Docs & Writing

tenfoldmarc Skill

Generate structured carousel slide content in your voice for Instagram carousels.

tenfoldmarc Skill

Render Instagram carousel slides as PNGs from structured slide data using your branded template.

textops Bundle

Summarize any content — lectures, meetings, articles, transcriptions, or any text — into structured Hebrew Markdown. Use when the user asks to summarize anything סכם לי, תסכם, סיכום, summarize, meeting notes, or any request to condense content. Output is ALWAYS in Hebrew regardless of input language.

the-focus-ai Bundle

This skill should be used when the user asks to "read document", "create document", "edit document", "google doc", "list documents", "insert text", "append text", "find and replace", "export document", "export to pdf", "export to word", "download as pdf", or mentions Google Docs operations. Provides Google Docs API integration for reading, writing, exporting, and managing documents.

the-focus-ai Bundle

This skill should be used when the user asks to "read emails", "send an email", "search gmail", "list messages", "check inbox", "manage labels", "find emails from", "check my calendar", "list events", "create an event", "schedule a meeting", "send styled email", "send markdown email", "create a draft", "draft an email", or mentions Gmail/Calendar operations. Provides Gmail and Google Calendar API integration.

the-openroad-project Skill

Fix an OpenROAD bug from a GitHub issue. Analyzes the issue, traces the root cause through the codebase, implements the fix, creates regression tests (registered in both CMake and Bazel), runs clang-format, and prepares a signed-off commit. Use when given a bug report issue number, error code (e.g. GPL-0305, DRT-0001, RSZ-2007), or when asked to fix a bug in any OpenROAD module (ant, cts, dpl, drt, gpl, grt, mpl, odb, pad, pdn, psm, rcx, rsz, sta, stt, tap, upf, utl, etc.). Also triggers on: "fix issue", "debug this error", "resolve crash", "fix segfault", "repair", "patch bug".

timpara Bundle

Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy.

tjxj Skill

自动生成周报。当员工或组长在飞书说"本周周报/生成周报/weekly report/这周干了啥"时触发。从 worklogs 表按周汇总工时、按项目分组、对比任务进度、抽亮点和卡点，按"本周成果 / 下周计划 / 风险求助"三段式生成可直接发的周报。支持个人周报、项目周报、团队周报三种视角。

tjxj Skill

自动生成月报。当员工或组长在飞书说"本月月报/生成月报/月度总结/monthly report"时触发。在周报数据之上叠加月度维度：跨周工时趋势、里程碑完成率、关键成果、风险复盘、下月规划，按"成果数据 / 关键项目 / 问题复盘 / 下月规划"结构输出。比周报更强调趋势和结论，适合向更高级别汇报。

tmchow Bundle

This skill is specifically for the Clawpatch CLI (openclaw/clawpatch, https://clawpatch.ai) — an npm-installed automated code-review and per-finding fix tool. Use it ONLY when Clawpatch itself is in play: the user says "review with clawpatch", "run clawpatch", "clawpatch fix", "find bugs with clawpatch", "clawpatch report/findings", "clawpatch open-pr", wants to dispatch subagents to fix Clawpatch findings in parallel, or otherwise names Clawpatch or one of its commands. Do NOT use it for generic "review this code", "find bugs", or "code review" requests that don't involve Clawpatch — those belong to a different tool.

topunix Bundle

Use when triaging bugs in a Bugzilla 5.0+/Harmony installation - reading or building a bug's dependency (Depends On/Blocks) tree, deciding whether a new report is a duplicate, judging whether a bug is a "blocker" versus routine severity, or picking a legal status/resolution transition (e.g. moving a bug to CONFIRMED, RESOLVED, or VERIFIED). Covers the default status workflow, resolution meanings, dependency-loop rules, and how duplicates are recorded.

torpedod Bundle

Claim-sliced report composer for research Phase 6. Writes canonical output/report.md from section briefs and claim slices; publishing renders optional formats later.

torpedod Bundle

Extracts canonical claims from collected evidence, enriches them with compact graph relationship metadata, and produces section briefs plus per-section claim slices for report composition.

