jajupmochi
- 46 skills
- 0 followers
- 8 hours ago last updated
- ▌
- ▌ Code Verifier 2 · jajupmochiUse BEFORE claiming any code/test/script runs successfully. Detects FAKE-RUN patterns (hardcoded results, assert True, mocks-only tests, swallowed exceptions, fabricated numbers, dead-code short-circuits). Apply automatically whenever about to claim "test passes", "code works", "results show X", "training converges", or commit/push. Complements superpowers:verification-before-completion (which enforces real-run discipline) by auditing whether the run itself is genuine.
- ▌ Verify Visual 2 · jajupmochiUse chrome-devtools MCP to screenshot a target URL/element and visually verify it matches a reference. Auto-fires when the user requests a UI change with a visual reference (paired with the ui-iteration-loop rule).
- ▌ Privacy Redact 2 · jajupmochiScan a markdown / text file for usernames, absolute paths, secrets, and project codenames; replace with placeholders. Use before promoting any private/draft file into a public commit or recommendation.
- ▌ System Cleanup 2 · jajupmochi bundleUse when a Linux disk is filling up or the user asks to free space / clean the system / "系统盘满了" / move large files off the system disk. Diagnose where the space went (df / du / dpkg / snap / docker), then give a prioritized, risk-tagged plan — do safe user-level deletions, and LIST the sudo items for the user to run (default to advise-then-confirm; this kind of box often has no passwordless sudo, so use pkexec or hand over the commands). Covers the biggest reclaimables — `~/.cache/uv` (Python package cache, 58 GB seen), `~/.cache/huggingface` (model/dataset cache, 24 GB seen), Docker build cache, VS Code WebStorage PDF-cache bloat, JetBrains indexes — plus old-kernel pile-up, snap/journal/apt caches, and NTFS data-disk write failures.
- ▌ Research Critic 2 · jajupmochiUse AT EVERY RESEARCH STEP (hypothesis design, experiment setup, result interpretation, conclusion writing) to challenge soundness BEFORE committing the step. Catches confirmation bias, p-hacking, leakage, weak baselines, ungrounded claims, ad-hoc thresholds, survivorship bias. Apply automatically whenever about to write a paper claim, design an ablation, interpret a number, or update a results doc. Pairs with code-verifier (which audits artifact authenticity).
- ▌ Verify Template 2 · jajupmochiRun the project's CI gates locally before claiming work is done. Customize the body to match the project's actual lint/test commands. Use before opening a PR or marking a phase complete.
- ▌ Preview Template 2 · jajupmochiStart the local dev server / preview environment for this project. Customize per project type. Use when iterating on UI or before visual verification.
- ▌ Long Running Tasks 2 · jajupmochiDecision tree for handling long-running operations in Claude Code — when to use background subagents, Monitor tool, explicit timeouts, or refactor the task. Auto-fires when a task duration estimate exceeds typical bounds.
- ▌ Autoresearch Toolfinder 2 · jajupmochi bundleFind the right autonomous-research / autoresearch tool, framework, port, or skill for a research or engineering task. Searches a local cached index of two curated awesome-autoresearch lists (alvinreal + yibie, 550+ entries) and returns only the few matching tools, never loading the whole catalog into context. Use when the user wants to pick, compare, or set up an autoresearch loop, an AI-scientist / research-agent system, a domain or hardware port (Apple Silicon, RTX, RL, trading, materials, bio, vision, kernels...), or an evaluation harness, or asks "is there an autoresearch tool for X".
- ▌ Verify Visual 3 · jajupmochiUse chrome-devtools MCP to screenshot the local site (or a specific element) and visually verify it matches the design intent. Required after every UI-affecting change before marking work done.
- ▌ Agent Harness General · jajupmochiAudit the source agent-harness general skill catalog. Use only when maintaining or adapting this repository's original reusable skill set.
- ▌ Autopilot · jajupmochiSet up or manage the autopilot daily autonomous project-driver. Configures a daily timer that runs a fresh autorun session to advance a project (features, bug fixes, refactors, design, docs). Use when the user wants to "set up autopilot", schedule autonomous daily work, or configure/inspect the autopilot tool.
- ▌ Doc Writing · jajupmochi bundleUse when writing or updating any document a human will read — a design or architecture spec, a feature manual and its in-app guide, an audit / bugfix / test report, a README, release notes, a plan, or a session handoff. Encodes the document requirements mined from two real project sessions (define every term in place, prove every claim and say how a tester re-proves it, full clickable links, mermaid diagrams, nothing stale, remaining tasks highlighted, no secrets) and ships `scripts/doccheck.py` to lint the finished file against the ones a machine can check.
- ▌ Code Verifier · jajupmochiAudit whether code, tests, scripts, or reported results are genuine before claiming success. Use before saying tests pass, code works, a script ran, training converged, or results show a conclusion.
- ▌ Tui Installer · jajupmochi bundleUse to install (or just plan) the recommended terminal/TUI stack for driving multiple AI coding agents on Ubuntu — zellij + claude-squad + lazygit + delta. Dry-run by default (prints the plan, installs nothing); --apply asks y/N per tool. When onboarding agent-harness, offer to run --check and ask before installing anything.
- ▌ Verify Visual · jajupmochiVisual verification for UI changes using Playwright screenshots and native model vision (GPT-5.5, Claude). For models without vision (DeepSeek), uses Playwright screenshot capture with pixel comparison for regression detection. BackstopJS available as optional regression tool.
- ▌ Privacy Redact · jajupmochiScan and redact private details before publishing or committing text. Use for usernames, absolute paths, secrets, project codenames, private URLs, and local machine details.
- ▌ Prompt Library · jajupmochi bundleUse to save and reuse good prompts across projects and agents, and to MINE past prompts out of local Claude Code / Codex / Copilot / opencode history. Many prompts recur (a detailed feature spec, a "design the whole thing" brief, a manual/onboarding prompt) and are worth reusing verbatim or as a reference. This curates them as browsable, greppable Markdown — each with the original, an optimized rewrite, and when to use / when NOT to use it — behind a PRIVACY GATE that refuses to store anything still containing paths/emails/tokens/usernames/codenames, so the library stays publishable.
- ▌ System Cleanup · jajupmochiDiagnose and plan Linux disk cleanup from Codex using the source agent-harness system-cleanup skill. Use when disk space is low, the user asks to free space, or a data disk or mount is read-only. Advises first and requires confirmation before destructive or sudo cleanup.
- ▌ Publish · jajupmochiTag a new version of agent-harness, push to GitHub, and create a GitHub release. Use when shipping a meaningful update (new rules, new templates, etc.). Asks for SemVer bump and writes release notes from git log.
- ▌ Memory Flywheel · jajupmochi bundleUse to persist and recall per-project cross-session working memory so long or multi-project sessions don't lose detail to context compaction. Record each round of progress (verbatim I/O + reasoning + metadata) into a project memory dir, read a coarse INDEX first, then open only what keyword recall points at. Deterministic, grep-native, LLM-as-component.
- ▌ Research Critic · jajupmochiCritique research hypotheses, experiment design, results, ablations, baselines, and paper claims before committing them.
- ▌ Verify Template · jajupmochiRun project verification from Codex before claiming work is done. Use before marking a phase complete, opening a PR, or saying tests/lint/build pass.
- ▌ New Hook · jajupmochiScaffold a new hook under hooks/<kebab-name>/. Creates README.md (what/when/install/variants) and settings.snippet.json (drop-in JSON), plus updates INVENTORY.md and hooks/README.md in the same edit batch. Hooks are sensitive — pipe-test the raw command before wrapping.
- ▌ New Rule · jajupmochiScaffold a new workflow rule under rules/<kebab-name>/. Creates RULE.md (frontmatter + body template) and snippet.md (drop-in for downstream CLAUDE.md), plus updates INVENTORY.md and INVENTORY.zh.md in the same edit batch.
- ▌ Init Agent Config · jajupmochiScaffold a new project with the relevant subset of agent-harness rules, hooks, skills, recommendations, and templates. Asks about project type, language preferences, and context tags, then composes a project-specific CLAUDE.md, .claude/settings.json, and starter files. Use in a fresh or existing project to apply agent-harness conventions.
- ▌ Preview Template · jajupmochiStart or identify the local preview environment from Codex. Use for UI, docs, static site, Vite, Next.js, Storybook, MkDocs, or visual verification workflows.
- ▌ New Skill · jajupmochiScaffold a new skill under skills/<bucket>/<kebab-name>/. Creates SKILL.md with proper frontmatter, plus updates INVENTORY.md and skills/README.md in the same edit batch.
- ▌ Init Codex Config · jajupmochiScaffold or migrate a project to use agent-harness from Codex. Use when applying agent-harness in Codex, converting Claude Code setup to AGENTS.md/.codex/.agents, or making a project ready for Codex skills and hooks without changing the original Claude setup.
