AGENT SKILLS · ÉQUIPEMENT DE MISSION
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
- 22 403
- dépôts
- 3432
- dernière synchronisation
- 27 oct. 2026
b-mendozaresponding-to-pr-review-comments
Assess and respond to pull request review comments through a status-gated workflow: collect comments, evaluate feedback, draft replies, write a verified local report, and optionally post exact approved replies to supported GitHub review-comment threads.
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 20 oct.
hcaianocyber-audit
Check whether this machine is affected by a named CVE, malicious package, or supply-chain advisory; read-only, writes a report.
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 20 oct.
hcaianoland-it
Merge a revertible PR whose review findings are all fixed or declined with a reason, test it after merge, and check the conversation's remaining work; a change to a screen users see waits for the user's OK on its demo. Use when a PR reaches merge-ready.
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 20 oct.
hcaianotest-audit
Test value gate and pruning workflow. Use when adding or changing tests, auditing a suite for low-value tests, or running a test-pruning campaign.
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 20 oct.
lkrdevagentic-lookml
Unified LookML engineering, SQL-to-LookML refactoring, and Medallion semantic modeling skill (agentic-lookml). Combines the 14 SQL-to-LookML pattern playbooks (lkr parse sql-lookml-compare, Canonical Looker Query gate, Query-layer Table Calculations and Custom Fields with matchesfilter, and Bronze/Silver/Gold Medallion architecture) with the LookML writing reference skills from looker-open-source/looker-skills into a single reference set. Use when authoring LookML models, views, explores, fields
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 20 oct.
port-labsport-blueprints
Model a Port context lake data model using blueprints, defining identifiers, titles, icons, properties, relations, and calculation, mirror, or aggregation properties, then author them with the raw Port API. Use when asked to create a Port blueprint, define a Port data model, add a property to a blueprint, relate two blueprints, add a calculation property, add a mirror property, or add an aggregation property.
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 12 oct.
port-labsport-getting-started
Set up Port and connect it to your coding agent: sign up for a Port account, install Port's MCP server, and optionally the Port CLI. Use when asked to 'get started with Port', 'set up Port', 'connect Port MCP', 'install the Port MCP server', 'how do I use Port from Claude Code/Cursor/VS Code', or before using any other skill in this repo for the first time.
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 12 oct.
port-labsport-permissions
Configure Port's role-based access control: context lake (blueprint/entity) permissions (read, register, update, or delete entities, down to a single property or relation) and page/dashboard view/edit permissions. Use when asked to 'set up Port permissions', 'restrict who can edit an entity', 'only let the owning team modify this blueprint', 'add a dynamic read policy to a blueprint', 'control who can view a Port dashboard or catalog page', or 'why can this user see/edit something they shouldn't
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 12 oct.
port-labsport-skill-creator
Author a new Agent Skill for this repo (port-labs/port-skills): scaffold the skills/port- / directory, write valid frontmatter, structure the body as a short router into references/ and assets/, validate it, and regenerate the README index. Use when asked to create a new Port skill, add a skill to this repo, help me write a SKILL.md, contribute a skill, port an internal Port AI skill to this repo, or fix a skill that fails validate-skill.js.
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 12 oct.
screensdesign-comscreensdesign-data
Research mobile apps, broader-market competitors, positioning, public App Store reviews, onboarding, paywalls, recorded screens, user flows, App Store creatives, developers, and saved collections through the ScreensDesign MCP. Use when the user asks for mobile product or market research, app ideas, competitor comparisons, revenue/download evidence, review pain points or sentiment, UI references, visual similarity, sequence analysis, or ScreensDesign MCP setup and skill updates.
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 5 oct.
augmntreviewing-code
Provides structured code review with prioritized feedback. Use when reviewing PRs, analyzing code quality, checking for bugs, or auditing changes. Triggers on "review this", "check this code", PR reviews, or code quality questions.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 24 janv.
bostonaholicauditing-complexity
Ranks where code complexity concentrates in a git repository (cyclomatic complexity, nesting, fan-out, mutable state) and scores CRAP change risk from a coverage file. Read-only. Use when asked for complexity hotspots or change risk. Not for test value; use auditing-tests.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 20 oct.
bostonaholiccomposing-agent-prompts
Composes a self-contained, source-cited task prompt for another coding agent to execute in a target repository, without running the task. Use when the user asks to write, draft, or hand off a prompt, brief, or task spec for another agent. Not for system prompts; use writing-system-prompts.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 20 oct.
bostonaholicconducting-deep-research
Conducts source-backed, goal-directed research that combines a scholarly evidence review with an institution, company, or funding map. Use when a request needs both an evidence review and an organization or funding map. Not for quick lookups or general research write-ups.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 20 oct.
bostonaholiccutting-skills
Audits or trims an existing agent skill to its behavioral core and narrows over-broad trigger metadata. Use when the user asks to cut, simplify, shorten, de-slop, or reduce the context cost or trigger aggressiveness of a SKILL.md or skill folder. Never infer from a skill being long or edited for another purpose.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 20 oct.
bostonaholicfixing-root-causes
Traces a bug or failure to its root cause and fixes it there instead of patching the symptom. Use when debugging a crash, failing test, regression, or "fails after restart" bug, or when a fix would add a guard, retry, or workaround to silence an error.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 20 oct.
hungrykelvin123roblox-physics
Design or review Roblox assemblies, constraints, collision, hit detection, and network ownership.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 4 sept.
salimhamedwt-destroy
Destroy a worktree — close any PR, delete local and remote branches, and remove the worktree, discarding all uncommitted changes. Optionally takes a branch name argument; defaults to the current worktree.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 22 sept.
alber70gorchestrator
Session mode where the main thread orchestrates: subagents on a cheaper model do research and execution, the main thread plans and validates. Use when the user runs /orchestrator, asks you to act as an orchestrator, asks to keep the main thread token-efficient, requests a large implementation plan or a large research task, or wants you to work toward an overarching goal.
- installations
- 1
- GitHub Stars
- 0
- Mis à jour
- 18 oct.
albertmartorell1975compose-recomposition-performance
Use when investigating Jetpack Compose recomposition performance, skippable/restartable composables, composables.txt or compiler reports, Layout Inspector recomposition counts, back-writing snapshot state across phases, or frame-rate State reads in composition vs layout/draw, and it is not yet clear whether the cause is parameter stability, deferred reads, or cross-phase back-writing.
- installations
- 1
- GitHub Stars
- 0
- Mis à jour
- 20 oct.
firegoat-aireading-browser-screenshots
Use when a session trace contains browser-agent screenshot turns, or when a run's friction happened in the browser (login, signup, OAuth, dashboard) rather than in the code agent's terminal.
- installations
- 1
- GitHub Stars
- 0
- Mis à jour
- 20 oct.
irfanfaraazgpt-taste
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
- installations
- 1
- GitHub Stars
- 0
- Mis à jour
- 21 avr.
irfanfaraazredesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
- installations
- 1
- GitHub Stars
- 0
- Mis à jour
- 21 avr.
itamarweiceberg-optimizer
Diagnoses an Apache Iceberg table and produces a ranked, cost-aware plan covering three domains: table layout (compaction, partition evolution, format upgrade), ingestion pipeline (write distribution, file sizing, sort order at write time), and maintenance (snapshot expiry, orphan cleanup, manifest rewrite). Use when asked to optimize, tune, speed up, shrink the cost of, clean up, repartition, compact, or design a maintenance schedule for an Iceberg table, or to decide whether a table is even wo
- installations
- 1
- GitHub Stars
- 0
- Mis à jour
- 1 juil.