Recently active skills
Trending is calculated from star growth this site has recorded itself. No history is estimated or back-filled.
Not enough history yet: 2 of 7 days recorded. Until then this list is ordered by the most recent content change.
71536 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| submission-readerDavidCho1999/archaiflow-skillsReads a letter from an authority — a correction letter, a completeness notice, a staff report, a conditional approval, a denial — and separates the four things inside it that behave differently: what must change, what must be shown, what must be answered, and what is a comment with nothing to do. Then finds the parts that carry a clock, since a response period or an appeal window is usually one line in the middle of a page. Trigger on "they sent this back", "read this correction letter", "what does the city actually want", "plan check comments came in", "submission-reader", or any letter from an authority handed over to work out. Carries no procedures and no periods; every deadline comes from the letter or from the jurisdiction. `plan-check-response-builder` writes the response; this works out what the letter asked. It does not replace the code consultant, the expeditor, or the Architect of Record. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| submittal-log-builderDavidCho1999/archaiflow-skillsReads a project specification section by section, pulls out every submittal each one calls for, classifies it, and assembles a submittal log ready to issue. Trigger on "build submittal log", "submittal log", "extract submittals from spec", "shop drawing log", "submittal register", "submittal-log-builder", or a pasted specification section list. Works with any specification format and any contract. The user supplies the spec text by pasting it, naming files to read, or pointing at an indexed PDF, and supplies the review durations from their own contract. The skill never invents a submittal, never carries a list of typical submittals, and never assumes a review duration: every row traces to a line in the user's spec, and anything it could not find is listed as a gap rather than filled in. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| submittal-reviewDavidCho1999/archaiflow-skillsThis skill should be used during construction administration when the user shares a contractor submittal — shop drawings, product data, samples, or mockup documentation — and wants it reviewed for conformance with the contract documents. Trigger on 'review this submittal', 'shop drawing review', 'check this product data', 'submittal log', 'is this approved', 'spec compliance check', 'AIA G712', or pasted submittal content paired with CA-phase context. Generates a structured submittal-review markdown in `docs/submittals/` and appends to the project submittal log. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| survey-reviewDavidCho1999/archaiflow-skillsReads a land survey the way a design team has to: establishes what kind of survey it is and therefore what it is certified to show, checks it against what the project actually needs, and reports the gaps before a scheme gets built on top of them. Separates what was measured from what was compiled from records, works the boundary, the encumbrances, the topography, the utilities and the datum in that order, and flags every place the drawing shows a line that no instrument supports. Trigger on "review the survey", "is this survey adequate", "what's missing from this survey", "ALTA survey review", "survey-review", or a survey handed over at the start of a project. Carries no survey standards and no certification requirements; the standard the survey was made to comes from its own certificate. It is not a survey, does not verify a boundary, and does not replace the surveyor or the Architect of Record. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| test-fitDavidCho1999/archaiflow-skillsRuns feasibility arithmetic for a site: floors times plate against your FAR and height limits, gross to net through your efficiency, net to units through your unit sizes, parking through your ratio, laid out as side-by-side scenarios with every step shown. Trigger on "test fit", "what fits", "does it pencil", "how many units", "buildable area", "yield study", "massing numbers", "test-fit", or a pasted site area with zoning limits. Every limit and assumption comes from you or your zoning summary, cited: the skill never supplies a FAR, an efficiency factor, a unit size, or a parking ratio from memory or from web search, and a scenario built on an unverified limit says so on its face. Arithmetic only, no geometry: setback envelopes, floor plates that actually fit the lot, and massing are drawing work it does not do. Early feasibility, not a zoning compliance check (test-far checks one scheme) and never a substitute for the zoning analysis. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| thread-readerDavidCho1999/archaiflow-skillsReads a thread of emails or messages and answers the question that starts most disputes: what did we actually agree. Separates what was decided from what was proposed and never answered, tracks who was on the thread at each point since a decision made after somebody dropped off is a decision they never saw, finds the requests that were never replied to, and flags anything that quietly accepted scope, cost or time. Trigger on "read this thread", "what did we agree on this", "go through this email chain", "did we ever answer this", "thread-reader", or a chain of correspondence handed over. Carries no contract terms; whether something is binding comes from the agreement. `draft-email` writes one message; this reads a chain of them. It does not replace the Architect of Record. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| utilization-trackerDavidCho1999/archaiflow-skillsKeeps one dated record of hours against fee at the level where it can still be acted on: by phase and by person rather than by project total, with the percentage of work complete recorded separately from the percentage of fee spent, since a project can be on budget and forty percent behind. Records what caused each overrun so the pattern separates from the incident, and flags the hours that should have been additional services before they are written off. Trigger on "utilization tracker", "are we over on this project", "hours against fee", "track the team's time by phase", "utilization-tracker", or a timesheet export handed over to make sense of. Carries no rates, no utilization targets and no benchmarks; the practice sets those. It does not replace the accounting system — it reads what that produces — and it does not replace `fee-tracker`, which follows the fee itself. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| value-engineering-advisorDavidCho1999/archaiflow-skillsSorts a cost-cutting list against an issued design into accept, accept with an alternate, and block, with the reasoning written out per item across design intent, performance, lifecycle cost, schedule, risk transfer, and reversibility. Trigger on "VE review", "value engineering", "review this VE list", "where can we cut", "cost reduction options", "VE round 2", or a pasted contractor proposal with substitutions and savings figures. Works with any contract and any specification format. Performance requirements come from the user's own specification and contract; the skill supplies the sorting method and never a code threshold or a performance value from memory. Produces a recommendation memo, not a directive. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| variance-request-builderDavidCho1999/archaiflow-skillsBuilds a variance or discretionary relief application around the findings the deciding body is legally required to make, rather than around why the project wants it: extracts each required finding from the jurisdiction's own criteria, works the evidence for each one separately, tests whether the hardship claimed is of the kind the criteria recognise, and assembles the record so the decision can survive an appeal. Trigger on "variance request", "zoning relief application", "hardship findings", "special exception", "what do we have to prove for a variance", "variance-request-builder", or a zoning requirement named as unmeetable with a request to seek relief. Carries no criteria, no precedent and no legal positions; the findings come from the jurisdiction's own text. It does not give legal advice and does not replace the land use attorney, the planner, or the Architect of Record. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| view-analysisDavidCho1999/archaiflow-skillsWorks views in both directions, because a window is two things at once: what a room looks at, and what looks back into it. Establishes what is worth seeing and whether it will still be there, what each room needs to see and what it must not, where privacy runs both ways between this building and its neighbours, and which views depend on land somebody else owns. Trigger on "view analysis", "what does this room look at", "will we still have this view", "overlooking", "privacy from the neighbours", "view-analysis", or a scheme where the windows have been placed by elevation rather than by what they see. Carries no angles, no distances and no separation requirements; overlooking rules are local text you quote and sun angles come from `shadow-study`. It does not model and does not replace the Architect of Record. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| wind-snow-lookupDavidCho1999/archaiflow-skillsAssembles the site environmental criteria block a project needs before any structural or envelope design starts: wind, snow, seismic, ice, rain, and flood parameters, each recorded with the source it came from. Trigger on "wind speed for this site", "ground snow load", "site hazard parameters", "design criteria block", "seismic parameters", "rainfall intensity", "wind-snow-lookup", or a pasted site location with a request for design values. Works in any jurisdiction. The skill knows which parameters a design needs and what each one feeds; the values come from the user's own code maps, official hazard tool, or authority, supplied by typing, pasting, or naming a file. It never supplies a hazard value from memory or from web search, and reports every parameter it could not source as a gap. Returns mapped parameters only, never design pressures or loads. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| zoning-summaryDavidCho1999/archaiflow-skillsThis skill should be used when the user provides a site address, parcel info, or zoning lookup text and needs a structured zoning summary for early design. Trigger on 'zoning summary', 'zoning lookup', 'site zoning for [address]', or pasted zoning portal output. Targets North American projects (US + Canada). Generates a worksheet markdown in `docs/zoning/` and updates the project zoning index. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| qwen21-nsfw-pose-skillArekejoker/qwen21-nsfw-pose-skill | Stars: 4.4k | Updated | Claude CodeCodex | Verified | Install |
