Results for “fix”

When tackling a task that requires domain expertise beyond general coding ability — architecture patterns, framework-specific gotchas, deployment strategies, security anti-patterns, or specialized workflows — call the windags_skill_graft MCP tool with your task description. You'll receive expert knowledge including decision trees, failure modes, worked examples, and anti-patterns from a library of 503+ curated skills. Only graft when the task genuinely requires specialized knowledge. Simple tasks (rename a variable, fix a typo, format code) do not need grafting.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

This skill should be used when the user wants to "dca into" a token, "buy X every day", set up a "recurring buy", "dollar cost average" into an asset, "schedule a buy", or "auto-buy on a dip". Buys a fixed amount into a token on a schedule, optionally only when a condition holds (for example only when ETH is below a price threshold). The host agent's scheduler wakes the skill on a cadence; each wake is one self-contained run.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Select alternative execution paths when a plan step fails — branch on outcomes instead of blind retry. Load when a structured plan step fails, an unexpected observation arrives, or the user asks what to try next after an error. Also triggers on "try another approach", "route around this failure", "replan on failure", "if X fails try Y", or outcome-based branching during multi-step work. Pairs with structured-planning and debug-and-fix. Does not replace root-cause debugging — adds plan-level path selection.

Reviews a pull request: runs its own baseline review of the PR diff, then a persistent Monitor watches CI and incoming reviewer comments, triages each comment through an independent skeptical agent, applies only verified fixes, and commits+pushes via inline git commands until CI passes and no comments remain to adopt — then asks whether to merge. Use this skill when the user asks to "review a PR", "monitor PR review comments", "address reviewer feedback on #123", or "watch CI on a pull request".

Build a compact, validation-gated implementation plan for multi-step, risky, or ambiguous work — typically when phases need explicit checkpoints, the change touches multiple files/services, or the user wants alignment before execution. Output goes to `.claude/plans/<topic>.md` (or `.agents/plans/`) with goal, in/out-of-scope, phased steps, validation per phase, and replanning triggers. Skip for trivial single-file fixes, bug investigations (use `tracer`), or open-ended exploration (use `explore`). Pair with `ship` once the plan ends and merge work begins.

Establish CSS/Tailwind baseline quality — font smoothing, line-height defaults, box-sizing, focus rings, color contrast, Tailwind anti-patterns, and CSS containment. Use when asked to "set up CSS baseline", "Tailwind best practices", "fix font rendering", "global CSS foundation", "typography defaults", "CSS anti-patterns", "improve CSS quality", "line-height reset", "normalize styles", or reviewing a new project's base styles for correctness. Do NOT use for: full design system token architecture — see design-system-gen. Do NOT use for: component-level animation — see motion-design.

Manages automated dynamic/trailing stop losses (DSL only) for leveraged perpetual positions on Hyperliquid. Default mode: High Water (pct_of_high_water) — the trailing floor is a percentage of the peak ROE, recalculated every tick, no ceiling. Also supports fixed ROE tiers for legacy positions. Monitors price via cron, ratchets profit floors through configurable tiers, syncs the stop loss to Hyperliquid via edit_position, and auto-closes positions on breach via mcporter. Supports LONG and SHORT, strategy-scoped state isolation, and automatic cleanup.

Interactive project setup wizard. From a clean codebase, guides user through provider selection (OpenAI/Azure/DeepSeek/Ollama/Qwen/Gemini/etc.), API key configuration, dependency installation, config generation, and launches the dashboard. If user selects an unimplemented provider, auto-scaffolds the provider code following the plugin architecture. Auto-diagnoses and fixes startup failures with up to 3 retry rounds. Use when user says 'setup', 'set up', 'configure', 'init project', '初始化', '环境配置', '项目配置', 'first run', 'get started', 'quick start', or wants to configure and launch the project from scratch.

Interactive project setup wizard. From a clean codebase, guides user through provider selection (OpenAI/Azure/DeepSeek/Ollama/Qwen/Gemini/etc.), API key configuration, dependency installation, config generation, and launches the dashboard. If user selects an unimplemented provider, auto-scaffolds the provider code following the plugin architecture. Auto-diagnoses and fixes startup failures with up to 3 retry rounds. Use when user says 'setup', 'set up', 'configure', 'init project', '初始化', '环境配置', '项目配置', 'first run', 'get started', 'quick start', or wants to configure and launch the project from scratch.

Interactive project setup wizard. From a clean codebase, guides user through provider selection (OpenAI/Azure/DeepSeek/Ollama/Qwen/Gemini/etc.), API key configuration, dependency installation, config generation, and launches the dashboard. If user selects an unimplemented provider, auto-scaffolds the provider code following the plugin architecture. Auto-diagnoses and fixes startup failures with up to 3 retry rounds. Use when user says 'setup', 'set up', 'configure', 'init project', '初始化', '环境配置', '项目配置', 'first run', 'get started', 'quick start', or wants to configure and launch the project from scratch.

Diagnose and fix retention problems using behavior design (B=MAP). Use when the user mentions "users drop off", "activation rate", "onboarding friction", "retention metrics", "why users dont complete", "churn analysis", "user activation", or "aha moment". Also trigger when analyzing cohort retention curves, designing activation milestones, reducing time-to-value for new users, or investigating why users stop after their first session. Covers the Ability Chain, prompt design, and tiny behaviors that compound. For habit loops and variable rewards, see hooked-ux. For intrinsic motivation, see drive-motivation.

Remove signs of AI-generated writing from academic medical papers. Use when editing or reviewing manuscripts to make them sound more natural and professionally written. Based on Wikipedia's "Signs of AI writing" guide, adapted for medical literature. Detects and fixes patterns including: inflated significance claims, superficial -ing analyses, vague attributions, AI vocabulary words, copula avoidance, excessive hedging, generic conclusions, informal word choices (linked/beyond/via/where/yield), overly assertive causal claims, and artificially condensed expressions. Preserves legitimate academic transitions (Notably, Prior studies have shown, etc.).

Inspects a skill's SKILL.md and its observations/runs.md log, identifies failure patterns, and proposes a targeted amendment to improve the skill. Trigger on: "improve this skill", "fix this skill", "update this skill", "why does X keep failing", "this skill is wrong", "add this to the skill", or automatically when observations/<skill-name>/runs.md contains 3 or more failure entries. Outputs the amendment as a diff the user can review before applying. Records the amendment rationale in observations/<skill-name>/runs.md after user confirmation.

Builds a new Claude Code skill from scratch through a relentless, evidence-based interview that walks the skill's design tree decision-by-decision — entity fit, use cases, name, description, workflow steps, tools, and progressive-disclosure layout — then reviews the finished skill against the plugin-building guidance and applies every fix it finds. Use when creating, authoring, scaffolding, designing, or drafting a new skill or slash command. Does not build an agent or subagent — use agent-builder. Does not serve, vendor, or refresh the authoring guidance itself — use guidance.

Run a Codex prompt on a cron schedule or at a specific future time. Codex app Automations is the official, always-on surface for durable recurring schedules — recommend it FIRST; this local skill is a terminal fallback that only fires while its daemon runs. Triggers include "/schedule", "cron", "every Monday 9am", "run this at 3pm", "schedule a codex prompt", "recurring codex task", and one-time future runs ("run once at 3pm", "remind me to check X tomorrow"). For fixed-interval repeats ("every N minutes"), use the separate `loop` skill instead.

Repair and verify cross-references between SKILL.md files after a skill is created, renamed, removed, or restructured. Ensures every skill that calls another skill references the correct name, and every skill that is called has accurate "Called by" context. Load after universal-skill-creator creates a skill, after improve-skills completes a cycle, after a skill is renamed or removed, or when the user asks to fix cross-references, sync skill links, repair broken skill references, update skill cross-links, check skill references, or "are cross-links correct".

Trata o saneamento e a organizacao do processo (CPC 357): resolucao das questoes processuais pendentes, fixacao dos pontos controvertidos, delimitacao das questoes de direito relevantes, distribuicao do onus da prova (357 II c/c 373 §1 — distribuicao dinamica) e definicao das provas a produzir e da audiencia de instrucao. Cobre o saneamento compartilhado (357 §3) e o pedido de esclarecimento/ajuste em 5 dias (357 §1). Use quando o operador disser saneamento, decisao de saneamento, pontos controvertidos, organizacao do processo, distribuicao do onus da prova, ou houver despacho saneador a impugnar/cumprir.

Score the experience a new customer actually has, not just whether they activated. Grades the first 90 days on the moments that make someone feel taken care of, finds where the welcome goes cold, and hands back a scored audit with the specific fixes. Built for any post-sale team, customizable to your product and lifecycle. Trigger on "audit my onboarding", "score our onboarding experience", "why do new customers churn early", "grade our first 90 days", "where does onboarding go cold", "is our welcome any good", or any onboarding-quality question.

Build lean, opinionated products using the 37signals philosophy from Getting Real, Rework, and Shape Up. Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat marker sketch", "build less", "underdo the competition", or "opinionated software". Also trigger when cutting scope to ship faster, running small teams, avoiding long-term roadmaps, or eliminating meetings. Covers shaping, betting, building, and the art of saying no. For MVP validation, see lean-startup. For design sprints, see design-sprint.

Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction precision), its 3 fixed sizes, edit-with-preservation language, and when to route to a sibling (Flux 2 / Nano Banana Pro / Seedream) instead. Calls `runcomfy run openai/gpt-image-2/text-to-image` or `/edit` through the local RunComfy CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2", "image 2", or any explicit ask to generate or edit with this model.

Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction precision), its 3 fixed sizes, edit-with-preservation language, and when to route to a sibling (Flux 2 / Nano Banana Pro / Seedream) instead. Calls `runcomfy run openai/gpt-image-2/text-to-image` or `/edit` through the local RunComfy CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2", "image 2", or any explicit ask to generate or edit with this model.

Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction precision), its 3 fixed sizes, edit-with-preservation language, and when to route to a sibling (Flux 2 / Nano Banana Pro / Seedream) instead. Calls `runcomfy run openai/gpt-image-2/text-to-image` or `/edit` through the local RunComfy CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2", "image 2", or any explicit ask to generate or edit with this model.

Builds a new Claude Code agent (subagent) from scratch through a relentless, evidence-based interview that walks the agent's design tree decision-by-decision — entity fit, domain focus and vocabulary, role identity, anti-patterns, description, model tier, tools, and self-containment — then reviews the finished agent against the plugin-building guidance and applies every fix it finds. Use when creating, authoring, scaffolding, designing, or drafting a new agent or subagent. Does not build a skill or slash command — use skill-builder. Does not serve, vendor, or refresh the authoring guidance itself — use guidance.

Submit one or more wandb-logged training/finetuning runs to the HPC scheduler. `WANDB_PROJECT` is fixed per repo (snake_case basename); `WANDB_RUN_GROUP` is picked per invocation. The training script must take the experiment/group name as a config key (e.g. Hydra `meta.experiment_name=<group>`); the skill passes it on the command line. The working tree is committed first so each run pins to a real SHA. Delegates SLURM/PBS templating to `cluster-instructions`. Use when the user asks to submit, queue, launch, or kick off a wandb training/finetuning job.

Dispatch coding work across the intelli-verse-x gastown swarm — pick the right rig (gastown, hermes-agent, content-factory, intelli-verse-kube-infra, intelliverse-x-games-platform-2, the SDKs, nakama, leantime, etc.), spawn or assign to a polecat with the right role (coder, reviewer, tester), monitor the convoy through to merge via the refinery. Use whenever the user says "have an agent fix X", "swarm on Y", "open PR for Z across all the SDK forks", "assign this work", or anything else that turns a beads task into a running async agent.

Audits any draft against Built GTM voice rules and returns specific, line-level violations with rewrites. Not a general style critique. A rule-based QA check. Every violation gets a specific fix. Trigger on "check this", "does this sound like me", "voice check", "is this on brand", "review this draft", "what's wrong with this", "flag the AI tells in this", "make sure this sounds like me", or any request to audit a draft against Heath's Built GTM voice before publishing. Can be used on posts, articles, newsletter editions, comments, or any Built GTM content.

