All authors
Claude Skills by xkazm04
github.com/xkazm0452 skills0 installs13 views
- AssayMine an external source - a skills library, a repository, an article, pasted notes - for craft that belongs in the `recipes/` lane. Cross-checks every candidate against the existing corpus, gives each finding a recommended disposition (new recipe, enrich, example, lesson, lead, discard), puts the whole set in front of the operator on one screen, executes what is accepted, and remembers every deviation from its recommendation so the next run recommends better. Discarding a whole source is a su...Votes: 0GitHub stars: 2
- DeepenReview and widen an existing knowledge-bundle topic via deep web research + training data: scan a domain for undercooked subjects, research the chosen ones in mandatory-counter-evidence lanes, and land gate-clean corrections, techniques and dated field applications. Runs interactively (finding-level triage), in batch (worker-per-subject under Director diff-review), or as a long-running loop with a saturation ledger. Use when a bundle's subjects should rise above the repo they were forged from...Votes: 0GitHub stars: 2
- ForgeExtract a repository's domain knowledge into a four-layer RKB bundle in this registry: scout every context, design subjects with the operator's split doctrine, then forge each subject two-phase (expert draft + web hardening before repo reconciliation) with a bounded agent pool. Use when a new domain repo should populate the knowledge lane.Votes: 0GitHub stars: 2
- HarvestDrain the graded source queue in librarian/harvest/ through the /intake method, in parallel and in bulk - or, in backlog mode, drain the untriaged tail of past intake runs by measuring each candidate and landing only what comes back better: admit only sources that map to a measured live gap, mine a batch with scoped subagent miners, land what survives the intake discipline, then prove or refute the landing's impact with an A/B evaluation on a connected project. The loop that turns 100+ queued...Votes: 0GitHub stars: 2
- HygieneStart-of-day fleet sweep before any development: scan every project registered on this machine for open pull requests, merged or abandoned branches and worktrees, a red default branch, and open GitHub security alerts (code scanning, secret scanning, Dependabot), plus invalid Claude Code project settings via `claude doctor`, and the disk debris agent runs leave on the machine (landed scratch clones, build output, stale compiler caches, session and test-fixture temp). Cleans up what is mechanic...Votes: 0GitHub stars: 2
- IntakeMine an external source - a YouTube video, a news roundup, an article, pasted notes, a repository - for what it should change in THIS registry, and in the connected projects that consume it. Ingests the source, reads its design decisions as well as its claims, maps both against existing bundles for prior art, triages with the operator, and lands what survives corroboration - amendments for boundary cases, techniques and subjects for mechanisms, forge handoffs for systems whose architecture th...Votes: 0GitHub stars: 2
- LibrarianMaintain the registry as a whole: sweep every bundle for structural and quality decay, rank what needs work by measured attention points, and dispatch scoped /deepen or /forge workers at it. Also evaluates the lane skills from their per-run log (`/librarian skills`). Keeps coverage memory in an Obsidian vault under librarian/ so each run knows what the last one touched, what is saturated, and what is owed. Run manually; a scheduler is a later wrapper. Use when nobody has looked at the registr...Votes: 0GitHub stars: 2
- ReconcileRun the external-reconcile lane as its director: pick a bundle's single-stack subjects, choose world-class counterparts by class (repository, specification, public record), pin them, dispatch scoped Opus workers under docs/reconcile-brief.md, review every diff, then run the technique cycle that lands measured disproofs and two-sighting families. Portable across devices - resolves everything from the registry checkout, not from any one machine's project fleet. Use when a bundle carries single-...Votes: 0GitHub stars: 2
- Sources**Class: paper** (single primary, cs.AI, submitted 2026-08-27). Expected yield stated before extraction, per the class entry: *authoritative for its measurement in its protocol, weak for its framework - framework papers are the class's marketing; measurements, failure taxonomies and negative results are its substance.* This is a framework paper, so the prediction was that its named architecture would yield little and its ablation and transfer tables would yield the run. That is what happened:...Votes: 0GitHub stars: 2
