x-reply
Handle the replies under the user's own X posts - sort every one, then draft answers in the order that matters. Use when the user pastes the replies on their…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-15 00:13
General & other
53,835 results
iterate-sketch
Ongoing mindset for refining an existing solutionize sketch plan in place.
build-on-host
Use when an approved tasks.md should run somewhere other than this machine — offload the build to a remote host, build server, or second machine over ssh,…
markdownlint
Ensures style consistency and correctness in Markdown files using markdownlint-cli2. Use whenever creating, updating, editing, or reviewing any Markdown (.md)…
debloat
Compress and harden supplied prose. Use when repetition, softness, ceremony, or structural bloat obstructs developer use. Do not use for source code, commit…
panel
Produce one recommendation from independent analysis of legitimate alternatives. Use when a consequential technical, architectural, operational, or product…
commit-atomic
Group staged changes into atomic commits with commitizen convention
plannotator-setup-goal
Turn ideas into executable goal packages with guided interviews and codebase analysis
execute-task
Executes a task, either from a TASK_N.md file or a free-form description. Use when: (1) implementing a task from a TASK_N.md file, (2) the user provides a task…
a11y
Accessibility guide (WCAG 2.1/2.2, Level A–AAA). Trigger: When building UI components, interactive elements, or auditing accessibility compliance.
audiobits
Build procedural browser audio with AudioBits, from a simple confirmation sound to original recipes, sustained live controls, and complete interactive…
ft-assess
Produce an evidence-backed internal assessment of a project, feature, or idea. Use when the user asks to assess, evaluate, audit, or review project…
ft-spec
Draft unified spec.md (Outcome plus Phases) and tasks.md with parallelism groups for a track that has intent.md. Chains to implement on user continuation.…
wechatide-skill
Root entry point for WeChat Developer Tools task execution. It is used to complete environment checks before execution, then route to preview, automation, debugging, and cloud-related operations.
review-and-archive
Use when reviewing active Loop Factory specs against the working tree, checking verification evidence, deciding ACCEPTED or CHANGES_REQUESTED, and archiving…
template-skill
Replace with description of the skill and when Claude should use it.
improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the project domain glossary and the decisions in docs/adr/. Use when the user wants to improve…
plan
Write or update a single-feature PRD (`Type: feat`/`fix`/`chore`) with scope, user stories, and acceptance criteria. Triggers: plan prd, write feature spec,…
sharingan
This skill should be used when the user asks to clone and analyze a repository into a portable context bundle, such as "clone this repo and build reusable…
integrated-reasoning-v2
Enhanced meta-orchestration for selecting and combining reasoning patterns. Now includes 9 methodologies (ToT, BoT, SRC, HE, AR, DR, AT, RTR, NDF) with…
revor-company-discovery
Discover and rank a list of companies matching a natural-language ideal customer profile through Revor Websets. Use when the user asks to find target…
eval-triage
Investigate failing experiments and evaluations with LangWatch. Triage a failing experiment run to the exact rows and evaluator scores that regressed, then to…
improve-setup
Expert AI engineering consultant for your LangWatch setup. Audits your codebase, traces, evaluations, and scenarios, then guides you to improve — starting from…
codebase-litter-audit
Find unfinished code litter