anentrypoint
- 23 skills
- 0 followers
- 7 hours ago last updated
- ▌
- ▌ Engage · anentrypointSingle self-contained, non-linear workflow graph for a productionlined anything-agent. 146 technique anchors wired into 8 phases + 1 cross-cutting memory layer, navigated by a 10-node cyclic control layer.
- ▌ Lean · anentrypointMethod for building software. Use for any coding, refactoring or debugging task.
- ▌ Trading · anentrypointSystematic and quantitative trading knowledge expressed as semantic anchors in a nonlinear backreferencing mermaid graph, in the style of the llm-coding Semantic-Anchors catalog. Each anchor is a well-defined concept attributable to canonical literature and its authors; naming an anchor activates the whole knowledge cluster. Use for strategy research, factor investing, trend following, mean reversion, options and volatility, portfolio construction, position sizing, backtesting methodology, financial machine learning, market microstructure, execution, behavioral finance, and trading tooling selection.
- ▌ Spoint · anentrypoint bundleBuild multiplayer physics games with the Spoint engine. Use when asked to: create a game, add physics objects, spawn entities, build a map/level, handle player interaction, add weapons, respawn, scoring, create moving platforms, manage world config, load 3D models, add HUD/UI, work with the EventBus, or develop any app inside an apps/ directory.
- ▌ Docmcp · anentrypoint bundleGoogle Docs, Sheets, Drive, Apps Script, and Gmail operations. Use when creating, reading, editing, or formatting Google Docs and Sheets. Use when searching Google Drive. Use when managing Apps Script projects. Use when sending, receiving, and managing Gmail messages.
- ▌ Agent Gsuite · anentrypoint bundleGoogle Workspace operations — Docs, Sheets, Drive, Apps Script, Gmail, Calendar, Tasks, Slides, Contacts, Chat, and Search. Use for creating, reading, editing Google Docs/Sheets/Slides. Use for Drive file management. Use for Calendar events and scheduling. Use for Gmail messages, labels, and filters. Use for Tasks, Contacts, and Chat.
- ▌ Codebase Text Report · anentrypointIngest an entire codebase (local directory or remote Git URL) as plain-text chunks via gitoutput's default text mode, read every chunk, and write a report answering a supplied prompt/question about the codebase. The non-image counterpart to codebase-vision-report -- use this when you want the raw text digest read directly rather than rendered as dense images. Requires npx and network access to npm and the target repo.
- ▌ Codebase Vision Report · anentrypointRender an entire codebase (local directory or remote Git URL) into the minimum number of dense PNG pages via gitoutput --images, read every page as images, and write a report answering a supplied prompt/question about the codebase. Use when the user wants a codebase analyzed, summarized, audited, or questioned via the image-packing pipeline instead of pulling raw text into context. Requires npx and network access to npm and the target repo.
- ▌ Adaptogen · anentrypointImprove any agent skill -- itself included -- by running it as an isolated subagent, adversarially critiquing the result, and landing every evidence-backed fix immediately as a direct edit to that skill's own files (or, if the finding is in the host project rather than the skill, a direct edit there). Git is the entire durability layer: no side files, no state tracking -- a commit IS the checkpoint, the commit message IS the record. Use whenever asked to improve, harden, or debug a skill, or to build a new one from a real run instead of a guess.
- ▌ Adaptogen Run · anentrypointDispatch a real, isolated subagent run of a target skill against a concrete, anchored task and capture its verbatim report -- never simulated. Central run state of the adaptogen DAG, entered from orient, build-new, critique (loop-back), or commit-confirm (regression). Use when adaptogen's router sends you here to actually exercise a target skill.
- ▌ Adaptogen Land · anentrypointEdit the target skill's actual files for every finding confirmed by adaptogen-critique's evidence gate, reading each edit back to confirm it landed. Also the state that restructures a target skill into a DAG of self-contained sibling skills, agentskills.io-compliant, when a pass's evidence calls for it. Use when adaptogen's router sends you here with confirmed findings in hand.
- ▌ Adaptogen Orient · anentrypointFirst state of the adaptogen DAG: locate and classify a target agent skill (existing vs. new) and confirm its git co-location, before any run or edit happens. Use when adaptogen's router sends you here, or whenever you need to determine whether a skill target is improvable in-place or needs to be drafted from scratch first.
- ▌ Adaptogen Critique · anentrypointDispatch a fresh-context adversarial critique of a run captured by adaptogen-run, applying a strict evidence gate (cited + independently re-checked) before any finding is allowed through to adaptogen-land. Use when adaptogen's router sends you here with a run report in hand.