- Sources**Class:** practitioner skill repository (prompt-only, no runtime). Operator focus: hiring domain. Commit `634a8dd8`. Expected yield: one subject at most, mostly from the reference documents; the README is its advertisement. Swept: story-mapping engine, gap-handling module, calibration engine, differentiation, challenge protocol, evidence sourcing, JD decode, transcript processing, version roadmap. Live siblings at start: 4, none on recruiting.Votes: 0GitHub stars: 2
- Adopt BpOnboard any codebase into the bp product blueprint. Checks which artifacts the repo already has (context map, app-structure v3 map, events, lens-scan store, registration) and produces only what is missing: a v3 map with domains, capabilities, features and evidence-based stages; an events log from git history; static metrics in the lens-scan store; LLM judgement facets, proposals and coverage; then validates with bp's own validator and registers the repo so bp's project switcher shows it. Dete...Votes: 0GitHub stars: 2
- Agent Guidance BootstrapCreate or refresh a repo's AGENTS.md so an agent joining the codebase gets commands, architecture and constraints without guessing. Use on a repo with no agent guidance, or when the existing file has gone stale.Votes: 0GitHub stars: 2
- ArchitectHeavy structural codebase scan - surfaces weak patterns to upgrade and strong patterns to codify, and proves whether the repo's own gates (lint rules, hooks, CI checks, type rules, test guards, ratchets) still fire, producing ADR-style decisions with a durable cross-session backlog. The highest-risk / highest-payoff scan in the suite; walks the context map area by area. Modes: scan (one theme, parallel-angle sweep), area (one area), gates (inventory every gate touching a theme, state what it ...Votes: 0GitHub stars: 2
- Ci BootstrapGive a project its first real CI gate, built only from commands the repo already declares, and ratcheted so it goes green on day one. Use when a repo has no CI, has CI that has never passed, or has CI nobody trusts.Votes: 0GitHub stars: 2
- Ci Gate CheckRun the exact checks CI enforces before you push, so a red pipeline is never how you find out. Use before every push, before opening a PR, and after an agent finishes a batch of edits.Votes: 0GitHub stars: 2
- Ci TriageTurn a red build into a located first cause and a scoped fix proposal, without scrolling the whole log or weakening the check. Use when CI fails and you need the actual reason.Votes: 0GitHub stars: 2
- Cloud DispatchSpend the Claude Code cloud-session credit as a parallel engine beside local agents. Ships a self-contained brief to a `claude --cloud` session that clones the GitHub origin, works on branch claude/cloud-<id> and returns one pull request with a RESULT.md for local review. Two ways in: explicit dispatch (a plan by default, --go to launch) and overflow - fan-out skills queue cloud_ok briefs before dispatching local workers, and a StopFailure hook ships the still-queued ones when the seat hits i...Votes: 0GitHub stars: 2
- ConformEvaluate this repository against the registry standards that govern it, one context at a time, and keep the verdicts. Reads .ai/registry-map.json (the generated join between this repo's contexts and the registry's subjects), picks the highest-value unevaluated or stale pairs, reads the governing golden path and techniques against the context's real code, and writes back conformant / deviation / not-applicable with file:line evidence - so the map becomes a standing, incrementally-completed dev...Votes: 0GitHub stars: 2
- ConsultConsult the ai-registry's knowledge bundles before a product, architecture or domain decision: resolve the registry (local checkout or GitHub), pick the bundle(s) this repo consumes, match the task against subjects and techniques by their use_when triggers, read the golden path + the techniques that apply, apply them, and log the consult so the signals lane can count demand. Use before designing a feature, choosing a pattern, writing a prompt/rubric, or making a product call in any domain the...Votes: 0GitHub stars: 2
- ContestBlind design contest between CLI agent seats (Claude Code, Codex CLI, Grok CLI, Antigravity agy). Each participant you name - engine:model@effort - builds three genuinely different prototype variants of one idea in its own workspace; a cross-family panel scores every variant blind on seven dimensions (wow, clarity at scale, wayfinding, interaction, craft, concept, utility); the host adds a visual pass in a browser; an optional reveal round lets every seat see the whole field, keep one of its ...Votes: 0GitHub stars: 2