tsudo Skill

Turn a substantial analysis or long conversation into a standalone Markdown report, using the restructuring as a second pass over evidence, assumptions, risks, and recommendations. Use this when someone asks to write this up, document a decision, or make findings durable. Not for short factual answers, status updates, or transcripts.

lesliexqing Bundle

Generate professional financial analysis reports from raw news, market observations, or a given topic. Supports morning briefs, weekly reports, deep dives, and strategy notes. Use when user asks to 写个周报, 整理市场分析, write a market report, summarize this week market, or any request to produce structured financial analysis writing.

lightsparkdev Skill

Style guide for all prose authored in this repo: mintlify docs pages, OpenAPI field and endpoint descriptions, changelog entries, READMEs, PR descriptions, PR review comments, and commit messages. Read BEFORE drafting, not after. Based on the Google developer documentation style guide (developers.google.com/style). Triggers: writing or editing any .mdx page, schema description, guide, PR description, or review comment.

lihanghang Bundle

ClawShire 年报数据查询技能 - 北交所上市公司年度报告结构化提取结果查询，支持按证券代码、年份检索营收、利润、分红、战略要点等标准字段

lihanghang Bundle

上传任意 PDF（简历/合同/研报/说明书等），用自然语言描述要提取的字段，自动输出结构化 JSON。支持多文档批量提取、多轮迭代修正、Schema 复用。当用户需要：(1) 从 PDF 中提取结构化信息 (2) 把文档内容转成 JSON/表格 (3) 批量解析同类文档并复用字段模板时使用此 Skill。

limit881010 Skill

Automated comprehensive stock investment due diligence. This skill is used when users provide the stock code they want to research (e.g., "Research 2330, I want to know about TSLA"). It automatically performs an 8-stage research process, covering fundamentals, industry, financials, governance, market divergence, valuation, etc., and generates a Traditional Chinese report. Fully automated, no user intervention required.

linuxfoundation Skill

Repo-owned code-review skill for lfx-v2-meeting-service, the repo-code role of this repo's local pre-PR review. Audits one commit or range against this repo's written rule surface — CLAUDE.md, the FGA/indexer/event-processing/ITX contract docs, the Goa design boundary, and the chart — and returns a Markdown review in which every finding quotes the rule it cites. Loaded under its exact `/meeting-service-code-reviewer` name by the `/lfx-skills:lfx-local-review` lifecycle; not a skill a developer invokes by hand.

linuxfoundation Skill

Repo-owned learnings-review skill for lfx-v2-meeting-service, the repo-learnings role of this repo's local pre-PR review. Matches one commit or range against this repo's knowledge base of patterns extracted from real past PR review comments, applies the known-false-positive floor last, and returns a Markdown review in which every finding quotes its KB entry. Loaded under its exact `/meeting-service-learnings-reviewer` name by the `/lfx-skills:lfx-local-review` lifecycle; not a skill a developer invokes by hand.

llnl Bundle

Maintain a CHANGELOG.md in Keep a Changelog format: record new features, changes, and fixes under an Unreleased section, and cut releases. Use whenever a user-facing change ships or the user says "update the changelog", "add a changelog entry", "record this feature/fix", "cut a release", "what changed since <ref>", or mentions release notes or a CHANGELOG. Works for versioned and unversioned projects — fall back to dates plus merge-request or commit IDs when there are no version numbers. Trigger on any notable change worth recording, even without the word "changelog".

llnl Bundle

Build and maintain a living architecture wiki for a codebase: one markdown article per module/subsystem plus an index that maps how they fit together. Use whenever the user wants to document, map, or reason about the code's architecture — "map the codebase", "update the architecture wiki", "what does module X do", "how does X connect to Y", "reconstruct the architecture", or onboarding to an unfamiliar repo. Trigger on any mention of an "architecture map", "code wiki", "module map", or keeping architecture docs in sync with the code, even without those exact words.

