Coding & Refactoring Agent Skill

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Turn a validated bounded diff into one intentional local commit with explicit scope review, named verification carry-forward, and a visible stop line before push or publish. Use when a bounded code, config, or docs diff is already prepared locally and the next honest move is one local commit boundary rather than more coding. Do not use when the task still needs more repair or verification, when no bounded diff exists, or when the main task is push, PR, release, or public-share.

An implicit match may suggest this skill, but must not load or execute it until explicit invocation or a source-authorized parent-route selection. Bridge session evidence into memory writeback decisions without turning raw session history into reviewed memory. Use when a live session, closeout, PR, commit, or review reveals a memory-worthy decision, failure, route change, owner-boundary event, service contract, eval posture, or consumer handoff and the agent needs to decide whether to write a local memo candidate, prepare a reviewed-intake export, or record an explicit no-writeback stop line. Do not use for raw session capture, reviewed memory landing itself, proof verdicts, eval scoring, or generic summaries with no owner route.

Separate reusable core logic from glue, orchestration, and infrastructure detail. Use when stable rules are mixed with wiring, the same logic repeats in several places, or reviews are muddy because the responsibility center is unclear. Do not use for tiny isolated fixes or when the real task is introducing a port or adapter around a concrete dependency.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Mine .aoa session evidence for missed eval triggers, candidate regression cases, and local eval pressure only after web research and repo owner surfaces are checked, returning raw and segment refs with freshness rather than proof. Use when the user asks to study sessions for eval moments, missed triggers, repeated failures, or session-derived eval cases. When the parent has classified session mining but the trigger classes, target owner map, session provider/status, or freshness evidence is unavailable inside the active evidence boundary, stop with blocked_missing_input; do not relabel missing input as deferred_owner_boundary or invent refs. Do not use for raw .aoa preservation, hook repair, search-index maintenance, memo writeback, decision records, or treating session history as reviewed proof.

Refactor code toward clearer ports and adapters so domain or application logic is less entangled with infrastructure details. Use when concrete dependencies leak into core logic, tests are hard because external concerns bleed inward, or a module needs a clearer seam before further change. Do not use for tiny local fixes or when there is no meaningful boundary to clarify.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Turn reviewed session evidence into explicit next-route forks with likely gains, costs, risks, owner targets, and stop conditions so continuation stays legible instead of buried in chat memory. Use when a reviewed session ended with several plausible next moves and you need visible branch choices rather than a hidden recommendation. Do not use when there is only one obvious next move, when donor harvest still has not happened, or when the real question is final promotion of one repeated quest unit.

Implement a bounded feature slice through test-first discipline, minimal implementation, and explicit refactor boundaries. Use when a behavior change can be specified in tests before code and confidence or regression resistance matters. Do not use for undefined exploratory work, one-off glue, or broader architectural restructuring.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Record explicit operator approval for Forge mutation or Delta judgment gates without treating approval records as owner truth. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Maintain the app-server bridge approval queue while preserving Forge and Delta gates, receipts, and visible operator intent. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Operate the Titan app-server bridge as inspectable thread, turn, event, approval, replay, and metrics state without hidden execution. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Generate an inspectable Titan app-server launch plan as JSONL or equivalent plan output without executing the local coding agent. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Close a Titan service-cohort session with role, risk, provenance, gate, verification, and next-owner summary. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Open or maintain a visible Titan operator-console state while keeping Forge and Delta locked until approvals exist. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Replay Titan bridge or console events into inspectable state without granting runtime authority to the replay result. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Initialize or update Titan Memory Loom records as candidate memory with source refs, confidence, and authority warnings. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Propose redaction, tombstone, or pruning candidates for Titan memory without silent deletion or canon rewrite. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Use when the user wants a thorough PR or branch review. Triages by diff size — small PRs get a single-pass review, large PRs fan out to parallel sub-agents (correctness, architecture, security, scope, and an Agentic & Evals lens that activates on AI/agent code) with a validation phase that drops false positives.

Construct deep-link URLs for the AWS CloudWatch console — Logs Insights queries, Alarm detail pages, Metrics graphs. Use when encoding log groups, time ranges, query strings, metric dimensions, or opening CloudWatch views in a Playwright browser session. Keywords: CloudWatch deep-link Logs-Insights alarm metrics fragment-encoding *XX-encoding epoch timestamp hash-routing url-construction SPA alarm-detail metric-graph log-group query-string cloudwatch-console.

Complete Biome toolchain guidance for real repository workflows. Use when users ask to configure biome.json, run lint or format commands, migrate from ESLint or Prettier, tune rule severity, fix formatter drift, or replace mixed ESLint+Prettier pipelines with Biome-only workflows.

Given a user-provided set of coding standards (either as direct text input or as a link to a file/URL), systematically review the codebase to identify violations, report findings, and optionally remediate them. The model MUST ask the user for the standards — never guess or assume them.

Creates structured context files (plans, justifications, scratches) in the .context/ directory with unique three-word IDs and frontmatter metadata. Use when starting a new task and needing to document a plan or task breakdown, when recording decision rationale or architectural choices as a justification, when saving temporary notes or exploratory thinking as a scratch, or when the user asks to "create a plan", "document my thinking", "save context", "track decisions", or "keep notes" in a structured project context directory.

Comprehensive toolkit for validating, linting, and testing GitHub Actions workflow files, custom local actions, and public actions. Use this skill when working with GitHub Actions YAML files (.github/workflows/*.yml), validating workflow syntax, testing workflow execution with act, or debugging workflow issues.

用一面交易哲學鏡片(預設「存活紀律派」,可換),把你的真實交易復盤成一張卡——一個最大的洞 + 一條下次要守的規矩 + 一句鏡片原則。先用機械算抓出最大的行為漏洞(假分散 / 梭哈 / 攤平 / 賣太早 / 把beta當alpha),再用鏡片的思路問出每筆交易背後的「動機」(焦慮還是判斷、看好還是不想認賠)。用戶說 /fomo-kernel、復盤我的交易、看我的交易紀錄、幫我 review 這份對帳單、trade review 時使用。不用於個股研究、選股建議、大盤預測或財經新聞問答——那些不是復盤,不要觸發。資料全程留在用戶本機,不外傳。

Master higher-order functions, map/filter/reduce patterns for expressive data transformations