Docs & Writing

kakatur Bundle

Create or revise Confluence pages and Git repository README files using verified project sources, clear structure, natural language, and preserved technical detail. Use only for these two documentation formats; do not use for articles, blogs, generic prose, presentation scripts, or narration.

ryanalexanderbrashear Skill

Investigate a bug or feature from a ticket or a user's description, then write an implementation plan to a file for the user to review and iterate on before any code is written. Use when the user wants a plan, wants work scoped or broken down, asks how they would approach a ticket, or hands over a ticket ID, ticket URL, or bug report.

ryanalexanderbrashear Skill

Files a bug report or work item in the project's tracker — GitHub, GitLab, JIRA, Linear or whatever the repo actually uses — with the report in the reporter's words, the cause traced or explicitly unknown, and a reproduction. Use when the user reports a bug, says "file this", "open a ticket", "raise an issue", or when work is discovered that will not be done now and would otherwise be lost.

gabson0x Skill

Bug triage validation system, Immunefi report format, and 20 real paid bounty examples dissected. Use this when validating a finding before submitting, writing an Immunefi report, checking if a bug is actually valid, or studying real examples of paid vulnerabilities.

barnabys-drew Skill

Open a markdown file as a rendered, live-reloading preview in a separate Herdr pane (Glow, split to the right). Use when the user invokes /mdp, or asks to preview, render, open, or show a markdown/.md file "in a pane", "side by side", or "like the Cursor preview". Requires running inside Herdr (HERDR_ENV=1).

barnabys-drew Bundle

Find where a word, topic, quote, or moment comes up in a Lex Fridman Podcast episode, using the official transcripts on lexfridman.com, and return timestamped YouTube deep links with verbatim quotes. Use whenever the user mentions a Lex Fridman podcast/episode and asks "where did they talk about X", "when does <guest> mention X", "find the part about X", "what did <guest> say about X", wants timestamps for a topic, wants to find a quote or moment, or says they can't listen to or watch the whole episode.

rifteo Bundle

Complete HTTP Parameter Pollution methodology server behavior fingerprinting, server-side and client-side HPP, WAF bypass via parameter splitting, OAuth/payment/access-control abuse, header and JSON body pollution, and report structure. Trigger when the user wants to test for HTTP Parameter Pollution, is trying to bypass a WAF with a known-blocked payload, sees a payment/role/redirect parameter and wants to test override attacks, or is testing OAuth flows for redirect_uri manipulation.

rifteo Bundle

Computes an exact CVSS v3.1 base score and vector from a vulnerability description infers metrics from context, asks one sharp question only when ambiguity would change the severity level. Trigger when the user needs a CVSS score for a vulnerability finding, is writing a bug bounty report or pentest finding needing a severity vector, says "score this" or "what's the CVSS?", or has a vulnerability description and wants a severity level.

wenqiiizwq-creator Bundle

Autonomous-Schematic-Generation (ASG): create, add, redraw, and inspect KiCad schematics with topology-specific layouts, obstacle-aware orthogonal routing, readable fields, and native ERC/netlist/geometry/render verification. Includes a deterministic generator from reusable Circuit IR modules with explicit ports, real pin resolution, automatic functional placement, supported multi-unit symbols and protected regeneration. Includes SKiDL/circuit-synth data adapters and geometry checks. Analyze KiCad schematics, PCB layouts, Gerbers, PDF schematics, netlists, BOMs, power trees, and DRC/ERC findings with evidence and confidence labels. Use for .kicad_sch, .kicad_pcb, .kicad_pro, schematic generation or redraw, 原理图自动生成、画原理图、原理图排版、信号追踪、电源检查 and KiCad design reviews.

calvinwang123 Skill

Edit documentation and other writing intended for other people to remove AI patterns while preserving facts, technical details, and clear full sentences. Use for READMEs, guides, reports, PRs, issues, emails, and shared prose. Do not apply to ordinary Caveman chat replies.

rifteo Bundle

Systematic IDOR/BOLA detection methodology recon, multi-account testing, bypass techniques, and report structure. Trigger when the user asks to test authorization controls or object-level access restrictions, wants to hunt for IDOR or BOLA on an API or web app, needs a structured methodology for multi-account access testing, is doing a bug bounty or pentest and wants to maximize IDOR coverage, or asks if they can access another user's data or whether authorization is enforced server-side.

rifteo Bundle

An SSTI detection, fingerprinting, and exploitation engine. Triggered by suspected server-side evaluation (e.g., {{7*7}} = 49) or stack traces referencing a template engine (Jinja2, Twig, FreeMarker, etc.). Facilitates blind detection, sandbox escapes, and escalation to RCE. Includes report structuring (severity, CWE, remediation).

