Explore

Weekdays, browser only when the card needs one. Takes the next ready cards off the launch board and does the work each one names: stages copy into the dashboard, fills a directory or press form and leaves it open in its tab, verifies a setup, packages a handoff, or researches its own next targets. It ticks its own card the moment it has verified the file that closes it. It submits only where you released the channel, sends only where you released the channel, spends only where you released it, and never touches a credential.

Runs once by hand on the first day and once a month after that. On the first run it researches the business from its own public surfaces before asking anything, writes the strategy folder, seeds the launch board, builds the tailored command center, reconciles the schedule table, and registers the recurring jobs. On every monthly run it re-reads the evidence the kit produced, applies what changed, reconciles drift, and rebuilds. It holds every outbound action unless you released the channel, and it never enters a credential.

Monthly, on the last weekday. Re-tests every segment in strategy/icp.md against the evidence in this kit's own ledgers, then rewrites the targeting itself where the evidence disagrees with the assumption the segment was written on. It records every change in strategy/CHANGELOG.md. It sends only where you released the channel, never re-queues anyone, never edits the contacted ledger, and never writes a number it did not read out of a named file.

Weekdays, file work only, no browser at all. Reads every ledger, queue file, and run record, turns yesterday's ticks into sent dates and closed cards, folds the card inbox, rewrites the launch board, and writes the short morning brief the member opens first. It holds every outbound action unless you released the channel, and it never touches a credential.

Monthly on the last weekday, light browser lane. Re-tests every theme and every severity rule against a month of real ticket evidence and rewrites strategy/themes.md wherever the evidence disagrees with the assumption. It merges two themes the evidence shows are one, splits a theme whose tickets have two different answers, retires a theme with no volume, creates a theme for a cluster that kept landing unclassified, and rewrites a severity rule wherever the outcomes contradict it. Theme ids are never reused and never renumbered. It holds every outbound action unless you released the channel, and it never touches a credential.

Weekly on a Friday, conditional browser lane. Scores the week from the ledgers with a source beside every number and an estimate nowhere, reads the review and rating movement off the member's own listing screens, replays the browser flows the weekday routines depend on, and names the one product change that would have removed the most tickets this week. It sends only where you released the channel, never posts, never resolves anything, spends only where you released it, and never touches a credential.

Weekdays, conditional browser lane. Selects from the ticket ledger hardest first, meaning by severity and then by age within severity, and writes each customer a reply into a dated queue file the member reads, edits, and sends by hand. Where the right answer is a refund, a credit, a plan change, or a cancellation, it names the remedy, the exact amount, and the exact screen, and leaves the granting to the member. It sends only where you released the channel, never posts, never resolves a ticket, spends only where you released it, and never touches a credential.

Weekdays, heavy browser lane. Reads every support channel named in strategy/channels.md, meaning the mailbox, the helpdesk queue, the review and rating listings, the marketplace pages, and the forums where the member's products are discussed, and captures every new or changed item as one dated, sourced, severity graded line on the ticket ledger. It replies to nothing, reacts to nothing, marks nothing read or resolved, and takes no action of any kind on LinkedIn. It holds every outbound action unless you released the channel, and it never touches a credential.

Weekdays, file work only, no browser at all. Reads every ledger, every queue file, and every run record since its cursor, turns the member's ticks into replied lines and closed cards, computes the first response and time to resolution clocks the Friday report is built from, folds the card inbox, re-renders the desk board, and writes the short morning brief the member opens first. It holds every outbound action unless you released the channel, and it never touches a credential.

Runs once by hand on the first day and once a month after that, light browser lane. On the first run it researches the business from its own published surfaces before asking anything, writes the strategy folder, creates the ledgers, seeds the opening cards, builds the single page dashboard, reconciles the schedule table, and registers the eight recurring jobs. On every monthly run it re-reads a month of the kit's own evidence, applies what changed, adds a tab for a channel that gained volume, rebuilds, and reconciles every registered job against the table. It holds every outbound action unless you released the channel, and it never enters a credential.

Weekly on a Wednesday, light browser lane. Turns the questions that keep coming back into the answer that only has to be written once. It reads the ticket ledger over the recurrence window, finds every theme that crossed its threshold, checks the member's own help center and the existing macros for an answer that already covers it, and writes a reusable macro and a help article draft for every theme that has neither. It publishes only where you released the channel an article, never edits a live help center page, sends only where you released the channel, spends only where you released it, and never touches a credential.

Weekdays, conditional browser lane. Reads the ticket ledger and the account, billing, and usage surfaces the member named, and decides which paying customers are about to leave. Every flag is a dossier carrying the trip wires that fired, the exact evidence behind each one, that account's whole history, and one suggested save with its cost and the screen it happens on. It reads billing screens and touches no control on them: a refund, a credit, a plan change, and a cancellation are named and never made.

Weekly, conditional browser lane, read only everywhere. Scores the fleet and the business for the week with a source beside every single number and no number anywhere without one, cites the Employee that owns a metric rather than recomputing it, refuses a rate below the floor, and writes one capped weekly page. It opens a browser only where the metric map names a live screen, never writes into another Employee's folder, sends only where you released the channel, spends only where you released it, and never touches a credential.

Weekly, heavy browser lane, read only toward the world with no exception. Works the surfaces on its own watchlist through one contiguous browser phase, captures one dated observation per real change with a verbatim quote and the exact URL, refuses to report any change against a surface it has no baseline for, and writes one capped weekly page. It types nothing that changes anything, takes no action on LinkedIn ever, sends only where you released the channel, spends only where you released it, and never touches a credential.

Weekdays, file work only, no browser at all. Walks every AI Employee installed on this machine, reads each one's own run log strictly read only, classifies every routine as running, stopped loudly, stopped silently, or paused, ages the faults, folds the decision register, and writes the one short brief the member opens first. It never writes into another Employee's folder, sends only where you released the channel, spends only where you released it, and never touches a credential.

Weekdays, file work only, no browser at all. Takes the single highest ranked open fault on the fleet and turns it into something the member can act on in a minute: the fault in one sentence, the first record that shows it, what changed around that date, three ranked causes each with its evidence line, what the failure has cost, and one paste ready correction line with the exact path it belongs in. It reads other Employees strictly read only, writes nothing outside its own folder, sends only where you released the channel, spends only where you released it, and never touches a credential.

Monthly, on the last weekday, file work only, no browser at all. Folds the decision ledger, scores this Employee's own judgement against the metric files that measured it rather than against its own predictions, appends one outcome line per closed decision, retires a move proposed three times and never accepted, and rewrites the priorities where the evidence disagrees with them. It refuses to publish a calibration figure on too few closed decisions, changes nothing outside its own folder, proposes nothing to anybody, sends only where you released the channel, spends only where you released it, and never touches a credential.

Weekly, file work only, no browser at all. Reads everything the week produced, picks exactly three moves, and argues both sides of each one before the member reads a word of it, with every clause carrying a number or an observation from a file it names. It argues against its own top recommendation last, records a predicted effect and the metric that would show it so the monthly review can score it, and files each move onto the register. It sends only where you released the channel, spends only where you released it, never deploys, and never touches a credential.

Runs once by hand on the first day and once a month after that. On the first run it researches the business from its own public presence, writes the charter with a source and a date beside every conclusion, discovers the AI Employees actually installed on this machine within a bounded search, writes the map every other routine in this kit reads, seeds the priorities and the watchlist once, builds the fleet dashboard, and registers this Employee's own seven jobs. On every monthly run it re-runs discovery and reconciles the map against what is really there. It never writes into another Employee's folder, never registers a job it does not own, sends only where you released the channel, spends only where you released it, and never touches a credential.

Weekdays, file work only, no browser at all. Reads every run record, folds the metrics, change, and creative ledgers, turns yesterday's ticks into facts a machine can count, folds the card inbox, rewrites the board, and writes the short morning brief the member opens first. It holds every outbound action unless you released the channel, and it never touches a credential.

Weekdays. Produces one creative set per run against evidence rather than taste, reading the standing doctrine for the angles currently earning and the metrics ledger for what has decayed. It writes the images and the exact strings into a dated local set folder with the destination screen named, files one card, and uploads nothing to any account. It never opens an account screen, sends only where you released the channel, spends only where you released it, and never touches a credential.

Monthly, on the last weekday. Folds a month of the creative ledger against the daily metrics ledger to score angle, format, hook, and offer framing rather than individual files, tests every line currently in the creative doctrine against what the month actually measured, and rewrites the doctrine where the evidence disagrees with the assumption. It records the fatigue curve it observed, retires what has not earned, and changes nothing where the month holds too few rows to tell one angle from another.

Weekly, on a Friday, read only everywhere. Scores the week from the daily metrics ledger alone, with the screen and the date range beside every number, then writes the ranked paste ready list of what to change in the account next week. Each line names one change, the exact screen, the current value, the proposed value, and the evidence row it came from. It proposes no change it cannot source, it names no action it took because it takes none, and it spends only where you released it.

Weekdays. Works the next ready card on the board, one card per run, and assembles what it needs as a complete local file ready to paste: a campaign build sheet, a negative keyword file, a conversion action specification, an audience definition, or an upload packet. The whole step happens in a text editor until you release the ad account in RELEASES.md, and then Step 6a publishes the approved package through a connection you already have and writes a receipt for every id the platform returns.

Weekdays. The only routine in this kit that opens a screen inside an account that can spend, and everything it does there is read. It confirms the primary conversion event still fired inside the read window before it trusts any other figure, then reads yesterday's spend, delivery, and result rows at account, campaign, ad set, and creative level and appends one row per object per day to the daily metrics ledger with the screen, the date range, and the read date beside every figure. It creates nothing, saves nothing, activates nothing, and spends nothing, unless you released the channel.

Runs once by hand on the first day and once a month after that. On the first run it researches the business from its own public surfaces before asking anything, reads the account structure once, writes the plan folder, seeds the board, creates the creative doctrine, builds the dashboard, and registers the recurring jobs. It asks about exactly two things, the monthly ceiling and the daily cap, because those are the two numbers that decide how much money can leave. On every monthly run it re reads the evidence, corrects what the ledgers prove wrong, and reconciles drift.

Expand all TaskMaster tasks with deep research before coding begins. Reads tasks.json, launches parallel research agents per task in waves using the research-expander agent. Writes findings back to tasks.json. Part of the prd-taskmaster toolkit. Use after PRD is parsed and before implementation. Invoke with /expand-tasks.

Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher worktrees with inbox-based result collection, verified CDD cards, sequential integration merges, and one final PR.

Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default provider, preferred execution mode, and template choice. For deeper tweaks beyond the curated questions, users can hand-edit files in .atlas-ai/customizations/. Use when the user says "customise workflow", "customize workflow", "adjust my PRD settings", "tune the skill", or wants to change how prd-taskmaster behaves.

The Atlas engine — turn any goal into a validated PRD and an executable, verified task graph. Brand-name entrypoint; a thin alias for the `go` orchestrator. Use when the user types /prd:atlas, says "I want to build", or asks for a PRD / task-driven build.

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

Execute Elixir/Phoenix plan tasks with progress tracking. Use after phx-plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.

Watch an Elixir/Phoenix PR with an Amp Orb keep-alive lease until required non-deployment CI is green and review threads are resolved.

Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.

Triage review findings interactively — approve, skip, or prioritize each issue. Use after phx-review to filter findings before fixing.

Use when debugging how a value or request reaches Elixir code, finding who calls a function, or planning a signature change. Builds the call tree with mix xref callers instead of reading files one by one.

Analyze Elixir/Phoenix technical debt — duplicates, refactoring opportunities, credo issues. Use when asked about code quality, cleanup, or what to improve.

Recall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives. Use when asked 'have we done this before' or 'how did I fix X' in Elixir/Phoenix work. ccrider MCP when available, else git + solution docs.

Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.

Recommend safe Bash permissions for Elixir mix commands in settings.json. Use when permission prompts slow workflow, "fix permissions", "reduce prompts", "auto-allow mix".

Use when anything in a Phoenix app is slow, times out, or uses too much memory, even if the cause looks obvious. Load it before analyzing or fixing: it runs measured Ecto, LiveView and OTP checks and ranks fixes.

Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return structured JSON evidence. Also use when the user asks how to install or configure modsearch, or wants to switch engines or add a key.

Make the Tiny Engineer desk robot say something out loud through its speaker while it gestures, via POST /play. Use whenever the user asks the robot to speak, announce or celebrate a result, greet them, or "tell me through the robot", and when debugging /play errors such as 415 "expected 16-bit mono PCM" or 400 "name must be ...".

Verifies a KiCad board production/bom.csv against schematic fields, PCB footprints, and the JLCPCB LCSC catalog, then interprets each FAIL and WARN, marks string-match false positives, and recommends a fix only for real mismatches. Use when checking a board BOM, LCSC part numbers, JLCPCB parts, or whether production/bom.csv matches the schematic and footprints.

Build evidence-bound journal or conference shortlists for Light stage 12. Use after typesetting delivers venue-handoff.json/PDF/compliance facts; when an author asks where to submit, journal selection, conference fit, scope or article-type matching, publication strategy, reach/match/safety tiers, transfer order, APC/OA/indexing/deadline constraints, or predatory/hijacked-journal risk. Produces a current-source candidate registry, fit/risk/unknown reports, and an unchosen decision packet; never recompiles the PDF, invents acceptance rates, condemns a venue from soft signals, chooses without a direct user choice or explicit delegation, or submits.

Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11. Use when receiving a paper-writing manuscript, figure delivery, citation delivery.json/references.bib/citekey-audit.json, or a venue/template profile; when selecting pdfLaTeX/XeLaTeX/LuaLaTeX and BibTeX/Biber; when diagnosing LaTeX errors or unresolved references; when checking page limits, double-blind identity, PDF metadata, template, page box, embedded fonts, TODOs, figures, tables, labels and citations; or when producing a reproducible compile manifest, PDF, compliance report, failure bundle and venue-matching handoff. Distinguishes PASS, manuscript ERROR, toolchain UNAVAILABLE and convergence UNRESOLVED without redoing citation authenticity or figure scientific QA.

Design or modernize a software system from an evidence-backed current-state inventory through quality attributes, architecture options, API and schema contracts, migration/rollback plans, ADRs, and verification. Use for greenfield or existing monoliths, modular monoliths, services, system/API/ database design, schema migration review, data-flow reliability, tenant/PII controls, or architecture evolution. Existing systems stay read-only until the user selects an option and authorizes exact mutations. Unknown facts stay UNKNOWN. This is an off-DAG engineering skill: do not emit findings or invent STAGE_GATES, ROUTES, stages, or back-edges.

Prepare China software copyright registration material drafts from a real software project: application-field worksheet, source-code deposit material, user/operation manual, screenshots when needed, consistency checks and local formal-output evidence. Use for 软著, 软件著作权, 软件版权登记, source-code page extraction, operation manual drafts, version/name consistency, or pre-submit review. This off-DAG engineering/IP handoff skill does not provide legal advice, does not submit applications, does not guarantee registration, and never fabricates source code.

Build auditable peer-review revision and author-response packages for Light stage 13. Use after receiving reviewer comments, a decision or meta-review; when drafting a rebuttal or response letter; when triaging major/minor revisions; when simulating a pre-submission review; or when a rejection may require a user-chosen 13→3 novelty, 13→5 experiment, or 13→8 writing back-edge. Consumes the selected venue/context and real PDF facts, preserves reviewer wording, atomizes issues, binds claims/evidence/actions/provenance, separates PLANNED from DONE, checks current venue limits without borrowing another venue's rules, and emits the stage-13 gate without changing venue, manuscript, evidence, citations, figures, PDF, or passport automatically.

