Total 58,118 skills
Showing 12 of 58118 skills
Manage persistent context threads for cross-session work
Use when asked to tag or cut a patch, minor, or major release. Tags the remote default branch in the repo's convention, pushes, and watches the release to green.
Use when asked to "ship it", commit and open a PR, or get CI green. Verifies locally, commits, opens the PR, and loops on CI until every check passes.
Use for stacked PRs with the gh-stack extension: creating, viewing, editing, pushing, submitting, syncing, rebasing, merging, or checking out a stack, or splitting multi-part work into reviewable layers. Also use whenever a stack is checked out or the user mentions stacks, branch layers, or dependent PRs.
Use when a repo has .sops.yaml and secrets/<env>.env, or a pnpm secrets script. Covers reading and writing dev secrets, prod elevation, running with secrets, and the human key setup.
Run a product sunset end to end — decide, align, plan, prepare, announce, close. Use when you need the whole EOL process, not just one artifact.
Guide developers through creating a Slack app or agent using the Slack CLI and Bolt (JS or Python). Handles prerequisites, sandbox setup, authentication, project creation from templates, and local development.
Use the ready-to-use qiqi command to handle general tasks of Qiqi Service Industry ERP. It is applicable for verifying identity and profile, discovering objects and fields, querying records or work views, handling pagination and large outputs, executing documents or approval actions, deleting records, processing attachments, or verifying writes with unclear results.
Guide to Business Semantics and Fact Judgment for Qiqi Service Industry ERP. It is used when you need to understand product capability domains, archives, documents, master-detail tables, project-based business-finance stages, statuses, references, enumerations, and time semantics, calibrate profit, budget, task or working hour calibers, or judge whether records can support a certain business conclusion.
Research and compare destinations with source-backed Gezgin data, and coordinate connected Gezgin workflows for shortlists, profile context, member discovery, follows, presence, and casual meetups. Use when a user asks for destination research, personalized travel planning, Gezgin community discovery, or meetup creation and management.
Administer MongoDB databases. Configure replica sets, sharding, and backups. Use when managing MongoDB deployments.
Generate long HTML articles for human reading — organize existing materials, experiences, and data clearly before writing. Each time it is triggered, first use AskUserQuestion to clarify 4 key parameters in one go: [Who is it for / What will readers gain after reading / Depth level / Style + Focus], then output according to the 6-stage framework. **The only output format is HTML** — this skill should not be used if the user requests markdown or direct chat responses. It is triggered when the user says phrases like "do a retrospective", "summarize this", "compile into HTML", "create a tutorial/study guide", "explain X clearly", etc., which require structured reading content of over 500 words. It is not applicable for: project plan reports/framework plans/version roadmaps (use issue-pool, which has built-in md2html), PRDs/requirements documents/test cases (use prd-test-writer), interface design drafts (use design-exploration), naming (use product-naming), writing code/fixing bugs/modifying files, or questions that can be answered in one or two sentences.