rifteo Bundle

An XXE detection and exploitation methodology engine. Triggered when testing for XML injection, interacting with XML content-types/endpoints, or processing XML-based file uploads (SVG, DOCX, SAML, SOAP). Facilitates classic file reads, blind OOB exfiltration, WAF bypasses, and SSRF chaining. Includes report structuring.

qili09 Bundle

Log the time spent on a Jira story during the current Claude Code session as a Jira worklog (mirrored into Tempo Timesheets), computed from the session transcript instead of typed by hand. Use when the user says "log time", "log my time", "time report", "record this in Tempo", "how long did I spend on <KEY>", or when a Stop-hook nudge reports unlogged time — and at the natural end of any session in which a Jira story (e.g. PROJ-12345) was actively worked on, offer to run it. Do NOT use it for editing or reporting on Tempo timesheets in general, for estimating future effort, or for stories that were merely mentioned in passing.

iabuelruzz Bundle

Use when analyzing ICD/specification PDFs, generating comparison or status documents, or extracting structured tables about message families, frames, subframes, pages, alerts, uplink/downlink flows, RF bands, and missing/open items.

rifteo Bundle

Generates a complete, client-ready penetration test report from all findings in the current engagement executive summary, risk table, technical findings, and recommendations. Trigger when the user says "generate the report", "write the report", or "produce the deliverable", is at the end of an engagement with all findings confirmed and written up, or wants a draft report to review before sending to the client.

gabson0x Skill

Bug bounty report writing for H1/Bugcrowd/Intigriti/Immunefi — report templates, human tone guidelines, impact-first writing, CVSS 3.1 scoring, title formula, impact statement formula, severity decision guide, downgrade counters, pre-submit checklist. Use after validating a finding and before submitting. Never use "could potentially" — prove it or don't report.

gabson0x Skill

Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer = kill the finding and move on. Saves N/A ratio.

rifteo Bundle

Converts raw bug bounty findings into a complete, triage-ready report clear description, numbered reproduction steps, self-contained PoC, risk, and remediation. Trigger when the user has a confirmed bug bounty finding and needs to write it up, says "write this up", "report this", or "format this for H1/Bugcrowd/Intigriti", or has raw notes, a request/response, or a PoC needing a submission-ready report.

rifteo Bundle

Complete clickjacking (UI redressing) methodology framing protection detection, single-click and multi-step PoC construction, JS frame-busting bypass, drag-and-drop and OAuth consent variants, and report structure. Trigger when the user asks to test for clickjacking or UI redressing, wants to check if a sensitive endpoint (account delete, 2FA disable, OAuth consent) is frameable, needs to build a clickjacking PoC for a report, or wants to bypass JavaScript frame-busting protections.

makanfar Skill

Inspect the current directory's top-level entries and help the user reclaim space - classify each entry as protected, junk, abandoned, or active; report with evidence; move approved items to the macOS Trash with a reversible manifest. Use when the user asks to clean up, find junk, free disk space, or identify abandoned files and projects in a directory.

ankit1598 Skill

Writes terse, actionable code review findings to a markdown file under the project `.artifacts/` tree. Use when the user asks for a code review, diff review, review written to artifacts, or review saved as markdown; follow dev-artifacts for path and ALL_CAPS_SNAKE_CASE naming.

agentcorp-inc Bundle

Official Salesforce documentation retrieval skill. Use when you need authoritative Salesforce docs from developer.salesforce.com, help.salesforce.com, architect.salesforce.com, admin.salesforce.com, or lightningdesignsystem.com, especially when pages are JS-heavy, shell-rendered, or hard to extract with naive fetching. Use to ground answers in official Salesforce sources instead of third-party blogs or summaries. TRIGGER when: user asks for official Salesforce documentation, Apex or API reference, LWC docs, Agentforce docs, setup or help articles, or any doc from a Salesforce-owned domain. DO NOT TRIGGER when: user is asking for a code change, deployment task, or anything not requiring documentation retrieval — use the appropriate sf-* skill instead.

agentcorp-inc Bundle

Signals scout for PostHog surveys. Watches active surveys for score regressions, response-volume drops, abandonment spikes, and targeting drift, and aggregates open-text responses into recurring themes — filing each as a report in the inbox.

agentcorp-inc Skill

Use when the user wants to create or edit a Google-Docs-style markdown document as a widget on a Miro board they're already working on. For a brand-new, standalone document not tied to an existing board, use the miro-format skill instead.