- CouncilStrict, evidence-first triage of ONE already-built feature or ONE architecture redesign, ending at a human gate the method itself may never pass. Bounded members each answer a single question - worth to the user, workmanship, prior art, resilience, running cost, undo cost - reading only an evidence pack built from the tree, never the implementer's own account and never another member's answer. Mechanical members go first and an early exit stops the round on a security hard-fail or a measured ...Votes: 0GitHub stars: 2
- CxUse when a prototype or app already exists and the job is to make its user experience good, or to finish it. Walks the product's user journeys screen by screen with a CX/UX lens: at each stop a short overview of the screen as the user meets it, 3-6 specific improvements graded by impact and effort, each naming its heuristic and the project's design doc, the user's own read and expectation for that stop, then executor subagents that make the accepted changes - verified by gates and a screensho...Votes: 0GitHub stars: 2
- DojoAutonomous infinite training loop for media-generation craft: each cycle reflects prior human verdicts into the consuming repo's prompt surfaces, scans the registry for the weakest knowledge dimension, researches one candidate technique, generates seed-matched A/B pairs with the LOCAL image/video stack, machine-judges them pairwise, and parks the cycle for human gating in the app's Foundry -> Dojo tab. Human verdicts are consumed by the NEXT cycle, never immediately; approved improvements lan...Votes: 0GitHub stars: 2
- ExplorerShort, interactive, joins-first probe sweep of one codebase area. Picks a (context, lens) pair that neither explorer nor scan-sweep has run yet (scripts/pick.mjs reads the context map, explorer's coverage ledger and scan-sweep's history), runs a catalog of one-command cross-layer probes before sampling any file (a gate matrix over a route family, the repo's own idiom where it was not applied, a test title contradicting its assertion, a comment citing a gate, Known gaps docs, flags with no rea...Votes: 0GitHub stars: 2
- Flake RegisterQuarantine an intermittently failing test as tracked debt - owner, cause, expiry - instead of deleting it or leaving it to rot. Use before muting or skipping any test, and on a schedule to review the register.Votes: 0GitHub stars: 2
- FriendUse when the operator wants steady product momentum in ONE area of a codebase: an endless single-area companion loop that scans the area, proposes 5 development directions seeded from evidence (the area's registry-map deviation pairs and their golden-path techniques, the directions ledger, sibling passes and backlogs, and which earlier friend branches were merged), executes the picked one in a worktree with the repo's conventions as atomic commits, reports, and proposes 5 more. Interactive by...Votes: 0GitHub stars: 2
- I18n TranslateCopywriting-grade, context-aware localization for any managed app - a transcreation loop (draft -> typed MQM estimate -> gated refine) with an engineering guardrail. Portable across i18n stacks via a per-repo contract artifact; keeps a glossary, per-locale style guides, and gold exemplar pairs in the target repo so run N+1 stays consistent with run N. Invoke with /i18n-translate <mode> [locale] [scope].Votes: 0GitHub stars: 2
- IllustrateTake an existing web component that explains a concept with conventional web design (a card grid, a bulleted feature list, a static diagram, decorative art) and give it an illustration layer that carries the claim: read what the section is trying to prove, think divergently about how to abstract it graphically, then prototype three directional illustration variants inside the component behind a tab switcher, with the original kept as the default tab. Use when a landing, marketing, onboarding ...Votes: 0GitHub stars: 2
- KitRevitalize and unify the design of a web app: measure style divergence per module, gate a foundation (type scale, muting, colour roles) with the owner, stop new slips with ratchets and agent law, run a contest for a COMPOSITION KIT (the shared building blocks one level above buttons), port the finalists onto one real page so the owner chooses on the product, promote the winner at 0 measured deviations, then rebuild the app module by module in feature batches across sessions, with a coverage l...Votes: 0GitHub stars: 2
- Kpi SimKPI Simulation - measure a project's KPIs locally, simulate user behavior with UAT-style Characters, and predict real-world targets from web benchmarks, writing a result.json the Personas app ingests into its KPI module (env-tagged simulated series + proposal-gated adjustments). Engine doctrine mirrors src/features/teams/sub_kpis/kpiSimPrompt.ts - the app dispatches the same contract into managed repos as a Fleet Dev-runner session, so most target repos never need this skill installed. Invoke...Votes: 0GitHub stars: 2
- Lens ScanMeasure a product feature by feature through one lens - development, security, design, or any lens whose manifest declares a scan block (judgement, or composed script / conform / judgement steps) - and record hard numbers over time in a local store inside the repo, then propose backlog items that each name the metric they move and the expected delta against a registry or house standard, and execute only the items a person approved in the review UI - into a pack branch a person triages item by...Votes: 0GitHub stars: 2
- LeonardoGenerate images with OpenAI GPT Image 2.5 (Sunburst for detail, Flare for speed) or Leonardo AI (fallback), remove backgrounds, analyze with Gemini vision, and write SVG. For brand assets, UI illustrations, backgrounds, and icons.Votes: 0GitHub stars: 2
- Llm BenchCompare models head-to-head on ONE declared LLM use case of a connected project, and return a rating table a human can act on. Picks the project and the use case from tracklight's use-case registry (registering them if the project has none), fans the identical task across an arm per model - hosted Nebius open-weight models, an OpenAI-compatible endpoint, and the local Claude Code CLI - mirrors every call to tracklight so cost/latency land beside the project's real traffic, then judges the out...Votes: 0GitHub stars: 2
- MaintainRun resumable maintenance after rapid development: reduce demonstrated code debt through small verified refactors, defect repairs, tests, dependency upkeep, and documentation corrections. Use for sustained codebase maintenance; product ideation and redesign belong to other workflows.Votes: 0GitHub stars: 2
- MotionizeUpgrade a generic UI icon or loading/empty state into a traced, motion-animated SVG. Generates flat trace-friendly art (via /leonardo tools), validates with Qwen vision, vectorizes to a clean multi-path SVG, and emits a motion reveal component driven by the shared motion-preset library (draw, staggered-draw, fade-pop, float, pulse, hover-response, success-settle). For icon + loading-state visual upgrades - NOT raw image generation (use /leonardo for that).Votes: 0GitHub stars: 2
- MvpLaunch-readiness orchestrator for taking a dev project (typically NextJS) from "advanced WIP" to first market release. Assesses 21 checklist items across 7 chronological phases (Define -> Rails -> Automate -> Harden -> Polish -> Market -> Launch gate), reports an honest scorecard, then walks each phase with batched select decisions and executes accepted work with subagents. Delegates infra to passport-onboard, artifacts to project-populate, security to security-review instead of duplicating t...Votes: 0GitHub stars: 2
- Native CopyWrite, check and review native-quality ENGLISH web copy where it lives: i18n JSON catalogs, TS dictionary modules, hardcoded JSX text, MDX. Records the product's declared English (US/UK spelling, dash system, quotes, case per element) in a copy contract counted against the real strings, gates changed copy with a zero-dependency checker whose every finding cites a registry EN-* rule ID (baseline ratchet, coverage printed), runs an anchored checklist review for judgment rules, and drafts page c...Votes: 0GitHub stars: 2
- Npm UpdatesFetch npm package updates, analyze new features, and identify improvement opportunities for this app. Use when the user wants to explore what's new in dependencies or plan next development directions.Votes: 0GitHub stars: 2
- OnboardingTake a fresh clone of an app repo to a running, honestly-labelled install in one conversation: probe runtime deps, ask which connector capabilities the operator wants, collect keys into .env.local without ever echoing a secret, verify by booting the app, and hand back a capability matrix with three honest states per group (works / degraded with a stated fallback / hidden). Runs on generic defaults with no configuration (probe node, git and the Claude CLI; read .env.example; boot the dev scrip...Votes: 0GitHub stars: 2
- PerfectSession-after-session product perfection loop. The strongest available model at xhigh reasoning (currently Sonnet 5.5) directs - it walks the repo's context map context-by-context, proposes up to 5 challenged, high-value directions per context (features, design elevations, significant optimizations), gates them with the user until the pool is full, then orchestrates Sonnet-class builder subagents on ONE shared branch - grouped so their write sets cannot collide - while making every review/mer...Votes: 0GitHub stars: 2
- Project PopulatePopulate a newly managed repository with the data Personas needs to maintain and develop it - a context map, a feature (use-case) inventory, a triaged KPI set, and optionally simulated KPI data for a product that has not shipped yet. Contexts and features are assigned autonomously; KPIs are negotiated with the operator wave by wave. Scopeable - run all four lanes or just the ones you name. Dispatched by the passport wall, or run standalone with /project-populate.Votes: 0GitHub stars: 2
- PromotePromote a specific, already-existing pattern in this repo into the Personas workspace knowledge library - the grounded CLI equivalent of the "New practice" button in Dev Tools -> Workspaces -> Knowledge Library. Unlike /practice-harvest (a broad <=15-item sweep the agent chooses), /promote is targeted at ONE pattern the operator names, reads the real code, and writes the evidence. Emits the same `practice-harvest/runs/<id>/result.json` the app ingests through its one governed door - never tou...Votes: 0GitHub stars: 2
- ResearchExtract actionable improvements for a project from external sources (video, blog, article, raw text). Scores ideas against the codebase, buckets into Code / Template / Credential, and persists findings to an Obsidian memory vault.Votes: 0GitHub stars: 2
- Scan SweepLong-running quality sweep that walks a repository context by context, reads each area's code once, judges it through every scan lens, and lands what it can PROVE itself with atomic commits. With no arguments it runs the STABILIZE loop - bug hunting, UI perfection, performance - picking the least-covered context each round and keeping a per-context lens-coverage ledger so a codebase gets swept evenly instead of repeatedly in the same corner. Every finding climbs an evidence ladder (gate > pro...Votes: 0GitHub stars: 2
- Ship LoopMilestone-driven ship-readiness loop for any app repo, resumable across sessions. Boots by profiling the stack, running the verification gate once, and fanning out read-only audit lenses into a 9-dimension scorecard plus an append-only numbered backlog; when the repo's overlay declares value journeys, a value ledger (one readiness light per journey) sits above the scorecard, every item carries a journey tag, and milestones are picked as the next slice of one journey. Work runs in user-gated m...Votes: 0GitHub stars: 2
- SparkTurn a vague product idea (a "sparkle") into a complete, grounded design through waves of select/multi-select questions - then orchestrate the build. Targets exactly which contexts/files the idea touches, scouts them before asking anything, converges the design across four perspectives (functional, UX, UI, performance/architecture), and executes via builder subagents in a worktree under Director review. Runs live in a memory vault (a linked Obsidian folder, or <repo>/.spark/ with the same sch...Votes: 0GitHub stars: 2
- StraightenDrain the fleet's version debt against the registry in one sitting. Run from the registry checkout when a bundle landing, a context-map rebuild, a rename or an uncommitted converge rebuild has left registry maps behind: classify every checked-out project's .ai/registry-map.json (modified but equal to a rebuild from HEAD: generator-dirty, committed; verdicts differ: somebody's work, never touched), rebuild through converge's builder, print one debt table across the fleet (stale verdicts ranked...Votes: 0GitHub stars: 2
- Takeover AppTake over an unknown or vibecoded fullstack app and bring it under control toward production readiness: a phased, gated sequencer over the registry's existing skills. Recon the stack, boot it, map it, score readiness, scan it through the built-in lenses plus four takeover lenses (API and LLM call hygiene, security depth, backend performance, money and privacy) with an Opus judge, import the Azure DevOps backlog into the same queue, rank every item by severity tier (0 stop-ship .. 3 backlog), ...Votes: 0GitHub stars: 2
- Test Before CommitProve a change works before it is committed by writing or extending a test that fails first and then passes. Use whenever you change behaviour, fix a bug, or accept AI-generated code.Votes: 0GitHub stars: 2
- TigerHunt a codebase's most valuable feature area and evolve it with a cross-vendor council. Use when you want the product's strongest part made markedly more valuable - not swept for defects - and a person to choose what gets built. tiger ranks feature areas by value evidence (context-map groups and the use cases they serve, git heat, product docs, the bp product tree), writes a territory dossier for the chosen one, and convenes the strongest available CLI seats from different labs (Gemini via ag...Votes: 0GitHub stars: 2