrication of stakeholders, positions, or concerns.

kopp0510 Skill

Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture.

zenheart Skill

Neutral fixture skill inside a Plugin directory that has no plugin.json, to prove manifest-optional auto-discovery

oodle-ai Skill

Query Oodle metrics, discover labels and values, and build PromQL expressions using the label discovery workflow.

openai Bundle

Use when the user supplies or imports existing security findings, vulnerability reports, or security/vulnerability Jira/Linear tickets from scanners, advisories, GitHub, Atlassian Rovo, Linear, or similar backlog sources and wants static repo-impact triage. Do not use for discovery, duplicate-bug triage, validation, or fixes.

openai Bundle

Use when Codex is already in the finding-discovery phase of a security scan or the user explicitly asks to discover candidate security findings in a repository or code change. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

pkulijing Skill

把一条 backlog 创建成 issue（GitHub / GitLab 自动双轨，含三轴 label）—— issue 即单一真源，无本地索引文件

pramoddutta Skill

Triage a batch of defects instead of grinding through them one by one. Use when a lead says "triage these bugs", "prioritize the defect backlog", or pastes a list of open issues that need sorting. Groups likely duplicates, proposes severity/priority, routes each to a component or owner, and flags reports missing information. Every duplicate and routing is a suggestion for a human to confirm — it never auto-closes or reassigns silently.

pratikshadake Bundle

Evaluates PRD quality for clarity, testability, and build-readiness across problem clarity, scope, acceptance criteria, edge cases, and metrics. Use before sharing a PRD with engineering to catch gaps early.

silvabyte Skill

Manages Fizzy boards, cards, steps, comments, reactions, and pins. Use when user asks about boards, cards, tasks, backlog or anything Fizzy.

specdd Skill

Use when Claude Code needs to use the `specdd` CLI for setup, updates, spec discovery, inspection, or linting.

splunk Bundle

Research and answer current Splunk product questions from public sources with explicit product, deployment, version, freshness, and evidence boundaries. Use for explanatory questions such as what a feature does, where it is available, which edition or version supports it, whether two products or versions are compatible, or what changed. Route live incidents, stack changes, SPL execution, account-specific decisions, and unpublished roadmap questions to their owning workflow.

stacklok Bundle

Review completed non-trivial code across four independent axes: Spec, Standards, Test adequacy, and installed Domain specialists. Use proactively after implementation, modification, refactoring, bug fixes, feature work, or when asked to review/audit/check a diff, issue, PRD, finished change, or PR. Fans reviewers out in parallel, preserves each axis, and ends with the stable PANEL machine summary. NOT for drafting code, trivial edits (use /code-review), cloud review (/code-review ultra), pure config, or posting GitHub comments (/pr-review-post).

talkincode Skill

Roadmap and development-plan self-iteration (grooming). After each subtask delivery, or during periodic maintenance, check off completed items, update milestone status, backfill / split / re-prioritize subtasks, and fold newly discovered needs in via the feature checklist to keep the plan self-consistent and aligned with the checklist.

talkincode Skill

Global orchestrator / dispatcher role. Activated when the user issues an "auto-delegate development / continue the roadmap / auto-delegate" command (without naming a specific subtask); runs the full loop - select task, pick SOP, dispatch, quality gates, open PR, self-iterate the roadmap.

alim430 Skill

Run reproducible biomarker discovery via the BioResearch Agent biomarker workflow (differential expression, pathway enrichment, candidate ranking, volcano plot) over a GEO dataset or synthetic data. Use when the user asks to find gene biomarkers or candidate genes for a disease.

dazzleml Skill

Initialize standard GitHub issues (#1 Roadmap, #2 Quick Notes) with the canonical label set for a new project.

gerardordz96 Bundle

Use when someone asks to build, create, design, optimize, or audit a Claude Code subagent (an .claude/agents/*.md file), says "make me an agent", "build a subagent", "audit my agents", or wants help deciding whether something should be an agent at all. Runs a decision gate and Discovery Interview before writing files.

gerardordz96 Bundle

Use when someone asks to build, create, make, optimize, or audit a Claude Code skill -- "build me a skill", "make a /slash-command", "create a new skill", "audit my skills", or /skill-builder. Runs a Discovery Interview before writing files.

gerardordz96 Skill

Use when the user asks to build, package, bundle, optimize, or audit a Claude Code plugin or marketplace — a distributable bundle of skills + agents + commands + hooks installed via `/plugin`. Triggers — "build a plugin", "package this as a plugin", "bundle my skills", "make a marketplace", "turn these skills into something shareable", or `/plugin-builder`. The packaging + distribution sibling of `/skill-builder`, `/agent-builder`, `/agents-team-builder`, `/routines-builder`, `/hooks-builder`, `/workflow-builder`. Runs a decision gate and Discovery Interview before writing files.