Audit, plan, scaffold, and safely migrate research project structures across greenfield, existing Git/non-Git repositories, and monorepo subroots. Use for project folders, repository cleanup, source inventory, move maps, naming and storage policy, Python/R/mixed/LaTeX profiles, template provenance, conflict review, applied-move evidence, or rollback. Existing projects are read-only until the user authorizes exact action IDs bound to a plan digest. Preserve uncommitted and untracked work, symlinks, submodules, and memory-pm's .light content. This is an off-DAG local tool: do not emit findings or invent a STAGE_GATES/ROUTES connection.

Prepare evidence-backed patent invention disclosure materials for attorney or patent-agent review. Use when the user asks for 专利点挖掘, 技术交底书, 现有技术/查新记录, claim/patent-point support mapping, invention disclosure drafts, patent figures, or a handoff package for a software/research/project invention. This is an off-DAG engineering/IP handoff skill: it does not provide legal advice, does not submit filings, does not guarantee novelty, grant, allowance, validity or registration, and emits no Light research findings or back-edges.

Coordinate and recover multi-stage Light research projects through the canonical .light/passport.yaml state, stages 1-13, resident overlays, checkpoints, findings, parallel joins, stale propagation, handoffs and user-authorized reroutes. Use for a new/resumed/partial/dirty/failed/stale/delivered research project; when the user says continue, resume, take over, checkpoint, reroute, recover or deliver; or when work crosses two or more Light research stages. Never turn frontend-design/system-design/patent-disclosure/software-copyright or overlays into stages, never execute a suggested back-edge without explicit user authorization, and never declare delivery from file existence alone.

Light 科研主线第 4 步·审 idea：以**顶会审稿人标准严审** idea，**撞车/无创新 fatal flaw 一票否决**(critical 门)， 逼出真能发表的 idea。何时用：用户问"这 idea 行不行/够不够新/能不能发""帮我严审/挑刺/找致命问题" / idea 定稿前把关 / 收到 idea-generation 的候选要审 / 怀疑撞车(被人做过)。触发词：审 idea / 评审 / 严审 / 挑刺 / 这 idea 行不行 / 够不够新 / 创新性 / 撞车 / 被做过了吗 / 致命问题 / 能投顶会吗 / 拒稿风险 / critique my idea / review this idea / is this novel / fatal flaw / 一票否决。核心纪律：**撞车/无创新的 critical 一票否决在本技能**(不被其他高维度平均救回)； **硬性反谄媚**(不被作者反复反驳顺从放行弱 idea)；撞车判定**target/background 可追溯分解**非"感觉像"；judge 不靠裸 自评(用可计算否决闸门 + 密度先验 + pairwise)。**消费上游 idea-generation 的撞车 findings + facet 槽位**。

Light 科研主线 stage 6：把冻结的 question/estimand、experiment matrix、pre-registration 与 data lineage 落成最小可运行、测试先行、无泄漏、可复现且能交给 result-analysis 的实验代码。用于实现或复现训练/预处理/评测， 设计 gold/property/metamorphic 测试，控制 Python/NumPy/框架/CUDA/DataLoader 随机性，审查 train/test 或 CV fit 穿越，记录 config/code/environment/input hashes、stdout/stderr、raw metrics、patient/entity predictions 与 failure artifacts，以及运行 stage-6 checkpoint。数据泄漏或不可复现是 critical；静态扫描和同 seed 两次一致都不证明跨硬件 绝对复现。

维护 easyeda-agent 仓库的 Skill、CLI、daemon、connector 与文档，补回可复用经验并组织验证和 Git 贡献。 Develop and contribute to the linked automation repository; use easyeda-agent for circuit design operations.

只读查询 easyeda-agent 仓库的工具能力、实现、参数化样例与验证证据，适合在其他项目中复用 EDA 自动化经验。 Search the linked easyeda-agent checkout for capabilities, implementation, examples, and evidence; does not operate an EDA document.

Designs system architecture with C4 diagrams and technology selection. Routes to the right architect based on design scope (system, domain, application, or full stack). Two interaction modes: guide (collaborative Q&A) or propose (architect presents options with trade-offs).