Showing 16291–16320 of 77205 skills
Use this skill when the user keeps paper notes inside an Obsidian project knowledge base and wants filesystem-first literature review, explicit agent-first Zotero ingestion, `Papers/` plus `Knowledge/` synthesis, collection-wide normalization, and a default literature canvas without Obsidian MCP.
brycewang-stanford/Auto-Empirical-Research-Skills
Use this skill when the user is discussing daily research work, TODOs, plans, standups, meetings, milestones, or general project progress that should be reflected in Obsidian daily notes, plan notes, and hub updates.
brycewang-stanford/Auto-Empirical-Research-Skills
Use this skill when papers are collected in Zotero but the user wants detailed reading notes, project-linked literature synthesis, collection-wide paper-note coverage checks, and a connected knowledge map inside the bound Obsidian project knowledge base.
brycewang-stanford/Auto-Empirical-Research-Skills
Draft sections of the sewage-house-prices academic paper. Handles section drafting for the Overleaf LaTeX manuscript, notation protocol, anti-hedging, and humanizer pass. This skill should be used when asked to "draft the paper", "write up the results", "write the intro", or draft any section of the manuscript.
brycewang-stanford/Auto-Empirical-Research-Skills
Journal targeting analysis for the sewage-house-prices paper. Recommends ranked journal list across 3 tiers with formatting requirements, submission strategy, and desk rejection risk assessment. This skill should be used when asked to "target a journal", "where should we submit", "journal fit", or "submission strategy".
brycewang-stanford/Auto-Empirical-Research-Skills
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.
brycewang-stanford/Auto-Empirical-Research-Skills
Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary.
brycewang-stanford/Auto-Empirical-Research-Skills
Before building a feature or fix, search for open-source libraries that already solve it and decide per piece whether to adopt one or build it. A library is adopted only when it is actively maintained, not outdated, and compatible with the project's exact stack (versions, runtime, module format, types). Use when scoping a large or already-solved capability, or when the user asks "is there a library for this", "should we build this ourselves", or wants to avoid reinventing something.
ayoubben18/ab-method
Draw a task's blast radius twice. BEFORE implementing, a PLANNED map of the modules the missions expect to add, change or touch; AFTER the reviewers pass, an ACTUAL map derived from the real diff, plus the DRIFT between them. Writes docs/tasks/<task>/change-map.md. Use from create-task / extend-task (planned pass), and after review-implementation + sync-architecture in create-task / resume-task / start-task / start-roadmap (actual pass), or standalone on a task.
ayoubben18/ab-method
Shared vocabulary and principles for designing deep modules — small interfaces, clean seams, testable through the interface — grounded in Ousterhout's A Philosophy of Software Design. Holds the seam doc format, the default seam catalog and the book's red flags. Use when designing or improving a module's interface, deciding where a seam goes, writing a seam doc, hunting deepening opportunities, or when another skill needs the deep-module vocabulary.
ayoubben18/ab-method
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
ayoubben18/ab-method
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Parks the rare question you genuinely can't answer yet as an unresolved question with a placeholder, so the build proceeds instead of stalling. Use when user wants to stress-test a plan against their project's language and documented decisions.
ayoubben18/ab-method
Use when writing a PR body. Summary that shows the change, Evidence that it works, Merge Danger that says how risky it is to land. Inside an AB Method task it fills from change-map.md, the tracker's ## Protected evidence, ADRs and docs/seams/.
ayoubben18/ab-method
Cross-plan coherence critic for a whole roadmap. Reads roadmap.md plus every planned task's progress-tracker.md and pushes back ONLY on genuine discrepancies BETWEEN the finished plans — broken seams, coverage gaps, duplicated work, reversed/missing edges, terminology drift, conflicting assumptions. Read-only; silent when the plans cohere. Run standalone after planning finishes and before /start-roadmap.
ayoubben18/ab-method
Post-implementation review. Spins up three read-only critics on a completed task's diff — cleaner-architecture, slop-defender, reusability-inspector — that push back ONLY on real issues. Autonomous runs apply safe fixes (tests-green-gated) and write everything to review.md next to progress-tracker.md; interactive runs present findings to pick. Use after a task's missions are done (from start-task / start-roadmap / create-task) or standalone on a diff.
ayoubben18/ab-method
Post-implementation documentation-sync detector. Spins up ONE read-only subagent on a completed task's diff to find everything the change introduced that the architecture docs don't yet know about — new endpoints, patterns, seams, dependencies, domain terms, ADR-worthy decisions — routed to the exact doc each belongs in. Autonomous runs apply only in-place safe edits that pass the check-docs budget gate and defer domain/ADR reshapes; interactive runs present the proposed doc deltas to pick. Use after a task's missions are done (from create-task / start-task / start-roadmap) or standalone on a diff.
ayoubben18/ab-method
Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
ayoubben18/ab-method
Use when stuck, confused, or disoriented in a crosslink-tracked project — dumps the full context (session state, active issue, locks, blockers, hook config, git state, project rules) so you can re-orient and decide a next action. Trigger when the user says "I'm stuck", "audit", "what's going on", or asks for a context dump.
openwpm/OpenWPM
Use to check on background feature agents launched via /kickoff — running in tmux sessions or docker/podman containers. Reports each agent's state (Working / Idle / Waiting / Done / Error), captures recent output, and offers next-step commands. Trigger when the user says "check on the agent(s)", "how's the kickoff going", or names a `feat-*` / `crosslink-task-*` session.
openwpm/OpenWPM
Use to create a jj commit AND auto-document the result on the active crosslink issue. Writes a conventional-style message with the issue ref, and adds a `--kind result` comment so the audit trail closes. Trigger whenever the user asks to "commit", "commit changes", "commit and push", or finishes a unit of work in a crosslink-tracked repo.
openwpm/OpenWPM
Use when working in any repo that has `.crosslink/` and the workflow involves issue tracking, sessions, locks, swarms, kickoff, or knowledge pages. Reference for the full crosslink CLI surface plus the harness footguns (auto-CHANGELOG entries on issue close, --no-changelog flag, label-based skip rules, session lifecycle). Trigger when the user mentions crosslink commands, when the crosslink-behavioral-guard hook fires asking for issue creation, or when a session needs to be started/ended/handed off.
openwpm/OpenWPM
Use to author or iterate a feature design document grounded in actual codebase exploration. Drives a four-phase flow (Explore & Interview → Draft → Resolve open questions → Iterate) and writes `.design/<slug>.md` plus a pipeline state file ready for `crosslink kickoff --doc`. Trigger when the user says "design <feature>", "/design …", "iterate the design", or asks to write a design doc / spec / RFC for a feature.
openwpm/OpenWPM
Use to create a `feat/<slug>` bookmark AND spin up a new git worktree under `<repo-root>/.worktrees/<slug>`, then initialize crosslink hooks and an agent identity in the worktree so a child agent can work there. Trigger when the user says "make a worktree for <feature>", "/featree …", or asks to spin up an isolated workspace for a feature.
openwpm/OpenWPM
Use to create a `feat/<slug>` branch from a human-readable description and register a matching crosslink issue (priority medium, label `feature`). Slugifies the description, validates preconditions (no uncommitted changes, branch doesn't already exist), and checks out the new branch. Trigger when the user says "new feature branch for X", "make a feature branch", or "/feature …".
openwpm/OpenWPM
Use to launch a background Claude agent in tmux (or docker/podman) to implement a feature end-to-end. Delegates worktree creation, prompt building, and session launch to `crosslink kickoff run`, then prints how to attach (`tmux attach -t <session>`) and check status (`/check`). Trigger when the user says "kick off an agent for X", "/kickoff …", or asks for a background agent / sub-agent / worker to do a feature.
openwpm/OpenWPM
Use to run a periodic codebase-health pass — dependency audit, lint, test suite, dead code / TODO scan, doc freshness, crosslink issue hygiene, and build artifacts. Conservative by default (small fixes inline, larger work files a `maintenance`-labelled issue). Trigger when the user says "maintenance", "health check", "audit dependencies", "/maintain", or asks for a periodic project tidy-up.
openwpm/OpenWPM
Use BEFORE implementing code in a crosslink-tracked project — loads `.crosslink/rules/global.md`, the language rules for detected manifests, the project rules, and the active `tracking-<mode>.md`. Replaces the heavy context that would otherwise be re-injected on every prompt. Trigger when the user says "preflight", "load the rules", "ground yourself", or before starting a fresh implementation session.
openwpm/OpenWPM
Use as a pre-commit quality gate — review the working diff for stub patterns (TODO/FIXME/`unimplemented!()`/`todo!()`), debug leftovers (`dbg!`, stray `console.log`/`println!`, commented-out code), then run the project's lint, format, and test suites and verify the active crosslink issue is documented. Prints a PASS/FAIL checklist and hands off to `commit`. Trigger when the user says "review my changes", "/review", "ready to commit?", or asks for a final pass before committing.
openwpm/OpenWPM
Use to walk the user through a guided policy review of the project's crosslink configuration — tracking mode, security policies, language rules, hook implementations, and workflow conventions. Identifies drift from defaults via `crosslink workflow diff` and offers targeted fixes or a `crosslink init --force` reset. Trigger when the user says "review the crosslink config", "audit the workflow policies", "/workflow", or asks whether the hook/rules setup is right.
openwpm/OpenWPM
Add a SwiftUI component from ShipSwift. Use when the user says "add component", "add a view", "add X view", "I need a chart", "add animation", or wants a specific UI element.
signerlabs/ShipSwift