- ▌ Task Orchestrator · jajupmochiMeta-skill that enforces a structured Research-Design-Plan-Execute-Verify pipeline for every atomic task. Compensates for model/agent weaknesses (especially DeepSeek, non-native models) by adapting plan template strictness based on detected capabilities. Self-improving: records better approaches back into templates.
- ▌ End Of Turn Marker · jajupmochiEvery turn MUST end with a visible divider header followed by numbered summary items. Use [END:FINAL], [END:WAIT], or [END:NEEDS_USER] embedded in the divider.
- ▌ Figma Design Fetch · jajupmochi bundleUse when the user shares a figma.com URL, wants to implement/mock a UI from Figma, or do design-to-code — connect the Figma MCP, fetch the design (code/assets/screenshot) to disk, then rebuild with existing design-system components and visually self-verify against the Figma screenshot.
- ▌ Long Running Tasks · jajupmochiManage long-running commands and multi-step work in Codex. Use when a task may exceed normal turn time, needs a dev server, watcher, training run, crawl, benchmark, or repeated polling.
- ▌ Agent Config Adapter · jajupmochiAdapt an existing agent configuration or plugin to a new agent or model route. Use when moving agent-harness or another agent setup between Claude Code, Codex, Gemini, Cursor, local models, or non-native model backends such as DeepSeek routed through another agent.
- ▌ Agent Update Watcher · jajupmochi bundleUse to keep up with the fast-moving agent ecosystem (new/updated CLIs, plugins, skills) WITHOUT burning tokens on constant checks. Declares the sources to watch in a config, checks them only when a minimum interval has elapsed, and reports ONLY what actually changed vs the recorded version — you then decide whether to adopt.
- ▌ Autoresearch Toolfinder · jajupmochiFind the right autonomous-research or research-agent tool from Codex using the source agent-harness autoresearch-toolfinder skill. Use when choosing, comparing, or setting up autoresearch tools, AI-scientist systems, research-agent loops, platform ports, or evaluation harnesses.
- ▌ Claude Desktop Sessions · jajupmochi bundleUse when Claude Code sessions started in the terminal CLI don't appear in the Claude Desktop app's Code tab, when you want to hand a running CLI session to Desktop (and reach it from the phone via Remote Control), or when asked to "import/migrate my CLI sessions into the desktop app". Registers existing sessions in Desktop's sidebar by writing its per-session registry files, which point at the transcript store both apps already share — no transcript is copied or modified. Lists candidates numbered so you can import a chosen subset.
- ▌ Task Relationship Analysis · jajupmochi bundleUse BEFORE executing any multi-step or multi-feature request (3+ tasks). Forces a pre-execution pass that maps how the tasks relate — synergies, conflicts, shared substrate, ordering — so you don't mechanically execute them in listed order and miss that several should be built on one shared piece, or that two conflict. Scaffolds a pairwise matrix + synthesis checklist.
- ▌ Figma Authoring Constraints · jajupmochiUse when a designer asks how to structure a Figma file so it produces clean code, when a design keeps yielding pixel-snapshot output, or when get_variable_defs comes back empty — the 20 Figma-side authoring constraints that make a design cleanly code-able via the Figma MCP.
- ▌ Linux Freeze Triage · jajupmochi bundleUse when a Linux desktop/laptop goes black-screen, frozen, or unresponsive (often after idle, or when running a GPU/video app like Zoom/Chrome), and you must find the REAL cause instead of guessing. Covers ruling out suspend/sleep, NVIDIA driver kernel-vs-userspace version mismatch from auto-upgrades, OOM meltdowns, PCIe link errors, and DPMS/display-wake hangs. Bundles a near-zero-cost watchdog to capture the next freeze and a read-only diagnostic battery. Apply before recommending any fix for a freeze/black-screen.
- ▌
- ▌
- ▌ Verify · jajupmochiRun the project's CI gate locally — ruff lint, ruff format check, mypy, and fast pytest (excluding slow/download markers). Use before opening a PR or marking work done.
- ▌ Preview · jajupmochiStart a local dev server for this static site. Required before /verify-visual since file:// breaks fetch() calls for locales/*.json.
- ▌ I18N Sync · jajupmochiCheck key parity across locales/*.json. If divergence is detected, list missing keys per locale and offer to add stubs. Use after editing any locale file.