agentcorp-inc Skill

Use when the user wants a brand-new, standalone Miro item created as its own content — a document, table, diagram, timeline, kanban board, slide deck, prototyping container, activities board, or embed — not added onto a board they're already working on (e.g. "create a doc in Miro about X", "make me a Miro table for Y", "set up a kanban board for Z"). Prefer this over the document/diagram/table skills when no existing board is in play.

agentcorp-inc Bundle

Search Shopify developer documentation across all APIs. Use only when no API-specific skill applies.

agentcorp-inc Bundle

Multi-currency cash management — balances, receivables, obligations, FX exposure, runway, rebalancing, and indicative FX rates. Use when the user asks about cash position, treasury health, what is owed, money in or out, FX positions, or requests money movement (conversions, transfers, rate locks). Also load this skill when the user asks for a "transaction report", "accounting report", "reconciliation", "P&L", or "ledger" — the skill contains the required scope-boundary rules to refuse these properly and offer supported alternatives. Do NOT use for creating invoices from documents, supplier/beneficiary onboarding, or card provisioning (use the workflow skills for those).

sumanjeet0012 Skill

Explain complex, confusing, or abstract technical concepts using vivid, relatable real-world analogies. Acts as the ultimate "Explain Like I'm 5" (ELI5) fallback when conventional documentation or standard explanations fail to click. Use when the user says "I don't get it", "explain like I'm 5", "ELI5", "give me an analogy", "dumb this down", "make a simpler comparison", or "it's not clicking".

sumanjeet0012 Skill

Summarize the technical substance of the current conversation (topics discussed, concepts learned, architectural decisions, code snippets, and next steps) and publish it as a clean, structured Markdown note to a designated GitHub repository (defaults to sumanjeet0012/temporary). Use when the user asks to "save this discussion", "make a markdown of what we discussed", "upload notes to GitHub", "save session to temporary repo", or "push today's notes".

agentcorp-inc Bundle

How to author, edit, and adapt PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user wants to customize a canonical scout for their own setup (narrow its scope, retune its thresholds, add disqualifiers), tweak a scout's schedule or dry-run posture, or write a brand-new scout from scratch for a specific use case (a custom event, a product surface no canonical scout covers). Covers the scout SKILL.md anatomy, the report contract, the dedupe + scratchpad-memory conventions, the per-team skills-store path vs the canonical in-repo path, and the write-and-inspect test loop (with dry-run as an optional safety net). Trigger on "write/edit/customize a signals scout", "new scout for X", "tune my scout schedule", "make a scout that watches <event>".

agentcorp-inc Bundle

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user wants to understand what scouts they have, how each one is behaving, and whether the fleet is actually working. Covers surveying the fleet and its schedules, reading recent scout runs and drilling into a single run's reasoning, inspecting the durable scratchpad memory the fleet has built up, tracing a run to the reports it wrote or edited, and assessing a scout's health and performance over time (cadence, success rate, report rate, signal-to-noise). Read-only and exploratory — to write or tune a scout, use `authoring-scouts` instead. Trigger on "what are my scouts doing", "how is my <x> scout performing", "show me recent scout runs", "why did this scout find/report nothing", "what has the fleet learned", "explore scout run <id>", "is my scout working".

agentcorp-inc Skill

Explore PostHog's Inbox and act on what it surfaces — the place where signal reports cluster into actionable issues and trends. Use when the user asks "what's in my inbox?", "what should I look at?", "which reports are actionable?", "what's PostHog flagged recently?", asks about a specific report by ID or title, wants to act on / fix / implement a report (turn it into a PR), wants to dismiss or snooze a report, or wants to see which signal sources are configured. Covers listing, filtering, drilling into, and acting on reports, plus pointers to the deeper `signals` skill when raw signals or semantic search are needed.

agentcorp-inc Skill

Signals scout for PostHog distributed tracing (APM / OpenTelemetry spans). Watches RED metrics per (service, operation) — error rate, p95 latency, request volume — for regressions, new error signatures, and traffic cliffs, and files each validated regression as a report in the inbox.

agentcorp-inc Skill

Signals scout for PostHog feature flags. Watches the flag roster and the `$feature_flag_called` stream for evaluation cliffs, ghost flags, response-distribution shifts, and flag debt, and files each validated contradiction as a report in the inbox.

agentcorp-inc Skill

Signals scout for PostHog Replay Vision scanners. Watches that enabled scanners keep observing (throughput / quota cliffs) and that what they see in aggregate gets surfaced (score shifts, recurring themes across sessions), and files each validated finding as a report in the inbox.