- ▌ Adaptogen Build New · anentrypointDraft a brand-new agent skill from scratch when adaptogen's orient state finds no existing SKILL.md at the target. Writes a spec-compliant skill (or DAG of sibling skills, if the task warrants one) that is not yet run or committed -- adaptogen-run always follows to actually exercise the draft. Use when adaptogen's router sends you here after classifying a target as new.
- ▌ Adaptogen Commit Confirm · anentrypointCommit edits landed by adaptogen-land to git with an evidence-citing message, then regress to adaptogen-run to confirm the fix actually held -- reverting and retrying if it didn't. Terminal commit-and-verify state of the adaptogen DAG. Use when adaptogen's router sends you here with confirmed, file-landed edits ready to commit.
- ▌ Gm · anentrypointThe primary driver for every coding, refactoring, debugging, or engineering task -- used for the whole task.
- ▌ Gm Continue · anentrypointThe mandatory final handoff after a gm walk reaches phase=COMPLETE with prd_pending_count=0. Never end a gm session with prose alone -- dispatch this skill instead. It searches for genuinely remaining work and reloads gm if any exists; if gm already ran a full walk without resolving everything, it loads wfgy-method instead to apply bounded-retry-then-surface discipline before any further gm re-entry. Use immediately after any gm chain reaches its terminal state, never as a substitute for gm itself.
- ▌ Wfgy Method · anentrypoint bundleApplies WFGY (Wan Fa Gui Yi), a portable reasoning discipline for reducing drift and incoherence across multi-step agent work, adapted from onestardao/WFGY's core mechanism. Compares each step against the stated goal, considers more than one approach before committing to ambiguous or high-stakes decisions, and checkpoints before risky steps so it can revert and bounded-retry instead of compounding a mistake. Records durable lessons in this project so future sessions inherit them. Use when starting any non-trivial multi-step task, when a task risks losing track of its original goal over many steps, when facing a decision with real alternatives worth comparing, or when the agent notices it has contradicted itself or gone in circles and needs a disciplined way to recover. Distinct from `gm-continue`: that skill is the post-`gm`-COMPLETE remaining-work check; this skill is the general drift-recovery discipline `gm-continue` invokes when a `gm` walk repeats the same gap -- not a substitute for its check.
- ▌ Agent Memory · anentrypointSets up and drives TencentDB Agent Memory (MemoryCore + MemoryHub + MemoryProxy + MemoryPanel, from AnEntrypoint/agent-memory) -- a persistent, cross-session memory and knowledge system for AI agents. Chat Memory (L0 conversation -> L1 atom -> L2 scenario -> L3 persona), a versioned Skill library extracted from past work, a Wiki + CodeGraph knowledge map over docs and code, and a human-controlled review panel. Use when the user wants an agent team to share and accumulate memory/skills/knowledge across sessions and across multiple agent frameworks (not just this one Claude Code session), when they mention "memory hub", "team memory", "chat memory", "skill library", "wiki", "codegraph", or ask to install/configure/troubleshoot the memory-tencentdb plugin, or when onboarding a new agent into an existing team's accumulated experience. As of gm's tencentdb_backend addition, this system's format can ALSO be gm's own memorize/recall/memorize-fire/memorize-prune backend for an opted-in namespace (see gm.config.json's
- ▌ Polaris Protocol · anentrypointWFGY 5.0 Polaris Protocol -- the active flagship route from onestardao/WFGY. A two-layer reasoning system that compiles goals before execution and shoots complex problems into inspectable routes, with drift control throughout. This skill is the tree root: load it first, then dispatch its child skills as explicit transitions -- polaris-goal-compiler (compile), fifth-dimension-engine (shoot), wfgy-method (drift control). Use for any complex, multi-step, high-stakes, or long-horizon task where premature completion or goal drift is a risk.
- ▌ Polaris Goal Compiler · anentrypoint bundleA human-AI communication protocol layer that compiles goals into task atoms, active/blocked work, verification gates, and claim ceilings before execution. Part of WFGY 5.0 Polaris Protocol. Use before complex AI work to make it inspectable, harder to fake, and less likely to collapse into premature completion.
- ▌ Fifth Dimension Engine · anentrypoint bundleWFGY 5.0's core problem-solving tool. Lifts targets into higher problem-coordinates and returns structured routes (proof paths, strategy kernels, research structures, repair paths, positioning routes). Theorem work to everyday decisions. Use after Goal Compiler to execute the compiled problem specification.