Loading...
Loading...
Found 1,378 Skills
Use tmux from the command line to run, drive, and monitor terminal programs as a coding agent (detached sessions, send-keys input injection, capture-pane output polling, formats, completion detection, and control mode). Use when a task needs long-running or interactive processes (builds, tests, servers, REPLs, watch modes, TUI apps) kept alive across turns or inspected live; skip when plain `cmd > log 2>&1 &` is enough.
Hunt CAPTCHA Bypass — 6 distinct patterns: (1) CAPTCHA field simply omitted from the request (server-side validation absent), (2) CAPTCHA token replayed from a solved challenge (no single-use enforcement), (3) CAPTCHA response accepted on a different endpoint than it was solved on (no binding to action/session), (4) static or predictable CAPTCHA values accepted (e.g. '0', 'null', empty string), (5) audio/accessibility CAPTCHA trivially solvable programmatically, (6) CAPTCHA only enforced after N failures (first N requests bypass it). Detection: intercept a successful form submission, remove the CAPTCHA field entirely, replay — if it still succeeds, server-side validation is absent. Medium severity standalone; High when it removes the only rate-limit gate protecting a login, registration, or payment endpoint.
Use to build a genuine community — turning an audience into people who interact with each other, not just with the brand. Run when the user asks how to build community, foster belonging/loyalty, create superfans, start a group/Discord channel, get members talking to each other, or move beyond chasing followers/virality. Reads brand-profile/social-strategy/audience-research. Community outperforms virality, measured by relationship depth/retention, not follower count. Covers the audience-to-community distinction (member-to-member interaction), choosing the space (in-feed -> semi-owned -> owned groups/Discord), recurring rituals, building belonging, and nurturing superfans into advocates. KPIs read natively, never fabricated. Advisory: WoopSocial schedules the content but does NOT run Discord/Slack or show analytics — the human runs the community, the agent drafts. Never fake community; get consent before spotlighting. Pairs with reply-and-comment-writer and crisis-and-moderation.
Triggers alongside the grilling skill whenever the user invokes grilling-fix (e.g. `/grilling /grilling-fix`) or asks to be grilled with lettered options. Overrides only grilling's answer-option format; every question must offer explicit options labeled with letters (A, B, C…), never numbers, plus grilling's usual recommendation, and the user may always answer in their own words. Not for use without grilling, and not a replacement for grilling itself.
Modern CSS techniques that replace breakpoint ladders, wrapper elements and scripts. Use whenever you write, edit or review styles in any form, including plain CSS, Tailwind classes, StyleX, CSS-in-JS and inline styles, and whenever you build or restyle a page or component, even if the user never mentions CSS.
Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out. Use whenever text needs to sound human, when the user says humanize, "does this sound like AI", "remove the em dashes", "de-slop this", "this sounds like ChatGPT", or before any caption, script, comment, reply or DM is shown to the user.
Diagnose a fitness coach’s Xiaohongshu topic ideas or existing drafts aimed at local in-person prospects. Use this when the user already has a specific topic or draft and wants to check whether it will appeal to local members, whether it is credible, whether the title and opening are clear, whether the wording sounds like the coach themselves, and what to change next. It does not replace topic ideation, full draft writing, or platform compliance review.
Query and explore IBM i application objects including CL commands, data areas, data queues, programs, environment variables, exit programs, and watches via SQL services. Use when user asks about: (1) CL command attributes or discovery, (2) data area values or inventory, (3) data queue status and messages, (4) program information (ILE/OPM), (5) environment variables, (6) registered exit programs, (7) watch sessions, (8) user spaces or user indexes, or (9) replacing DSPCMD, DSPDTAARA, DSPLIB, DSPPGM commands.
Query IBM i system configuration including system values, hardware resources, device status, environment variables, and JVM settings via SQL services. Use when user asks about: (1) system value settings like QSECURITY or QCCSID, (2) security-related system values, (3) hardware resource inventory, (4) controller, device, or line status, (5) environment variable settings, (6) active JVM information, (7) replacing DSPSYSVAL, DSPHDWRSC, WRKCFGSTS, WRKENVVAR commands, or (8) any system configuration review.
Use to report how hardcoded style values on a page, file or diff map onto a project's existing design tokens, such as "are we using our tokens here", "which hardcoded colors map to which tokens", a token audit or planning a token migration. It never edits. Replacing the values is build-design-system.
Create and replay Phargus collector alerts or sandboxed diagnostic rules from an observed Node.js runtime problem. Use when defining a threshold, sustained condition, or custom diagnostic finding.
MUST be used whenever writing or replying to anything on GitHub - issues, pull requests, discussions, review threads. Enforces technical brevity, bans AI execution diaries, report bloat, bot watermarks, and em dashes.