Docs & Writing

efoo-team Skill

コード変更に伴うドキュメントの整合性を検証・同期するためのスキル。git diff から変更カテゴリを分類し、カテゴリ別にドキュメント同期の要否を判定し、自動生成ドキュメントを再生成し、リンク切れを確認し、表形式で報告する。ドキュメント同期、ドキュメント整合性確認、更新漏れ検出が必要なときに使用する。AGENTS.md 階層の生成・更新そのものが主題のときは agents-md-sync（明示起動）を使う。

oleg494 Bundle

Always-on development method: plan, check, implement, verify, report. Use for non-trivial tasks. Define observable acceptance before code, reproduce bugs before fixes, and complete the requested outcome without procedural permission gates.

oleg494 Skill

Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

technickai Bundle

File a report or piece of feedback from any Hermes platform session. Load this skill when the user says "/report", "file a bug", "report a bug", "something's broken", "something's wrong", "that's weird", "this is wrong", "this isn't working", "log this issue", or any other signal that they want to capture a problem for triage. Works on Telegram, Discord, Slack, and the CLI — the closed loop (a notification back to this chat when the issue is resolved) is wired automatically for gateway sessions.

technickai Bundle

Use to govern your own autonomy, deciding when to act on your own versus ask for approval, and earning more freedom over time the way a new employee earns trust through training and repetition. Group your capabilities into skill buckets, classify every action as a reversible (two-way) or irreversible (one-way) door, hold a trust level per bucket (L1 supervised, L2 guardrailed, L3 autonomous), and keep an honest markdown ledger of your decisions that you read back to promote or demote yourself. Load when setting up your autonomy rules or when a consequential act-vs-ask decision comes up.

technickai Bundle

Use when creating, importing, exporting, or quality-checking Google Slides decks via markdown-to-PPTX conversion and Drive import.

tabgab Skill

Compare simulation results between two projects or two git commits using opp_repl. compare_simulations / compare_simulations_between_commits check stdout trajectories, fingerprint trajectories, and scalar results; report IDENTICAL/DIVERGENT/DIFFERENT; and support debug_at_fingerprint_divergence_position() for interactive bisection. Load when investigating a regression or validating a refactor.

viniciusjsdev Bundle

Create or update a project-local skill from a stable, specialized, recurring capability with clear triggers, context, invariants, references, workflow, and validation. Use when durable project truth already defines the capability and future tasks will repeatedly need the procedure. Do not use for one-time tasks, unresolved decisions, generic documentation, individual files, classes, endpoints, entities, or deterministic operations better expressed as scripts.

zixun-github Bundle

Use when 需要在 Spec Pack 的 verification 阶段创建“可直接粘贴到外部缺陷系统”的缺陷报告（不在 Spec Pack 内落盘 bug 文件），并将缺陷引用回写到 `{FEATURE_DIR}/verification/report-*.md`。

zixun-github Bundle

Use when 需要在 Spec Pack 的 verification 阶段产出 `{FEATURE_DIR}/verification/report-{date}-{version}.md`（测试报告），给出可交付结论并可追溯到用例与缺陷引用。

mickpletcher Bundle

Deep-dive research report on a specific cryptocurrency before trading or investing. Always trigger immediately when the user's message starts with "cr" followed by a coin name or ticker. Also trigger on "research [coin]", "due diligence [coin]", "is [coin] worth buying", or any request for a structured breakdown of a specific crypto asset. Always verify current market, team, tokenomics, and project facts before responding; never answer from memory.

mickpletcher Bundle

Plan, format, and export travel itineraries as Obsidian-formatted Markdown files. Always trigger immediately when the user's message starts with "trip" or "itinerary". Also trigger when the user says "plan my trip", "build my itinerary", "travel plan", "export my trip", "format this itinerary", or describes an upcoming trip and asks Claude to organize it. Produces a day-by-day breakdown, logistics summary, packing list, and budget tracker in a single Obsidian-ready .md file.

mickpletcher Bundle

Export workout data to an Obsidian-formatted Markdown file. Always trigger immediately when the user types "owd". Also trigger on "export workout", "obsidian workout", "save workout to obsidian", or related requests to export workout data into Obsidian. Read the current conversation first before searching prior conversation history. Name the file after the date of the chat that contains the workout data.

myrgic Skill

Protocols for starting and ending work sessions - initialization, checkpointing, handoffs, and continuity. Use when beginning or ending a session, or creating handoff documentation.

myrgic Skill

Protocols for effective technical documentation - structure, clarity, specification, and executor-oriented writing. Use when writing specifications, reports, proposals, or documentation.

nafeeur Skill

Write accurate user, operator, API, and architecture documentation grounded in the implemented product.

nafeeur Skill

Implement production features end to end, including integration, error states, tests, documentation, and verification.

nice3point Skill

Write or review C# code. USE FOR: writing or reviewing any C# code. DO NOT USE FOR: prose, markdown, or wiki text (use technical-writing), or XML doc comment content (use writing-xml-doc-comments).

nice3point Skill

Write or review technical prose — markdown documentation, wiki pages, README or config comments. USE FOR: explaining a contract, behavior, decision, or API in human-readable text, and reviewing that prose says something a reader cannot already infer. DO NOT USE FOR: C# code comments (use csharp-style), or C# XML documentation comments (use writing-xml-doc-comments).

nice3point Skill

Write or review C# XML documentation comments on public API surface. USE FOR: adding or reviewing XML documentation on public types, members, parameters, type parameters, and return values. DO NOT USE FOR: prose, markdown, README, or wiki text (use technical-writing), or ordinary code comments (use csharp-style).

owl-listener Skill

Taste Report

owl-listener Skill

Use at project start and completion to OBSERVE and record how the user designs — the decisions they make, the styles they reach for, their habits and inclinations across projects. This is a descriptive record (a mirror), NOT a controller — it is never fed back to steer the work. Per-project direction comes from design-taste and a DESIGN.md; design-memory only watches and reflects, surfaced to the user as a report out of curiosity

shakacode Bundle

Report tight progress on the current work - done, in progress, blocked, and next - without starting new work. Use when asked for a status update or "where are we / anything needed from me".

shakacode Bundle

Use when asked where a dispatched PR batch stands - mid-flight or after dispatch - to report per-lane coordination and live GitHub state in the canonical readiness vocabulary. Read-only; use close-batch for completed-batch closeout and pr-monitoring for a single PR.

shakacode Bundle

Use before fixing, batching, or assigning GitHub issues or proposed fixes when the value is uncertain, the report came from AI/code analysis, the fix is complex, or the user asks whether an issue is worth doing. Produces an evidence-backed recommendation: fix now, document/work around, park, close, or ask for product input.

shakacode Bundle

Safely assess an outside-contributor fork pull request through metadata and diff evidence, then report a maintainer decision without executing untrusted content. Use when screening an outside-contributor fork pull request.

openbmb Bundle

Read, create, edit, merge, split, rotate, fill, render, and verify workspace PDF files. Use whenever the requested input or deliverable is a .pdf, including extracting text or tables, inspecting metadata and page geometry, generating a new PDF, rearranging pages, filling AcroForm fields, or checking visual layout. Do not use for Google Drive or browser-only PDF workflows.

openbmb Bundle

Create, edit, inspect, review, and finalize Microsoft Word .docx documents. Use for new Word documents, source- or template-based reports, precise edits that should preserve an existing file, visual or structural review, comments and tracked changes, and final DOCX delivery. Use only for .docx files, not legacy .doc, macro-enabled .docm, or live Microsoft Word control.

openbmb Skill

Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.

openbmb Skill

Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.

opsmill Bundle

Audits an Infrahub repository against best practices and rules, producing a structured compliance report. TRIGGER when: reviewing repo for compliance, onboarding to existing project, pre-deployment validation, catching issues. DO NOT TRIGGER when: creating schemas, writing checks/generators, querying live data, populating objects.

cogine-ai Bundle

Use when the user asks for a report-only browser QA pass on a web application, live site, preview URL, authenticated app flow, or release candidate without making code changes.

sitapix Skill

Choose between Swift Regex and NSRegularExpression for text parsing, and bridge match results to NSRange for use with NSAttributedString and TextKit. Covers regex literals, RegexBuilder DSL, runtime-constructed regexes, AnyRegexOutput, Foundation parser captures (date, currency, localizedInteger), NSRegularExpression patterns and options, NSTextCheckingResult, the NSRange(_:in:) bridge, syntax-highlighting patterns, and the performance and deployment-target tradeoffs that decide which engine to use. Use when picking a regex API for new code, migrating existing NSRegularExpression code to Swift Regex, wiring matches into syntax highlighting or attribute application in NSTextStorage, or debugging "the match is in the wrong place" bugs caused by NSRange/String.Index mismatch. Do NOT use for NLTagger, NLTokenizer, NSDataDetector, or general Natural Language utilities — see txt-detectors-tagger. Do NOT use for Markdown parsing or PresentationIntent — see txt-markdown.

sitapix Skill

Render and parse Markdown in SwiftUI Text and AttributedString — inline syntax that works, block-level syntax that doesn't, PresentationIntent interpretation, and custom `^[text](key:value)` attributes via MarkdownDecodableAttributedStringKey. Use when Markdown isn't rendering as expected, headings/lists are silently dropped, a `String` variable shows literal asterisks, you're choosing between native parsing and a third-party renderer, or you need block-level formatting in UITextView. Do NOT use for the AttributedString-vs-NSAttributedString decision in general — see txt-attributed-string. Do NOT use for parser/regex mechanics on non-Markdown text — see txt-regex.

sitapix Bundle

Look up working code snippets for common text-view features — placeholder text, character/word limits, auto-growing height, search highlighting, link/data detection, line numbers, custom cursor color, scroll-to-range. Use when the user asks "how do I…" about a small, well-scoped UITextView/NSTextView or NSAttributedString task and you need a copy-paste recipe rather than architecture guidance. Trigger on casual 'how do I add line numbers / a placeholder / a character limit / a custom cursor color' phrasings even when no API name appears. Do NOT use for picking between TextKit 1 and TextKit 2 (txt-textkit-choice), choosing a text view (txt-view-picker), or paragraph-style internals (txt-line-breaking).

cuic19053-hue Bundle

生成"三下乡社会实践-科技服务类"立项申报书 docx。覆盖科技服务、医疗服务、法律援助、农业技术指导四类子方向，含服务对象需求清单、专业能力匹配矩阵、按服务场次实施方案表（场次/日期/地点/对象/服务内容/人数/专业要求）、服务流程设计、持续帮扶机制、服务人次与解决方案量化产出。直接输出可提交的 Word 文档。