Automatically maintain skill library consistency whenever a structural change occurs — new skill added, skill renamed, skill deprecated, call graph rewired, or category changed. Updates SKILL-INDEX.md, AGENTS.md, README.md, skill graph, docs/prd/PRD.md, and docs/architecture.md. Load when universal-skill-creator finishes creating a skill, split-skill extracts a child, deprecate-skill retires a skill, improve-skills makes a structural change, or the user manually renames or restructures skills. Also triggers on "update the skill index", "sync skill references", "refresh the skill graph", "fix broken skill cross-references", or "update docs after skill change".

Step-by-step setup and troubleshooting for connecting an owner's Google Calendar to an OpenClaw agent with read and write access. Use when: setting up calendar access for the first time, fixing read-only access, re-authenticating a broken Google connection, explaining the difference between the owner's Google account and the agent's Google account, how an OpenClaw agent accesses Gmail or Google Workspace, where credentials are stored, how to use the agent inbox, how to give the agent write access to the owner's calendar, or guiding another agent or user through the email or calendar setup model.

Audits and repairs Markdown link health across a skills repo via a four-tier pipeline (config hardening, intra-repo file-ref fixes, external URL substitutions, residual exclusions) and enforces a Tier 3 substitution guardrail that prevents regressions of previously-passing links; designed for lychee-based GitHub Actions link checkers but generalizes to markdown-link-check and similar tools. Use when the request mentions link audit, dead links, link health, lychee, broken links, link checker, markdown link audit, link-health audit, 404 audit, check-links failing, CI link-check, or 連結健檢, 死鏈, 失效連結, 斷鏈檢查. Part of the AlterLab Academic Skills suite.

Operate Playwright for browser automation end to end: author and debug E2E test suites (robust locators, network interception and mocking, parallel workers, accessibility snapshot checks), wire them into CI, and drive headless browsing and scraping with an extract -> validate -> save loop. Use when writing, running, fixing, or scraping with Playwright, when a Playwright CI failure or JSON report needs triage, or when the bundled pwrun script should analyze a run. Do not use for QA strategy or test framework selection (route to qa-methodology), for frontend component or architecture design (route to frontend-engineering), or for Cloudflare/DDoS-GUARD challenge bypass (use flaresolverr).

APSA style checker for Quarto (.qmd) files. Checks numbers, capitalization, abbreviations, italics, in-text citations, titles of works, neutral and unbiased language, and APSA-specific terminology against the APSA Style Manual for Political Science (2018, updated 2023). Produces a structured markdown report organized by document section — never modifies the source file. Use when asked to check APSA style, fix citations, review capitalization, check number formatting, or flag biased language in a .qmd document. For grammar, spelling, and punctuation, use the proofread skill instead. Supports an optional output-file argument and an optional @sec-label argument to restrict checking to one section.

Firm-fixed-price cost buildup mirroring 1102 IGCE FFP wrap-rate math (BLS OEWS + GSA CALC+ + GSA Per Diem). USE WHEN the user asks to "build an FFP IGCE", "wrap rate buildup", "FFP cost estimate", "layer fringe overhead G&A fee", "how should we price this FFP task order", or "IGCE parity for our bid". Pulls labor categories from pursuit vault or defaults, stacks fringe/overhead/G&A/fee, exports JSON + XLSX to Studio. DO NOT USE FOR T&M/LH pricing (`igce-builder-lh-tm`), cost-reimbursement (`igce-builder-cr`), OT milestones (`ot-prototype-strategist`), or obligation intel (`competitive-intel`).

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.

Orchestrate the complete post-first-draft polishing pipeline for an academic LaTeX paper by invoking five existing skills in fixed order: (1) paper-polish, (2) paper-self-revise, (3) paper-style, (4) paper-polish again, (5) reference-verify. Trigger when user says "paper pipeline" / "paper-pipeline" / "论文流水线" / "全流程打磨" / "一条龙打磨" / "初稿打磨" / "full polish pipeline" / "run the whole pipeline", or wants the entire post-draft polishing sequence run on a paper folder. Use this skill whenever the user asks for several paper-finishing steps (polish + revise + style + reference check) on one manuscript in one go, even if they don't name every individual skill.