Project Context System — structured project memory for any project via layered docs and codebase index. Use for: documenting projects, writing PRD/roadmap, generating codebase repo-wiki, capturing requirements/decisions, writing dev notes, building doc navigation index, compacting bloated docs, auto-detecting stale…
Use to orient in an unfamiliar codebase with graphify, a local tree-sitter code graph — "what does this symbol touch", "how do these two connect", "trace this call chain". Opt-in (the human installs graphify once). A forward-orientation aid, NOT a reliable reverse-dependency tool. Shipped and kept current by Loom.
Plan and supervise user-approved software initiatives through Codex native tasks and bounded native subagents. Use when the user explicitly asks Agent Orchestration Gateway to clarify work, split it into non-overlapping modules, dispatch module tasks, or run an AOG module task.
Use when the user is running one or more coding agents and needs a shared control plane to coordinate work and keep an audit trail. Triggers include running parallel Claude Code/Cursor sessions, agents colliding on the same work, needing objectives instead of a task list, or needing auditable evidence of…
Use the skill-doctor CLI or UI to inspect and manage AI-agent skills, rules, instructions, MCP resources, and context cost across supported platforms. Trigger when the user asks to scan or audit agent skills, find duplicates or trigger conflicts, investigate unsafe instructions, estimate context-token cost, compare…
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Deploy and extend small web artifacts ("canvases") on a canvas-drop instance. Use when the user wants to ship static HTML/JS to a shared URL, or give a canvas backend capability (KV, files, AI, identity, realtime, admin-granted Connections) through the zero-config browser SDK. Connect over MCP for an identity-scoped…
Use this skill when checking, debugging, repairing, or hardening the wiring of an application so the intended way of running, building, styling, routing, importing, configuring, deploying, and using dependencies is correctly connected. This skill focuses on entry points, package scripts, CSS and asset references…
Token-efficient routing for a repo's Markdown docs. Use BEFORE reading or grepping any .md file to find the one canonical doc for a question — and to read it at the section level instead of whole. Trovex serves the single current doc per query (with a canonical/stale/duplicate freshness marker) for 60% fewer tokens…
Persistent cross-session memory via Engram's MCP tools (engramrecall, engramremember, engramcontext, engramfeedback, engramforget, engramstatus). Use this skill at the START of any session on a known project or with a known user — recall before acting. Also use it whenever the user states a preference, makes a…
Generate structured, self-contained Codex task prompts. Use when the user asks for a Codex prompt, delegation task, fix, build, audit, ops/tuning, refactor, PR-series, or master-session brief to hand to another Codex run. Grounds every cited path and command, distinguishes directive from investigative work, and binds…
Record, render, optimize, and embed a demo GIF in a repo's README. Use when asked to add a demo gif, record a demo, show the tool in action, or make a README more visual.
Pone a Claude como PM/orquestador de un proyecto donde los desarrolladores son instancias EFÍMERAS de glm-5.2:cloud que implementan usando el CCDD gate. Úsala cuando el usuario quiera ejecutar un proyecto, feature, refactor o conjunto de tareas delegando TODA la implementación a GLM — Claude planifica, descompone en…
Check SQL with sqlike — deterministic static analysis (validity, anti-patterns, rewrites, index advice) and query-equivalence verification. Use whenever you write, edit, review, or rewrite a SQL query, or need to prove two queries return the same results. Requires the sqlike MCP server (@sqlike/mcp) or the sqlike CLI…
Use when the session feels bloated or slow, the user mentions "too many skills", "context bloat", "skill list is huge", asks why a skill disappeared or isn't available, or wants to manually park/unpark skill groups mid-session. skill-valet automatically moves unused user-skill directories out of /.claude/skills so the…
Guided co-creation writing skill. Interviews the user, drafts content section by section, generates platform-specific variants from shared source. Creates the content manifest. Works with a brief from /media-idea or accepts freeform input.
★not rated 6 5mo agoA52 tokens
originalMIT
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: