[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MPDHX7RYH44V8DC6YB2RY9":3,"skill-same:01M6MPDHX7RYH44V8DC6YB2RY9":90},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":32,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":63,"ownerDescription":64,"updatedAt":65,"install":66,"resources":79},"01M6MPDHX7RYH44V8DC6YB2RY9","centricmem-agent",null,"Organises and retrieves Markdown memory on the hosted CentricMem librarian (search, notes, decisions, transcripts). Use when coding, researching, reviewing, troubleshooting, or doing multi-step project work — at session start or resume (context compress \u002F checkpoint \u002F new chat), at each deliverable or phase close, filing Non-Micro work, searching project memory, connecting an agent credential, or refreshing this Skill. Skip it for pure Q&A chat that ships nothing. On session start, compare the loaded copy (see REFERENCE Skill refresh) against cm_health \u002F ambient skill_latest and refresh if stale.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzeyu-j\u002Fcentricmem-skill\u002Fskills\u002Fcentricmem-agent\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"centricmem agent","search","changelog","work","notes","false","host","MCP","main","librarian","filing","card","move","cm","project","memory","ids","session start","never","project memory","2026-11-10 10:12:30",false,"---\nname: centricmem-agent\ndescription: \"Organises and retrieves Markdown memory on the hosted CentricMem librarian (search, notes, decisions, transcripts). Use when coding, researching, reviewing, troubleshooting, or doing multi-step project work — at session start or resume (context compress \u002F checkpoint \u002F new chat), at each deliverable or phase close, filing Non-Micro work, searching project memory, connecting an agent credential, or refreshing this Skill. Skip it for pure Q&A chat that ships nothing. On session start, compare the loaded copy (see REFERENCE Skill refresh) against cm_health \u002F ambient skill_latest and refresh if stale.\"\nrequirements:\n  mcps:\n    - centricmem\nlicense: MIT\ncompatibility: \"Requires host MCP at https:\u002F\u002Fmem.centricmem.com\u002Fmcp. Floors use the pre-1.0 0.21.x numbering; every 1.0.x satisfies them all. librarian >=0.21.50: a card is summary + key points (a keep stub is not a card); a folder is cm_keep card:false then cm_import items; archive zip is optional; share: shelf ids; cm_move takes whole paths (never lessons.md or #); cm_delete {file,shelf} a card, heading= for one ##; cm_rename {file,shelf,title}; omitting the cm_library id lists shelves; skipExisting and copy-aside FTS skip. >=0.21.51 Codex OAuth. >=0.21.55 applicant HTTPS callbacks. >=0.21.56 OAuth credential picker and the ChatGPT Approve hop. >=1.0.6 host-ops detail (cm_ops).\"\nmetadata:\n  version: \"1.0.50\"\n  compatible_cli: \">=1.0.38\"\n  changelog_url: https:\u002F\u002Fgithub.com\u002Fzeyu-j\u002Fcentricmem-skill\u002Fblob\u002Fmain\u002FCHANGELOG.md\n---\n\n# CentricMem Agent Skill\n\n**Names:** product\u002FCLI = `centricmem`; GitHub install package = `centricmem-skill`; this Agent Skill folder = `centricmem-agent` (keep that folder name — it is not a second product). Canonical copy: `github.com\u002Fzeyu-j\u002Fcentricmem-skill` → `skills\u002Fcentricmem-agent\u002F` — copies under `~\u002F.cursor`, `~\u002F.agents`, `~\u002F.codex`, plugin trees are synced installs; newest version wins and `centricmem doctor` lists every copy it finds (STALE marks older ones).\nHandover (when \u002F loop). Schemas win. Branches: [REFERENCE.md](REFERENCE.md).\n**Library** → **Shelf** → **Card** (summary + key points). No Inbox \u002F `unclassified`. One credential = grants. Never paste credentials in chat (REFERENCE **Bearer: where plaintext is OK vs not** — claim may write a private local MCP file; docs\u002Fplans use `${VAR}` or URL-only). Hooks and wrappers resolve the credential from process env → nearest `.env` up from cwd → `~\u002F.centricmem\u002F.env`; hook broken but MCP fine → `CENTRICMEM_TOKEN=` in `.env`, never in a prompt.\n**Style** of a card (voice, length, evidence density) is yours + this agent's — not a CentricMem house voice. Structure only: REFERENCE **Card contract**.\n\n## Quick path\n`cm_health` → `cm_ambient` **with `shelf=`** → `cm_note` \u002F `cm_log_decision` with the same `shelf=`. The rest of this file is for when those three are blocked.\n**Health:** `library:null` with valid `auth` \u002F `grants` means connected with no shelf selected, not \"no shelves exist.\" Call `cm_ambient` with `cwd=` or a named `shelf=` and choose from `libraries=`.\n**Shelf:** `suggested_shelf=` is a cwd heuristic, not authority. If the session is not about that shelf, use the one whose charter matches and say which you chose.\n**Wrap-up:** decision unlogged? friction unlogged? stale card cited (>90d, volatile fact)? If all three are no, stop.\n\n## Do not (full list: REFERENCE)\n\n- Don't wait for \"log this\" \u002F close \u002F wrap up to file a finished chunk — sweep before you yield (§4)\n- Don't write `unclassified` — pick or create a named shelf; don't treat this git checkout as the memory disk\n- Don't put secrets \u002F credentials in cards, and never ask the human to paste a credential or transcript in chat\n- Never echo a credential value — fingerprint to confirm (`9352... len=64 fp=5E4ED29C`), never dump `mcp.json` \u002F `config.toml` \u002F `*.env` whole, never redact by length threshold. A credential in the transcript → say so that turn and rotate it. (REFERENCE **Never echo a credential**)\n- Don't stop after a title-only card — every card needs summary + key points\n- No `cm_*` tool in your tool list = the MCP is not attached to this session. Do not simulate ambient or a sweep — skip memory work, and tell the human once at wrap-up that CentricMem was unreachable (host needs the MCP registered, then restarted)\n- Don't confuse a dead session with a credential problem — transport failure → re-handshake path (§0); refusal (401\u002F403) → rotation. Never call a credential unrotated from the store alone: compare card, env, and whether this host is on OAuth.\n\n## When to Use\n\nProject work — session start or resume, and again at each deliverable\u002Fphase close (a light ambient, not a full restart); search; file Non-Micro; connect \u002F refresh Skill. Pure Q&A chat that ships nothing: skip. Recipes: REFERENCE.\n**Daily:** §2 → work → §4 before yield. Connect: REFERENCE. Empty shelf once: REFERENCE Existing memory.\n\n## 0. Reach\n\n1. MCP only `https:\u002F\u002Fmem.centricmem.com\u002Fmcp`: `cm_health` `cm_ambient` `cm_doctor` `cm_search` `cm_show` `cm_note` `cm_log_decision` `cm_done` `cm_keep` `cm_library` `cm_copy` `cm_move` `cm_delete` `cm_rename` `cm_import` `cm_index` `cm_ops`. No curl \u002F CLI-write \u002F bootstrap.\n2. Missing tools or short grants → **connect this turn**. REFERENCE **Reach**. Remote\u002Fcloud is **not** \"paste the credential only\": OAuth if this agent receives the browser login; paste Bearer only when it cannot. Listed OAuth hosts only: an unlisted callback shape leaves the host stuck on \"connecting\", so prefer `\u002Fconnect?device=` and send that callback shape to zeyu@poppyg.com (REFERENCE \"Approved, but the agent stays connecting\").\n   Tools that vanish mid-session or a load-time `discover` failure = the MCP **session** died, not the credential: probe `centricmem doctor` (its own request), re-handshake (goose: disable\u002Fenable centricmem or restart host), retry once. While the session is dead, nothing here is loaded either.\n3. `cm_show` = card on the **hosted** shelf (not a local junction file). `grants=[\"*\"]` = full access. Extra `mode=read` = view-only (search\u002Fshow only). A `share:` shelf can be read-only — owner can share read-only; re-share with a different level to change it (writes then 403). `ACADEMIC.md` beside this → follow it. Upsert corpus paths: REFERENCE **Import shapes** (`bundle.imported` + `rel_path`, never bare `items=`). Host-specific install, refresh or failure detail: `cm_ops` — read it when a host detail actually blocks you (librarian >=1.0.6; served on request, not shipped in every copy).\n4. **Writes — `items=` and `bundle` are different contracts.** `cm_note` \u002F `cm_log_decision` \u002F `cm_done` file cards; `cm_import` with `items=` (or `package.items`, or a zip) adds **new cards under `imported\u002Fkept\u002F`** and nothing else; `cm_import` with **`bundle: {version: 1, …}`** also writes library files — `context` → **`active_context.md`**, `rules` → **`AGENTS.md`**, plus `decisions` \u002F `lessons` \u002F `sessions` \u002F `imported` \u002F `research`. Unknown top-level slot → **`400 BAD_IMPORT_BUNDLE`** (names slot + allowed list). Slot table: REFERENCE **Writes**.\n\n## 1. Classify\n\nSkip (Micro): typo, one-liner, no durable fact. Sweep (Non-Micro): implement \u002F ops \u002F research \u002F architecture \u002F decision — ≥2 real turns **or** one turn that shipped \u002F decided.\n\n## 2. Start\n\nPrefer `cm_ambient` with **`shelf=`** (or `library=`) first — it already carries grants \u002F mode \u002F skill_latest \u002F Recent \u002F Session. That shapes **Recent decisions \u002F Session tail \u002F Curate**, not only later write routing. When you know this session's aim pass **`task=`** (3–8 words) — it drives the `Cued:` \u002F `Warnings:` lanes. Ambient with only an unmatched `cwd` and no `shelf=` often shows empty Recent\u002FSession — that is not \"the shelf is empty.\" When ambient\u002Fdoctor returns **`suggested_shelf=`** (cwd basename matches a shelf id), **use that id on every write this session** — do not wait for the human to name it. Optional durable bind (full-access `*` credential): `cm_library {id, sourceDir: \u003Cabsolute cwd>}` so later ambient cwd-matches. When `library=(none)` and no suggestion: pick from `libraries=` or mint (`cm_library`), same turn as the first Non-Micro write. `cm_health` only when tools are missing, connect is needed, or ambient is unhealthy \u002F unreachable. Unreachable: say once — no bootstrap. Named shelf for writes.\n\n**Host parity before the first card.** `centricmem doctor` names this host and what it can do: `parity` carry on; `armed-off` say the one command that fixes it and do not claim the hook fired; `stale` = local copy older than the CLI; `ceiling` \u002F `unprobed` are normal. Only the CLI sees this — `cm_doctor` cannot read host config. An inject surface that exists but is not live = a session that will not remember itself — fix before filing, not after.\n\n**Resume = new session.** Compress, checkpoint restore, or new chat on same task → ambient first (health only if needed).\n\nOnce after ambient (or health): refresh if `skill_latest` newer. **Load path ≠ refresh path** — read the version of the copy **this host loads**, not a sibling skills dir (plugin-tree hosts: `\u003Chost-plugins-dir>\u002Fcentricmem-skill\u002Fpackage.json`; npx `-g` \u002F `~\u002F.agents` does not update that tree). Install morphologies: REFERENCE Skill refresh — adapt, never invent a fourth shared hub. After a disk refresh: **re-read this SKILL.md and Do not** before the next write — installing newer ≠ acting on it. Name the credential once (`mode=read` → view-only). Don't log → skip sweep.\n\n## 3. During\n\n**chunk** = accepted unit (verified fragment, locked decision, evidenced lesson, delivery). Any in this reply → same-turn sweep. Not the whole task.\n**yield** = any reply end (incl. progress).\n\nSearch\u002Fshow\u002Fambient while working; hold half-finished. **Chunk done → sweep before you yield.** Cards need summary + key points — keep stubs ≠ cards (REFERENCE Writes). Voice\u002Fdensity: theirs + yours (REFERENCE **Card contract**), not a CentricMem template.