AGENT SKILLS · MISSION KIT
Useful agent skills ranked by real adoption
Browse verified skills from public repositories. Compare what each skill does, package contents, install activity, and source evidence before adding it to your agent.
- CATALOG SCOPE
- VERIFIED
- skills
- 22,433
- repositories
- 3444
- last synced
- Oct 28, 2026
bateau84synabun-memory
Use Synabun memory tools to recall engineering experience, preserve proven architecture and hard-won implementation lessons, learn from failures, and curate stale or duplicate memories. Use when past experience may change an approach, a reusable lesson has been verified, the user asks to remember something, or memory cleanup is requested. Not a session journal or a guide to Synabun's other tools.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 18
bateau84typescript-common-practice
Baseline TypeScript engineering practice for strict projects: use the repository compiler/toolchain as a contract, keep types close to domain meaning, prefer inference without obscuring public APIs, preserve module boundaries, avoid speculative type architecture, and run the TypeScript-specific verification loop. Use for implementation or refactoring of TypeScript source.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 18
bateau84work-decomposition
Find coherent, context-bounded work groups, change surfaces, and dependencies before creating a delivery plan. Use when agreed work admits several splits, oversized execution units, one-task-per-file fragmentation, hidden integration work, or shared-state parallelism risks. Not for inventing product requirements or fixed scheduling policy.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 18
hu3rrorask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 20
hu3rrorimplement
Implement a piece of work based on a spec or set of tickets.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 20
hu3rrormy-pi-extension-maintenance
Sync a pi extension to its pi dependencies: upgrade to the latest (or pinned) version, verify the real import surface against the target's types, exports, changelog, and docs, fix breaking changes with zero behavior change (sign-off only when unavoidable).
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 20
hu3rrorno-comments
Audit the comments in a scope with the comment-sicko role, judge its findings, fix root causes, and encode claimed constraints.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 20
hu3rrorprototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 20
hu3rrorretro
Conduct a retrospective on a coding session.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 20
hu3rrorwhy
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 20
jbsanfskillver
Recover and maintain repo-native feature memory during feature work, and preserve verified reusable techniques after substantive investigation. Use for Skillver setup, feature tracking, memory queries, retrospectives, skill extraction, and feature-doc checks. Skip trivial one-off tasks.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Sep 10
miratcanpersona-driven-ux-walkthrough
Design and implement a Claude Code skill that simulates a user persona browsing a live website via Playwright and reports chain-of-thought inner voice, UX scores, and recommendations. Use when: user asks to create a "UX walkthrough agent", "persona simulation skill", "simulate a user visiting the site", "test UI from user perspective", "predictive user behaviour for UX". Example triggers: "bir kullanici personasini alip sayfada gezdirmek istiyorum", "persona gözünden walkthrough", "ux test skill
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- May 2
paragonhqa11y
Accessibility as part of building, not a pass afterwards. Semantic HTML first, keyboard order and focus management, visible focus, names for every control, ARIA only where HTML cannot, live regions, reduced motion, contrast, hit sizes, forms with linked labels and errors, headings and landmarks, inert layers, zoom to 200%, and how to test with a screen reader in five minutes. Use when building any interactive UI, when asked to make something accessible, or when a review needs an accessibility pa
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Sep 24
paragonhqpolish
The last ten percent, as a checklist. Favicons and social images, document titles, selection and scrollbar colours, focus rings, keyboard hints, tabular numbers, icon consistency, image dimensions, external link markers, anchor offsets, the 404 page, reduced motion and hover gating, tab title state, and the small fixes that separate a finished interface from a working one. Use when asked to polish, finish, ship, "make it feel done", or before a release.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Sep 24
paragonhqsurface
Colour, elevation and material for interfaces. Neutral palettes that survive dark and light mode, semantic tokens, borders versus shadows by theme, alpha overlays, contrast that passes, a single accent used sparingly, glass and blur budgets, theme switching without a flash. Use when building a palette, adding dark mode, fixing colours that look "muddy", "cheap", "flat" or "washed out", or when shadows and borders look wrong in one theme.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Sep 24
sshvarzman-salesforceactivating-datacloud
Salesforce Data Cloud Act phase. Use this skill when the user manages activations, activation targets, data actions, or downstream delivery of Data Cloud audiences and data. TRIGGER when: user manages activations, activation targets, data actions, or downstream delivery of Data Cloud audiences and data. DO NOT TRIGGER when: the task is segment creation (use segmenting-datacloud), data retrieval/search work (use retrieving-datacloud), or STDM/session tracing (use observing-agentforce).
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 15
sshvarzman-salesforceagentforce-skills-research
Research Agentforce configuration patterns — topics, actions, instructions, CLTs, knowledge, planner behavior. Searches Salesforce docs, Trailhead, internal repos (git.soma), Slack channels, and Google Docs to find working examples, known issues, and best practices.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 15
sshvarzman-salesforceharmonizing-datacloud
Salesforce Data Cloud Harmonize phase. Use this skill when the user works with DMOs, mappings, relationships, identity resolution, unified profiles, data graphs, or universal IDs. TRIGGER when: user works with DMOs, mappings, relationships, identity resolution, unified profiles, data graphs, or universal IDs. DO NOT TRIGGER when: the task is only about streams/DLOs (use preparing-datacloud), segments/insights (use segmenting-datacloud), retrieval/search (use retrieving-datacloud), or STDM/sessio
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 15
sshvarzman-salesforcepreparing-datacloud
Salesforce Data Cloud Prepare phase. Use this skill when the user creates or manages Data Cloud data streams, DLOs, transforms, or Document AI configurations. TRIGGER when: user creates or manages Data Cloud data streams, DLOs, transforms, or Document AI configurations, or asks about ingestion into Data Cloud. DO NOT TRIGGER when: the task is connection setup only (use connecting-datacloud), DMOs and identity resolution (use harmonizing-datacloud), or query/search work (use retrieving-datacloud)
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 15
sshvarzman-salesforcesf-agent-api-citations
Agent API citations — parsing and rendering cited sources returned by an agent. Use when handling the citedReferences array in an Inform response, rendering source lists or inline citations via inlineMetadata (claim + location), or linking cited records back to Salesforce.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 15
sshvarzman-salesforcesra-agent-debugger
Trace and analyze SRA (Service Rep Assistant) Agent sessions for a given Case ID or MessagingSession ID. Pulls GenOpPlan (Summary Plan), RecActorActionFeed, and full Data Cloud session trace (interactions, messages, steps, gateway calls, actions, grounded records, retriever requests/responses, observability spans). Includes knowledge grounding analysis and per-turn planner context inspection. Use when user asks to debug, trace, or analyze an SRA agent session.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 15
nousresearchsystematic-debugging
4-phase root cause debugging: understand bugs before fixing.
- 1h installs
- 1
- GitHub stars
- 255.5K
- Updated
- Oct 20
vercel-labsvue
Vue 3 renderer for json-render. Use when building Vue UIs from JSON specs, working with @json-render/vue, defining Vue component registries, or rendering AI-generated specs in Vue.
- 1h installs
- 1
- GitHub stars
- 18.7K
- Updated
- Oct 13
bmad-code-orgbmad-retrospective
Review a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket's story file and plan, diffs, commits — and produce a retrospective with sourced findings, action items, and an acceptance decision. Use when the user says "run a retrospective" or "lets retro the epic [epic]". Supports -H/--headless
- 1h installs
- 1
- GitHub stars
- 54.4K
- Updated
- Oct 20