Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Share secrets securely using zKettle — a zero-knowledge, self-destructing secret sharing tool. Create, read, revoke, generate, and audit secrets via MCP tools. Secrets are encrypted client-side with AES-256-GCM; the server never sees plaintext. Use for credential sharing, API key rotation, temporary access grants, and…
OpenClaw workspace initialization & standardization. Sets up a proper agent home: standard directory structure (projects/tasks/outputs/knowledge/scripts/ memory/tmp) + WORKSPACE.md rules + multi-agent config safety (config.patch, never config.apply) + memory log. Use when an agent enters a new/empty workspace root, or…
Multi-agent research war room. Personas debate in sequential turns through two phases — ideation and proposal writing. Persona persistence and drift detection are enforced every turn via the persistent-persona skill.
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
Personal assistant for one person's own medical data — genome, laboratory history, prescriptions, wearables. It reads them against each other locally and states what the data cannot support. No data is baked into the skill: everyone supplies their own. Use it when you need to check a physician's prescription as a…
Automatically detect when reusable workflows should become new or updated personal skills, safely manage personal and source-installed open-source agent skills across independently connected machines, and keep this manager current. Use when organizing, installing, updating, backing up, synchronizing, restoring…
Create stateful TypeScript/Hono mock API servers from OpenAPI 3.0/3.1 contracts. Use for building OpenAPI-based mock APIs, creating or repairing .mockapi sidecars, validating mock profiles, generating admin state endpoints, or freeform requests such as "mockapi build a mock server for api/openapi.yaml".
A writing rule for concise answers: lead with the conclusion, use one or two sentences, and avoid plans, tool commentary, repeated background, and unnecessary sections.
Adversarial verification of code changes. Tries to break implementations rather than confirm they work. Produces structured PASS/FAIL/PARTIAL verdicts with evidence. Use when verifying code changes, after non-trivial implementations, before reporting task completion, or when asked to check if something works.
UniversalDesigner is the single entry point for ALL frontend design, animation, and 3D work. It understands the project architecture (stack, existing design infra, constraints), sets a design direction, then routes execution to the right specialist skill(s) among 24 design skills: 3D engines (Three.js, R3F, Babylon…
Close a feature group as a milestone. Writes docs, proposes E2E tests, and runs a go/no-go gate. Use when the user says "/milestone", "this group is done", or the agent detects all items in a group are complete.
Write clear, inclusive, conversion-optimized job descriptions from a short role brief. Produces a structured JD with must-have vs nice-to-have split, inclusive language, salary-band guidance, and a screening scorecard. Use when the user needs to write/improve a job posting, hire for a role, or asks for a job…
Guides assembly of the Stock Buddy data contract from stock-buddy-data MCP (PostgreSQL) or client-side web research when DB/MCP is unavailable, then analyzeticker. Use when gathering DSE OHLCV, fundamentals, shareholding, macro, news, when analyzeticker returns instructions, or when stock-buddy-data cannot connect.
Use when comprehensive production-readiness code review is needed after implementation — dispatches up to 7 specialized parallel reviewers covering tests, plan completeness, architecture, complexity, DRY violations, suppressed warnings, and production readiness.
Validate the architectural ALTITUDE of a stated root cause or proposed fix before peer review or implementation. Interrogates the frame itself — whether the concern exists because of an abstraction that could be removed — before mapping enforcement sites within the concern. Tests whether a different boundary could…
Project notes system to prevent AI context loss and reasoning loops. Init notes, save mid-flow, recover context, migrate messy notes, resolve lessons. Subcommands: /notebook, /notebook save, /notebook recover, /notebook migrate.
A workflow guide for planning research-based digital exhibitions and online museums from research through website implementation. It orders the work from defining the subject and writing content to structuring pages, setting visual rules, building prototypes, and recording methods.
Complete macOS system maintenance that replaces CleanMyMac, Tencent Lemon, Pearcleaner. Four modules: (1) deep app uninstall with 30+ location residual scan, (2) startup/login item audit with service identification, (3) disk cleanup with 3-tier safety classification, (4) system health check. Use when: uninstall app…
Explain LLM-Wiki adoption and answer stakeholder objections. Use when the user wants a concise FAQ response, evidence summary, ROI framing, migration answer, or plain-language rebuttal; route adversarial risk registers and bad-fit audits to llm-wiki-critique-audit.
Multi-turn lead qualification over WhatsApp. Asks a fixed sequence of questions across turns, stores each answer as a note on the chat, and tags the chat with the current discovery stage. At the end of the sequence, applies a qualification rule and tags the chat qualified or disqualified, then stops replying. State…
La routine batch del sistema Job Hunter: raccoglie le offerte per ogni intento di ricerca attivo, deduplica, filtra, valuta il fit, pre-genera i materiali per i fit migliori in staging e consegna un digest. Gira come sessione Claude Code schedulata (Desktop scheduled task o routine cloud), ma è invocabile anche a mano…
★not rated 3
changed 20d agoA230 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: