最近新增
刚加入收藏的新技能，抢先试用。
analyze-feature-requests
TurboSnails
"Analyze and prioritize a list of feature requests by theme, strategic alignment, impact, effort, and risk. Use when reviewing customer feature requests, triaging a backlog, or making prioritization decisions."
altitude-horizon-framework
TurboSnails
Understand the PM-to-Director transition through altitude and horizon thinking. Use when diagnosing scope, time-horizon, or leadership-level gaps.
ai-shaped-readiness-advisor
TurboSnails
Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build.
agent-orchestration-advisor
TurboSnails
Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized agents instead of one linear process.
figma-use
igor1309
"MANDATORY prerequisite — you MUST invoke this skill BEFORE every use_figma tool call. NEVER call use_figma directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the Figma file context — e.g. create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills, bind variables to properties, or inspect file structure programmatically."
spec-review
igor1309
Use when a spec exists and needs adversarial review for behavioral clarity, contract completeness, edge-case coverage, or boundary discipline before or during downstream work.
spec-drafting
igor1309
Use when accepted Product Intent or architectural decisions need to be translated into explicit behavior, contracts, flows, edge cases, and testable expectations before implementation.
product-intent-review
igor1309
Use when a Product Intent artifact needs review for story centrality, actor/outcome clarity, acceptance signals, boundaries, traceability, or downstream change-impact discipline.
product-intent-drafting
igor1309
Use when user-facing capability, actors, user stories, acceptance signals, boundaries, or downstream traceability need to be captured before research, ADRs, specs, implementation plans, or code.
stacks-error-handling
stacksjs
Use when implementing error handling in Stacks - the Result type (Ok/Err), handleError function, error page rendering (development with stack traces, production with friendly messages), ErrorHandler class, ModelNotFoundException, HTTP error mapping, log file writing, or error configuration. Covers @stacksjs/error-handling and config/errors.ts.
stacks-env
stacksjs
Use when working with environment variables in Stacks - the typed env proxy with auto-coercion, .env file loading, X25519 and AES-256-GCM encryption/decryption of env values, runtime/platform detection, CI provider detection, or the env CLI commands. Covers @stacksjs/env, config/env.ts, and .env files.
stacks-enums
stacksjs
Use when working with framework constants in a Stacks application - NpmScript commands, Action identifiers, or any enumerated constants used across the build system, CLI, and actions. Covers @stacksjs/enums.
stacks-email
stacksjs
Use when working with email in a Stacks application - sending emails via SES/SendGrid/Mailgun/Mailtrap/SMTP, email templates with STX, email drivers, the Mail singleton, the EmailSDK for inbox management, inbound MIME parsing, or email configuration. Covers @stacksjs/email, config/email.ts, and app/Mail/.
stacks-domain-modeling
stacksjs
Use when building or sharpening a Stacks project's domain language - challenging a fuzzy or overloaded term, naming a model or event, writing or editing CONTEXT.md, or recording an architecture decision as an ADR under docs/adr/.
check-pr
osdlc
"Tend one or more pull requests in a single pass: report their state, rebase them onto their base branch when they are behind or conflicting, and assess and answer new review comments. Fixes worthwhile comments straight away with --fix auto, or proposes the fix and waits for a thumbs-up with --fix ask (the default). Keeps no files of its own and records its answers to review-pr findings on a state ref beside the PR, so it suits a loop such as /loop /check-pr."
capability-groom
osdlc
Take a capability from a name to a chosen shape and implementation architecture: define it, research prior art and constraints, propose two or three shapes, select one with stated criteria, and leave a capability entry and a decision ready to record. Use it before any task is split from a capability.
api-enhancement-scan
osdlc
Given a library or module name, survey every call site of it across the codebase — fanning out subagents over independent codebase sections — and surface recurring caller-side patterns (repeated boilerplate, copy-pasted wrappers, awkward argument plumbing, repeated post-processing) that a new or enhanced API on the called module would absorb. Returns ranked enhancement opportunities, each backed by real call-site citations. Use when asked to find API improvement or enhancement opportunities for a module, library, or package, to spot missing affordances, or to understand how a module is actually used by its callers. Pass --in to survey only named packages or directories instead of the whole project, and --workflow to have it propose a reusable Workflow script for the survey instead of running it ad hoc.
technical-writer
ryanmat
Produces and reviews technical documents in the structure their audience expects, across six domains: user documentation (concept, task, reference, tutorial, troubleshooting, release notes), engineering and architecture (decision record, architecture description, design doc, postmortem, runbook, changelog entry), API reference text, AI governance (model card, system card, Annex IV file, GPAI form), security (advisory, disclosure notification, SECURITY.md), and privacy (privacy notice, DPIA). Use it when asked to write, draft, structure, or review any of these, or when a request names a document type, a standard behind one (MADR, the Hugging Face model card, CVE, CVSS, WP260, the ICO DPIA), or an audience for one. Classifies the type before drafting, takes one audience, fills the type's template with its evidence slots, marks every claim it cannot source as UNVERIFIED, and checks the structure. Not for README or PR bodies or assessment reports, which other skills own.
nes-romdev-debug
davefmurray
Drive romdev from the shell to debug NES ROMs — session setup, screenshots, input schedules, exact write/PC breakpoints, CPU calls, memory regions, and the NES-specific traps that produce false conclusions. Use when tracing a NES routine, comparing ROMs, or verifying a hack in an emulator.
nes-display-lists
davefmurray
Build and debug the LLBCS display-list renderer — run format, buffer/length, $C53A flush, RLE bit, grid addresses, font tiles, and the run-length bugs that blank the screen. Use when a NES screen is blank, garbled, or when adding text/rows to the bracket or selector.
mmc1
davefmurray
Work with NES MMC1 / SxROM cartridges — serial register writes, PRG and CHR bank modes, the 512 KiB A18 trap, PRG-RAM enable, reset, and board variants. Use when reading or patching an MMC1 ROM, debugging bank selection, expanding PRG, or deciding whether a mapper change is required.
llbcs-32-team
davefmurray
Work on the Little League Baseball Championship Series 32-team ROM hack in this repo — build chain, bank layout, bracket state, selector, stock game handoff, and known traps. Use when editing teams, rosters, brackets, banks, the selector, or launching games from the hack.
github-commit
ralagiya2053
Stage, commit with a conventional commit message, and push the current feature branch. Does NOT merge into main.
create-spec
ralagiya2053
Draft a spec.md for the current feature branch following the SDD workflow. Reads CLAUDE.md for roadmap and conventions, pulls context from the repo, and writes specs/<NNN>-<slug>/spec.md. Stops after spec.md for user review — does NOT create plan.md or tasks.md.