RADAR DES SKILLS · GITHUB
Des Agent Skills utiles classés selon leur usage réel
Comparez les Skills vérifiés par fonction, contenu, installations et fiabilité de la source avant de les ajouter.
- PÉRIMÈTRE
- VÉRIFIÉ
- Skills
- 15 628
- dépôts
- 2528
- dernière synchronisation
- 12 oct. 2026
hubspotdeal-management
Run the full deal lifecycle from CLI — discover pipelines/stages, qualify MQLs into deals with associations, advance/reassign in bulk, hunt stalled deals, and close.
- installations
- 5
- GitHub Stars
- 26
- Mis à jour
- 1 oct.
hubspotquote-to-cash
Build the product catalog, assemble quotes (line items + associations to deals), and track invoices and subscriptions through to revenue.
- installations
- 5
- GitHub Stars
- 26
- Mis à jour
- 1 oct.
hubspotsales-execution
Log sales activities — calls, notes, meetings, tasks — against contacts and deals, with the mandatory create-then-associate step that makes them visible in the CRM.
- installations
- 5
- GitHub Stars
- 26
- Mis à jour
- 1 oct.
hubspotsales-reporting
Daily briefings, pipeline snapshots, and win/loss analysis from the terminal — closing-this-week, open pipeline by stage/owner, and closed-won vs closed-lost over a period.
- installations
- 5
- GitHub Stars
- 26
- Mis à jour
- 1 oct.
hubspotteam-ownership
Assign and reassign CRM record ownership, audit who-owns-what across object types, and handle rep transitions. Built on bulk-operations.
- installations
- 5
- GitHub Stars
- 26
- Mis à jour
- 1 oct.
hubspotticket-resolution
Create, triage, advance, and close HubSpot support tickets — pipeline discovery, contact/company association, priority queues, bulk stage moves, resolution close-out.
- installations
- 5
- GitHub Stars
- 26
- Mis à jour
- 1 oct.
sambercorporate-event-strategy
Decide what a company-run technical event is funded to accomplish, before anyone plans it - the goal mix (ecosystem goodwill, developer adoption, customer retention, sales pipeline, or a blend), who owns the budget line and which functions co-fund it, and the measurement commitment written before registration opens. Use whenever a company asks why it is running a user conference, community day, developer summit or roadshow, which goal to optimise, who should pay for it, or how to prove it worked
- installations
- 5
- GitHub Stars
- 2
- Mis à jour
- 28 sept.
samberevent-comms-channels
Design the attendee-facing communication channel architecture for one edition of a technical event - which channels exist, who is on each, which class of message routes to which channel, how several writers stay consistent executing a register set elsewhere, and how every channel is wound down once the event ends. Use whenever asked whether an event needs a chat space, an app or a status page, where a room change or schedule slip should be announced, how to stop attendees missing announcements,
- installations
- 5
- GitHub Stars
- 2
- Mis à jour
- 28 sept.
samberevent-sponsor-outreach
Run the sponsor sales motion for a technical event, from target list to signed yes - target list building and scoring, outreach timed against sponsor fiscal-year budget lock-in, first-touch channel choice (warm intro, referral ask, cold email under sponsor-specific etiquette), the exploratory call, capped follow-up cadences, objection handling, pipeline tracking, and renewal versus net-new as distinct motions. Use whenever the user mentions finding sponsors, a sponsor outreach email, pitching a
- installations
- 5
- GitHub Stars
- 2
- Mis à jour
- 28 sept.
suzhengk2f-company-deck
Turn company facts, brand inputs, and stakeholder goals into a polished company overview deck with clear positioning, proof, and contact-ready closure. Use when the user asks for a company deck, corporate overview, company profile presentation, or brand deck (not a fundraising pitch or sales proposal). Create company decks with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and desig
- installations
- 5
- GitHub Stars
- 2
- Mis à jour
- 1 oct.
suzhengk2f-thesis
Blueprint degree theses from scattered drafts, data, and institutional rules—chapter arc, synthesized literature, evidence maps, and defense-ready hierarchy. Use when the user asks for a thesis, dissertation, PhD/Master’s manuscript, multi-chapter thesis, or thesis outline from notes or partial chapters. Create thesis documents with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and
- installations
- 5
- GitHub Stars
- 2
- Mis à jour
- 1 oct.
sentimonybranch-finish
You MUST use this when verified development work needs an integration decision - before merging, pushing, opening a pull request, preserving a branch for handoff, discarding work, or removing a workspace - covering which finish options the actual environment allows, which base branch the evidence supports, whether the verification verdict still applies to the current tree, and whether the workspace is provably ours to clean up.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonydebugging
You MUST use this when investigating bugs, regressions, failing tests, build or integration failures, flaky behavior, performance anomalies, or other unexpected technical behavior.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonyfrontend-crafting
You MUST use this when creating, redesigning, reviewing, or polishing a user interface - landing pages, product and dashboard screens, marketing surfaces, component work, visual and UX critique, and design-quality passes over existing frontend code. Not for driving a browser to verify that a local web app works, which belongs to web-debug.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonygit-worktree-isolation
You MUST use this when development work needs a decision about where it will run - before implementing a plan, starting risky or long multi-file work, dispatching parallel or subagent work units, or reproducing a bug in a clean environment - covering whether isolation is needed, reusing existing isolation, and selecting a harness-native workspace, a Git worktree, or safe work in place.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonyinline-plan-dev
You MUST use this when an implementation plan already exists and is to be executed directly by the current agent in this session - after choosing inline execution over subagent orchestration, or when resuming an interrupted execution - covering which plan details went stale against the current tree, which failures are ordinary work rather than blockers, how deep each task must be verified, and what fresh evidence closes the plan.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonymaintaining-agent-context
You MUST use this when auditing, improving, restructuring, or maintaining a repository's agent instruction and context architecture - AGENTS.md, CLAUDE.md and its variants, .claude/rules/, the instruction layer of SKILL.md files, or docs linked from them - including reducing always-loaded context cost, finding stale, duplicated, or conflicting instructions, and keeping Claude Code or Codex project memory aligned with the codebase. Not for documentation written for human readers, and not for auth
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonyparallel-agents
You MUST use this when several units of work might run concurrently through agents - independent investigations, specialist reviews, repository analyses, or plan tasks that look unrelated - covering whether they are genuinely independent, which mutable state needs isolation, how wide the wave should be, and how results are reconciled before integration.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonyreview-request
You MUST use this when a completed or partially committed implementation needs an independent code review against explicit requirements, a defined task scope, and the actual Git diff, including committed and working-tree changes.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonyreview-resolution
You MUST use this when code-review findings, PR comments, CI review output, or reviewer suggestions need technical validation before any fix or disposition, including feedback from human reviewers, subagents, GitHub, static-analysis tools, or external review systems.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonysubagent-plan-dev
You MUST use this when a sufficiently concrete implementation plan is to be executed through scoped subagents rather than inline - after choosing subagent execution, or when resuming an interrupted orchestration - covering how each task brief is scoped, which risk level drives implementer and review strength, what independent verification the controller owns before accepting a task, and when a stalled fix loop escalates.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonytdd
You MUST use this when implementing a behavior change - a feature, a bug fix, or a refactor whose contract is checkable - especially when a test could fail for a setup reason, assert the wrong boundary, pass without proving the requirement, or cross module, API, external, state, security, or visual boundaries. Not for purely mechanical edits with no observable behavior.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonyverification-gate
You MUST use this when work is about to be called complete, done, fixed, ready, or mergeable - before a completion claim, a merge or pull request, a branch finish, or a handoff report.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.
sentimonycommit-all
User-invoked via /commit-all only. Gathers the working tree into a single commit on the current branch, no push.
- installations
- 5
- GitHub Stars
- 6
- Mis à jour
- 5 oct.