longsizhuo Bundle

Maintain openInvest's docs (docs/wiki chapters + docs/wiki/adr) under Google's Open Knowledge Format (OKF). Two jobs. (1) Teach agents to maintain docs the OKF way — every doc carries a small YAML frontmatter block as the single source of truth (type, title, tags, intent, schema_source, documents); schema details link to the authoritative code instead of being copied into prose; no more hand-maintained thousand-line markdown. (2) Look docs up fast — grep the literal term FIRST; only when grep is ambiguous (hits scattered across files / synonym mismatch / zero hits) run find_docs.py to rank the owning doc by frontmatter intent, or resolve a doc's schema_source to the real code. Trigger phrases — "which doc covers X", "find the schema for PortfolioResponse", "where is GET /api/holdings documented", "docs for verdict.risk_profile", "add OKF frontmatter to this doc", "lint the wiki", "scaffold a new ADR/chapter". Run: scripts/run.sh find|schema|index|lint|new (or python3 scripts/find_docs.py --repo <path> ...).

lsegal Bundle

Access Google Workspace through gogcli. Use for sending and reading Gmail, creating and listing Calendar events, uploading and searching Drive files, managing Contacts and Tasks, and working with Sheets, Docs, Slides, Forms, Chat, Keep, and other Google services once the skill runtime is enabled.

lucemia Skill

Use when converting autoresearch markdown results (verified_insights.md and AGENT_R*_RESULTS.md) into structured JSON for reporting or slides generation.

lucemia Skill

Use when generating a structured markdown report from an autoresearch_result.json file for a given ticker. Triggered when user asks for a report, summary, or writeup of autoresearch results.

ludo-technologies Bundle

Python coding standards and best practices covering error handling, performance optimization, async patterns, SOLID design principles, documentation, data validation, and object-oriented programming. Use when writing, reviewing, or refactoring Python code, or when the user asks about Python style, design, or best practices.

lulu0119 Skill

Create Slidev decks that review a GitHub PR: show the diff and explain why each change was written that way. Use when asked to make PR review slides or explain a PR with slides.

maakbo Bundle

Explicitly export an existing Mermaid block or standalone .mmd source to self-contained SVG and PNG assets, validate the selected business-context, architecture-context, or flow profile, and inspect publication output. Use only when the user asks to render, export, publish, generate an image, create SVG or PNG, or perform visual artifact review; do not invoke for ordinary Mermaid authoring or Markdown preview.

maakbo Bundle

Create and refine simple Mermaid diagrams directly inside Markdown or as explicitly requested standalone .mmd sources. Use for fast GitHub or VS Code preview, actor/system/information master maps, relationship diagrams, business context views, operational flows, decisions, rework, and source-only Mermaid cleanup. This Skill never creates SVG or PNG; route explicit media requests to mermaid-diagram-export.

manavarya09 Skill

Generate detailed cost reports with charts and breakdowns. Shows daily/weekly/monthly spend, per-tool costs, per-branch costs, and trends. Use when user says 'cost report', 'spending report', 'usage report', 'show costs', 'branch costs', or '/cost-report'.

mapsui Skill

Reference and usage guide for RichTextKit (Topten.RichTextKit) in Mapsui's Skia renderers. Load this skill when implementing or modifying any text rendering feature that involves word wrap, BiDi/RTL text, emoji, font fallback, callouts, or multi-style text blocks.

marcinz606 Bundle

Use when the user supplies a film-stock spec sheet, datasheet, or spectral data (PDF / URL / numbers) and wants a NegPy spectral-crosstalk .toml matrix for the Process panel's Crosstalk control, or asks to calibrate / derive channel-unmixing for a specific film or scanner. Keywords: crosstalk, datasheet, spec sheet, film stock, dye density, spectral, separation, unmixing, toml.

openhonest Skill

Report in military brief format, BLUF first. Use ONLY when the user asks for a sitrep by name. Do not use it for "status," "what happened," "investigate," or a screenshot; answer those in ordinary prose per the `writing` skill. Enforces bottom line in the first sentence, ranking by what needs attention, evidence beside every claim, stated confidence, and a named gap for anything unverified. Run clarity.py before sending.

openshift Bundle

Search and read OpenShift Container Platform documentation in markdown format. Use when the user asks about OpenShift features, configuration, installation, troubleshooting, or any OCP-specific topic — including operators, routes, services, oc, RBAC, networking, storage, or cluster administration.