\n\n## 4. Sweep — single source\n\nNo wrap-up wait; Agent close does not run this; Don't log \u002F Skill done → skip. **Gate:** an unfiled Non-Micro chunk in this reply and zero `cm_*` writes for it, no Don't log → **sweep before you yield**.\n\n| File now | File at wrap-up |\n|---|---|\n| Locked decision; method-changing lesson; finished chunk | Version-tied stats; unverified conclusions |\n| Shipped deliverable (design, artifact, doc, deploy) — tag it `deliverable`; durable user facts (hardware, accounts, preferences) | Session stats |\n\nSame `lessons.md` title → 409; rewrite = `cm_delete` then write (REFERENCE). Early wrong write costs more. Writes carry **`task=` \u002F `outcome=`** when you have them — `outcome=friction` when the work hit a pit (lands in next session's `Warnings:` lane); `task=` defaults to the last session heading.\n\nMCP down: hold **CentricMem deferred sweep**; connect (REFERENCE); file after health. Say so once, keep working without memory, and never fake a card, pick a local hub, or treat a leftover copy of the hub as the shelf.\n\n`shelf=` \u002F `library=` (REFERENCE **Shelf routing**):\n1. Transcript plaintext exists → Shell-read → `cm_keep` (no paste \u002F `path=`). Else skip keep.\n2. Same batch: `cm_note` \u002F `cm_log_decision` \u002F `cm_done` (+ `attach`) as needed.\n3. Copy\u002Fmove\u002Fdelete\u002Frename leftovers: REFERENCE Writes.\n","# CentricMem Agent Skill\n\n**Names:** product\u002FCLI = `centricmem`; GitHub install package = `centricmem-skill`; this Agent Skill folder = `centricmem-agent` (keep that folder name — it is not a second product). Canonical copy: `github.com\u002Fzeyu-j\u002Fcentricmem-skill` → `skills\u002Fcentricmem-agent\u002F` — copies under `~\u002F.cursor`, `~\u002F.agents`, `~\u002F.codex`, plugin trees are synced installs; newest version wins and `centricmem doctor` lists every copy it finds (STALE marks older ones).\nHandover (when \u002F loop). Schemas win. Branches: [REFERENCE.md](REFERENCE.md).\n**Library** → **Shelf** → **Card** (summary + key points). No Inbox \u002F `unclassified`. One credential = grants. Never paste credentials in chat (REFERENCE **Bearer: where plaintext is OK vs not** — claim may write a private local MCP file; docs\u002Fplans use `${VAR}` or URL-only). Hooks and wrappers resolve the credential from process env → nearest `.env` up from cwd → `~\u002F.centricmem\u002F.env`; hook broken but MCP fine → `CENTRICMEM_TOKEN=` in `.env`, never in a prompt.\n**Style** of a card (voice, length, evidence density) is yours + this agent's — not a CentricMem house voice. Structure only: REFERENCE **Card contract**.\n\n## Quick path\n`cm_health` → `cm_ambient` **with `shelf=`** → `cm_note` \u002F `cm_log_decision` with the same `shelf=`. The rest of this file is for when those three are blocked.\n**Health:** `library:null` with valid `auth` \u002F `grants` means connected with no shelf selected, not \"no shelves exist.\" Call `cm_ambient` with `cwd=` or a named `shelf=` and choose from `libraries=`.\n**Shelf:** `suggested_shelf=` is a cwd heuristic, not authority. If the session is not about that shelf, use the one whose charter matches and say which you chose.\n**Wrap-up:** decision unlogged? friction unlogged? stale card cited (>90d, volatile fact)? If all three are no, stop.\n\n## Do not (full list: REFERENCE)\n\n- Don't wait for \"log this\" \u002F close \u002F wrap up to file a finished chunk — sweep before you yield (§4)\n- Don't write `unclassified` — pick or create a named shelf; don't treat this git checkout as the memory disk\n- Don't put secrets \u002F credentials in cards, and never ask the human to paste a credential or transcript in chat\n- Never echo a credential value — fingerprint to confirm (`9352... len=64 fp=5E4ED29C`), never dump `mcp.json` \u002F `config.toml` \u002F `*.env` whole, never redact by length threshold. A credential in the transcript → say so that turn and rotate it. (REFERENCE **Never echo a credential**)\n- Don't stop after a title-only card — every card needs summary + key points\n- No `cm_*` tool in your tool list = the MCP is not attached to this session. Do not simulate ambient or a sweep — skip memory work, and tell the human once at wrap-up that CentricMem was unreachable (host needs the MCP registered, then restarted)\n- Don't confuse a dead session with a credential problem — transport failure → re-handshake path (§0); refusal (401\u002F403) → rotation. Never call a credential unrotated from the store alone: compare card, env, and whether this host is on OAuth.