himkt
User๐ฐ๏ธ Agent Teams reinvented for collaborative coding supporting Claude Code and Codex, with full code transparency
Categories
Indexed Skills (14)
cafleet-design-doc-create
Create a new design document using CAFleet-native orchestration (Director/Drafter/Reviewer team). Use when the user asks to create a design doc, design document, specification, or technical spec. Do NOT write the doc directly with Write or use EnterPlanMode โ always invoke this skill.
cafleet-design-doc-execute
Implement features based on a design document using CAFleet-native orchestration with TDD cycle. Use when the user asks to implement or execute a design document. Takes document path as argument. Do NOT implement a design document by reading it and coding manually โ always invoke this skill instead.
cafleet-design-doc-interview
Validate an existing design document through fine-grained multi-round Q&A using CAFleet-native orchestration. Spawns a short-lived Analyzer member that reads the document and returns a numbered question list; the Director then drives AskUserQuestion rounds and writes COMMENT(claude) annotations inline. Supports multi-session splitting via question.md progress tracking. Use after the cafleet-design-doc-create skill and before the cafleet-design-doc-execute skill. Takes document path as argument. Do NOT use this to create or execute design documents โ use the dedicated skills instead.
cafleet-research-presentation
Create a Slidev presentation and reading transcript from an existing research report folder. Reads report.md and researcher files for context, creates slides using the cafleet-my-slidev skill and a reading transcript. Takes folder path as argument (e.g., topic-name). Do NOT use for research โ use the cafleet-research-report skill for that.
cafleet-research-report
Create a comprehensive research report with folder-based output. Researchers write findings to individual files, the Manager compiles report.md, and the Director reviews. Output goes to researches/[topic-slug]/. After report approval, offers to chain into the cafleet-research-presentation skill for slides and transcript. Members must always load skills using the Skill tool, not by reading skill files directly. Do NOT do a quick web search and summarize โ invoke this skill for thorough, multi-source research.
update-readme
Update README.md based on docs/concepts/ and docs/ directory. Use when documentation sources change and README needs to reflect the latest state.
cafleet-design-doc
Standardized design document format with template and guidelines. Load this skill ONLY to consult the template when editing an existing design doc, or transitively from the cafleet-design-doc-create skill. To CREATE a new design doc, use the cafleet-design-doc-create skill โ this skill alone does not author docs. Teammates in agent teams must always load this skill by its name cafleet-design-doc via their backend's skill-loader. Do NOT write design documents in a freeform format.
skill-author
Teach an author how to integrate the CAFleet-orchestrated team pattern into a new skill they are writing. Auto-load when the author intends to create a new CAFleet-orchestrated skill, write a skill that spawns cafleet members, add a Director/Member team skill, design a multi-agent broker-coordinated skill, build a CAFleet-team-driven skill, or write a skill that uses `cafleet member create`. This skill is project-local to the cafleet repo and is fully self-contained โ no `cafleet-base-dir` skill cross-reference is required to follow the guide.
cafleet-agent-team-monitoring
Active monitoring mechanism for CAFleet Directors. Documents the cron-like loop primitive per backend (Claude Code: CronCreate + /loop; codex and opencode: no in-session scheduling, fallback options listed) and the team-facilitation instructions (poll, ACK, dispatch queued work, health-check, escalate). Load whenever you are about to spawn or manage CAFleet team members. Foundation layer โ load before the cafleet-agent-team-supervision skill.
cafleet-agent-team-supervision
Governance layer for CAFleet Directors. Loads agent-team-monitoring as a hard prerequisite. Defines Core Principle, Communication Model, Idle Semantics, Authorization-Scope Guard, Spawn Protocol, User Delegation, Stall Response (cross-reference), and Cleanup. Load both monitoring and supervision whenever you are about to spawn or manage CAFleet team members (any 'cafleet member create' call).
cafleet-base-dir
Resolve the base directory for output files. Loaded by consuming skills via the `cafleet-base-dir` skill. Do NOT invoke directly.
cafleet-create-figure
Create data visualizations and charts using matplotlib. Triggered when user asks to create a chart, plot, graph, or visualize data. Do NOT use plt.show() โ always save to PNG files.
cafleet-my-slidev
Create Slidev presentations using the custom theme with cover, bullets, two-cols, blank, stats-grid, section-divider, and end layouts. Use when generating presentations from research reports, outlines, or other content. References /slidev for syntax details.
cafleet
Interact with the CAFleet message broker. Use when an agent needs to register, send/receive messages, poll inbox, acknowledge messages, or discover other agents.
Bio shown is the top-scored skill's repo description as a fallback โ real GitHub bios land in a future update.