| amendsimonepri/ifttt-lintAmend the last commit with current changes and/or an updated message. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| commitsimonepri/ifttt-lintStage changes and create a commit with a conventional commit message. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| cooksimonepri/ifttt-lintFull autopilot — plan, implement, and polish a task end-to-end. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| diffsimonepri/ifttt-lintFetch and display diffs for various scopes (PR, commit, branch, staged, working tree). Used by other skills that need to analyze changes. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| executesimonepri/ifttt-lintExecute a plan file — parse phases, spawn parallel subagents, handle failures. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| forksimonepri/ifttt-lintStart or end a forked session for exploring rabbit holes without losing the main conversation's context. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| plansimonepri/ifttt-lintStructured design intake for non-trivial tasks. Asks clarifying questions and produces a design proposal. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| polishsimonepri/ifttt-lintIteratively review and fix issues on the current branch until the review passes. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| prsimonepri/ifttt-lintCreate or update a pull request with a structured description. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| researchsimonepri/ifttt-lintInvestigate a topic, library, or approach before planning. Combines user context, prior knowledge, and external sources. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| reviewsimonepri/ifttt-lintThree-phase code review. Investigates internally, verifies findings, then reports only confirmed issues. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| awwwardsjuliobsz/skillsBuild award-caliber websites from a one-line prompt such as "make me a portfolio, my name is Ana". Uses the bar of sites that win Awwwards Site of the Day as a quality standard. Covers concept, art direction, typography, motion choreography, WebGL, page transitions, real content, SEO, accessibility and performance, then visual QA in a browser. Next.js by default, Astro for animation-heavy static showcases, or the stack the project already uses. Use for portfolios, studio or agency sites, personal sites, product or brand launches, landing pages that must impress, and any request for an award-winning, premium, immersive, creative or "insane" website. To only score or review a site without changing it, use /jury. | Stars: 1.3k | Updated | Claude CodeCodex | Verified | Install |
| juryjuliobsz/skillsScore any website the way an Awwwards jury would, from evidence alone. Screenshots every page type on desktop, a throttled phone and reduced motion, measures LCP, CLS, FPS, axe, keyboard focus and hover feedback, audits SEO and metadata, then a fresh critic that never sees the code scores Design, Usability, Creativity, Content and the six developer areas, with a ranked fix list. Use when someone asks to review, critique, score, rate or roast a website, portfolio or landing page, asks whether a site is good enough for Awwwards or Site of the Day, or wants design QA of a live URL or a local build. Not for building or redesigning a site; use /awwwards for that. | Stars: 1.3k | Updated | Claude CodeCodex | Verified | Install |
| ad-account-diagnosticmbfinotti/advertising-skillsDiagnose the root cause of an underperforming paid ad account - why the ads stopped working, why CPA went up, why ROAS dropped - instead of defaulting to 'increase the budget'. Weighs tracking, account structure, targeting, creative, bidding and budget, offer, and external forces, and returns a prioritised verdict with evidence and confidence. Covers B2B and B2C on search, paid social, video, and native. Use whenever the user mentions an ad account audit, a campaign structure review, wasted ad spend, rising cost per lead, or says their ads used to work - even if they never say 'diagnostic'. Diagnosis only, and it stops at the click: post-click page problems are mbfinotti/advertising-skills@paid-landing-page-audit and creative decay is mbfinotti/advertising-skills@ad-creative-fatigue. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| ad-attribution-gapmbfinotti/advertising-skillsQuantify and explain the discrepancy between ad platform reporting, an analytics tool, and the source of truth (CRM or order system), classifying every unit of the gap as timing, definitional, or unexplained residual. Use whenever the user says the numbers don't match, that the platform reports more conversions or revenue than the CRM or order system, or mentions cross-platform reconciliation, double-counted conversions, an attribution discrepancy, or asks whether a reporting gap is normal - even if they never say 'attribution'. Covers B2B (CRM-anchored) and B2C/ecommerce (order-system-anchored). Do NOT use to fix broken or missing tracking - use mbfinotti/advertising-skills@ad-conversion-tracking instead. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| ad-audience-targetingmbfinotti/advertising-skillsTurn a business's ICP and buying signals into a layered ad audience targeting plan - cold/broad prospecting, interest and in-market behavioural segments, lookalike/similar, first-party lists, and retargeting pools - each sized against platform audience floors, budgeted to the learning threshold, and kept from overlapping by exclusion rules. Use whenever the user mentions ad targeting, who to target with ads, audience tiers or layers, broad vs. layered targeting, audience overlap between campaigns, or mapping an ICP onto ad audiences - even if they never say 'audience'. Covers B2B and B2C. Do NOT use to pick the seed customers behind a lookalike (mbfinotti/advertising-skills@lookalike-audience-seeds) or to sequence retargeting messages (mbfinotti/advertising-skills@retargeting-funnel). | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| ad-bidding-strategymbfinotti/advertising-skillsChoose the bidding policy per platform and goal - manual vs automated, cost-goal vs value/return-goal, when to switch, and how to set and move the target - written up as a policy with an evaluation window, change discipline, and a rollback trigger. Use whenever the user mentions a bid strategy, target CPA or target ROAS, smart or automated bidding, bid cap vs cost cap, portfolio bid strategies, seasonal bid adjustments, value-based bidding readiness, or delivery collapsing after a target change - even if they never say 'bidding'. Covers B2B and B2C. Do NOT use to split budgets across campaigns (mbfinotti/advertising-skills@ad-spend-allocation) or to track spend against a budget (mbfinotti/advertising-skills@ad-budget-pacing). | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |