readme-updater
Update the root README.md with entries for new or changed agent companies. Use when a new company has been added to the repo, when company details have changed (agents added/removed, skills added/removed), or when the user asks to refresh/sync the README. Triggers on: "update the readme", "add this company to the readme", "sync readme", "refresh readme", or after creating a new company with company-creator.
What this skill does
# README Updater Update the root `README.md` to reflect all companies in the repo, matching the established format. ## Workflow ### 1. Discover companies List all top-level directories that contain a `COMPANY.md` file. Skip `default/`, `skills/`, and any dotfile directories. ### 2. Gather data for each company For each company directory, collect: - **Name and description** — from `COMPANY.md` YAML frontmatter (`name`) and the prose body (first paragraph after the frontmatter closing `---`) - **Upstream source** — from the `Generated from [name](url)` line at the bottom of `COMPANY.md`. Extract both the display name and the URL - **Agents** — list subdirectories under `agents/`. Count them. Format agent names by replacing hyphens with spaces and title-casing - **Skills** — list `skills/*/SKILL.md` files. Count them. Use the directory name as the skill name ### 3. Generate org chart image For each company that does NOT already have an `images/org-chart.png`, generate one: ```bash ~/paperclip scripts/generate-company-assets.ts <company-directory> ``` If the image already exists and the company hasn't changed, skip regeneration. If the user explicitly asks to regenerate, run it again. ### 4. Write the README Replace the `## Companies` section in `README.md` with entries for every discovered company. Preserve all other sections (`## Structure`, `## Shared Skills`, `## Usage`, etc.) exactly as they are. #### Entry format Each company entry MUST follow this exact format: ````markdown ### [Company Name](./<directory-name>) ```bash npx companies.sh add paperclipai/companies/<directory-name> ``` <One-sentence description from COMPANY.md body. Keep it concise — one to two sentences max.> Built from [upstream name](upstream-url).  > **Agents (N):** Agent One, Agent Two, Agent Three (limit to 25 "and N more") > > **Skills (N):** skill-one, skill-two, skill-three (limit to 25 "and N more") ```` Rules: - The heading links to the company directory - The description is a brief summary, NOT the full COMPANY.md body - The upstream source link comes from the "Generated from" line in COMPANY.md. Append it naturally to the description sentence (e.g., "Built from [gstack](url).") - The org chart image path is always `./<dir>/images/org-chart.png` - Agent names are title-cased with hyphens replaced by spaces - Skill names stay hyphenated (as directory names) - Agent and skill counts go in parentheses after the label - If a company has no skills directory or no skills, omit the **Skills** line #### Index table Before the `## Companies` heading, include a summary index table: ```markdown | Company | Agents | Skills | Source | | ------------------------------- | ------ | ------ | ------------- | | [Company Name](#heading-anchor) | N | N | [source](url) | ``` - The Company column links to the heading anchor (lowercase, hyphens for spaces) - Skills column shows `—` if the company has no skills - Table order matches the company entry order below #### Ordering The first three companies are always **GStack**, **Superpowers Dev Shop**, and **Agency Agents**, in that order. Remaining companies follow alphabetically by directory name. Place `default` last if it is included. #### Naming overrides Some companies use a display name different from their COMPANY.md `name` field. Always apply these overrides: - `agency-agents` directory → display as **Agency Agents** (not "The Agency") ### 5. Verify After writing, read back the README and confirm: - Every company directory with a COMPANY.md has an entry - No company entries exist for directories that were removed - All image paths point to files that exist - Agent and skill counts match actual directory contents
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.