最近新增
刚加入收藏的新技能，抢先试用。
manage-agent
t-benze
Enroll, update, or terminate an agent. Write a JSON file and call happyranch manage-agent --from-file to keep the invocation single-line. Enrollment requires founder approval.
happyranch
t-benze
Manage the HappyRanch AI tourism organization via the happyranch CLI — submit tasks, stream events, inspect audit logs, approve agent enrollments, operate the shared knowledge base, manage threads (compose/send/invite/archive/abort-replies), and record founder-resolved precedents. Use when the user asks about HappyRanch tasks, agents, threads, the daemon/runtime, the knowledge base, or the one-person-company system.
space-review
pham-canh
Review a change in two passes, spec compliance then code quality, without editing. Use before committing or deciding a task is done.
space-plan
pham-canh
Turn a vague request into an executable plan before any code is written. Use when a task is ambiguous, touches several files, or two people could disagree about done.
space-build
pham-canh
Implement one planned task and verify it with a real command. Use when the plan is settled and files need to change.
dm-encounter
askrzypczak
Run D&D encounter commands at the table through the ttrpg-agents MCP tools. Use when the DM says things like "add 3 goblins", "goblin 2 takes 7", "heal the shadow", "remove the wolves", "what's the initiative order", "clear it", or asks what a monster does or rolls.
validate-site-playwright
boi6765
Render-validate the built Copilot Workshops site in a real browser using the Playwright MCP server. Use as an optional deeper QA pass — after the static checks in build-and-verify-docs — to confirm pages actually render. Trigger when asked to "validate the built site", "check the pages render", "do a browser/visual QA pass", or before opening a PR that changes rendered output.
update-markdown-file-index
boi6765
'Update a markdown file section with an index/table of files from a specified folder.'
publish-to-pages
boi6765
'Publish presentations and web content to GitHub Pages. Converts PPTX, PDF, HTML, or Google Slides to a live GitHub Pages URL. Handles repo creation, file conversion, Pages enablement, and returns the live URL. Use when the user wants to publish, deploy, or share a presentation or HTML file via GitHub Pages.'
localizations
boi6765
A skill that localizes contents into given locales.
check-content-alignment
boi6765
Find workshop content that may need matching changes after a lesson edit. Use for content drift reviews before committing or updating a PR. Discover duplicated passages, parallel concepts, translations, and cross-references from the diff and current content tree. Report actionable candidates without editing files.
build-and-verify-docs
boi6765
Build, preview, and verify the workshop site using existing checks. Use before committing or updating a PR. Inspect affected content and translations separately rather than relying on fixed page counts.
beacon-triage
Up-Coast
Triage Beacon feedback reports on a GitHub repository — the bug, feature and feedback issues filed from inside an app by the Beacon SDK. Use when asked to "triage the reports", "go through the beacon issues", "work the bug queue", "triage feedback", or when a scheduled run fires. Reads every open issue labelled beacon that isn't yet triaged, checks each one is complete, checks it against what the product is actually supposed to do, reproduces it, fixes and merges only the ones that meet the simple bar, and leaves everything else labelled and explained.
beacon-setup
Up-Coast
Put Beacon — bug, feature-request and feedback reporting — into someone's macOS or iOS app, and set up the pickup that works the reports. Use when asked to "set up Beacon", "add Beacon to my app", "install Beacon", "add a feedback button", "get bug reports from my testers", "publish the Beacon page", or "set up the triage pickup". Walks one of the two setup paths (Claude-only, or GitHub) end to end from the documentation that ships with this skill, and never touches infrastructure the person did not ask for.
implement
E1i
Implement a task through the reasoning-budget ladder — classify effort, run a low-effort implementer under constraints, verify with the harness, escalate only on repeated failure or ambiguity.
implement
E1i
Implement a task through the reasoning-budget ladder — classify effort, run a low-effort implementer under constraints, verify with the harness, escalate only on repeated failure or ambiguity.
capability-map
osdlc
Map out the capability graph for one scope of the project: survey the code (or the product's capability-map table), propose new Capability entities where the map has gaps, enrich existing ones with locations, grain, audience and related links, and report retire candidates. Runs sdlc capability coverage and sdlc capability graph read-only, dispatches one read-only sub-agent per candidate, renders one batched plan for approval, then writes through sdlc capability create / sdlc capability update and opens a PR. Invoke when capabilities are missing, ungraded, unanchored, or when the System page's capability view looks empty for an area. Usage: /sdlc:capability-map <dir C-NNNN areas> [--dry-run] [--auto].
bug-finder
osdlc
Sweep an entire codebase for real bugs and fix them. Partitions the tree into module-boundary territories, then runs three chained agent workflows — scan (three altitudes: in-function, in-module, in-library) → adversarial validate → fix → verify-fix → land — so a fresh agent performs every step and the orchestrating session never reads source itself. Opens one PR per module boundary, then surveys the open PRs, computes the conflict matrix deterministically with git merge-tree, and merges the overlapping bugfix branches into each affected PR in a single aggregated push so CI runs once per PR, not once per fix. Pass --bomb for maximum parallelization.
backlog-triage
osdlc
Walk untriaged backlog files in docs/planning/backlog/ and decide what to do with each: promote to task, promote to milestone, close, defer (bump last_reviewed), or leave it for an open PR. Before each decision, checks the item against main: the code it names, merged and open PRs, and existing planning entities, and recommends an action with quoted evidence. Promotion calls sdlc task create / sdlc milestone create directly, or points at existing work that already covers the item, and updates the backlog frontmatter to match. Commits each decision atomically on the current branch, honouring the project's branching conventions.
pr-review
osdlc
Shell out to a headless external agent — codex by default, claude on request — for a code review of the current branch against the upstream default branch: potential errors, cleanup areas, duplication, and opportunities to better use or grow the project's own library set.
identify-assumptions-existing
TurboSnails
"Identify risky assumptions for a feature idea in an existing product across Value, Usability, Viability, and Feasibility. Uses multi-perspective devil's advocate thinking. Use when stress-testing a feature idea, doing risk assessment, or preparing for assumption mapping."
yanshi-painting
gradetwo
用 yanshi 的 MCP 笔触工具画"一笔一笔看都真实"的画 —— 大笔起手、一笔承载一块体积、用罩染代替平涂。适用于让 AI 通过 brush_stroke / medium_stroke 作画，或诊断"看起来像填色"的作品。
reflection
t-benze
Use this skill when asked mid-thread to reflect on your recent work. Produces an opening report (recent tasks, learnings, frictions) posted as a thread reply, and captures learnings + optional KB entries via direct happyranch learning add / happyranch kb add calls at the end.
space-finish
pham-canh
Close out a task: confirm checks, summarise the change, and hand the publish decision to a human. Use when work is implemented and reviewed.