\n\n## When to Use\n\nProject work — session start or resume, and again at each deliverable\u002Fphase close (a light ambient, not a full restart); search; file Non-Micro; connect \u002F refresh Skill. Pure Q&A chat that ships nothing: skip. Recipes: REFERENCE.\n**Daily:** §2 → work → §4 before yield. Connect: REFERENCE. Empty shelf once: REFERENCE Existing memory.\n\n## 0. Reach\n\n1. MCP only `https:\u002F\u002Fmem.centricmem.com\u002Fmcp`: `cm_health` `cm_ambient` `cm_doctor` `cm_search` `cm_show` `cm_note` `cm_log_decision` `cm_done` `cm_keep` `cm_library` `cm_copy` `cm_move` `cm_delete` `cm_rename` `cm_import` `cm_index` `cm_ops`. No curl \u002F CLI-write \u002F bootstrap.\n2. Missing tools or short grants → **connect this turn**. REFERENCE **Reach**. Remote\u002Fcloud is **not** \"paste the credential only\": OAuth if this agent receives the browser login; paste Bearer only when it cannot. Listed OAuth hosts only: an unlisted callback shape leaves the host stuck on \"connecting\", so prefer `\u002Fconnect?device=` and send that callback shape to zeyu@poppyg.com (REFERENCE \"Approved, but the agent stays connecting\").\n   Tools that vanish mid-session or a load-time `discover` failure = the MCP **session** died, not the credential: probe `centricmem doctor` (its own request), re-handshake (goose: disable\u002Fenable centricmem or restart host), retry once. While the session is dead, nothing here is loaded either.\n3. `cm_show` = card on the **hosted** shelf (not a local junction file). `grants=[\"*\"]` = full access. Extra `mode=read` = view-only (search\u002Fshow only). A `share:` shelf can be read-only — owner can share read-only; re-share with a different level to change it (writes then 403). `ACADEMIC.md` beside this → follow it. Upsert corpus paths: REFERENCE **Import shapes** (`bundle.imported` + `rel_path`, never bare `items=`). Host-specific install, refresh or failure detail: `cm_ops` — read it when a host detail actually blocks you (librarian >=1.0.6; served on request, not shipped in every copy).\n4. **Writes — `items=` and `bundle` are different contracts.** `cm_note` \u002F `cm_log_decision` \u002F `cm_done` file cards; `cm_import` with `items=` (or `package.items`, or a zip) adds **new cards under `imported\u002Fkept\u002F`** and nothing else; `cm_import` with **`bundle: {version: 1, …}`** also writes library files — `context` → **`active_context.md`**, `rules` → **`AGENTS.md`**, plus `decisions` \u002F `lessons` \u002F `sessions` \u002F `imported` \u002F `research`. Unknown top-level slot → **`400 BAD_IMPORT_BUNDLE`** (names slot + allowed list). Slot table: REFERENCE **Writes**.\n\n## 1. Classify\n\nSkip (Micro): typo, one-liner, no durable fact. Sweep (Non-Micro): implement \u002F ops \u002F research \u002F architecture \u002F decision — ≥2 real turns **or** one turn that shipped \u002F decided.\n\n## 2. Start\n\nPrefer `cm_ambient` with **`shelf=`** (or `library=`) first — it already carries grants \u002F mode \u002F skill_latest \u002F Recent \u002F Session. That shapes **Recent decisions \u002F Session tail \u002F Curate**, not only later write routing. When you know this session's aim pass **`task=`** (3–8 words) — it drives the `Cued:` \u002F `Warnings:` lanes. Ambient with only an unmatched `cwd` and no `shelf=` often shows empty Recent\u002FSession — that is not \"the shelf is empty.\" When ambient\u002Fdoctor returns **`suggested_shelf=`** (cwd basename matches a shelf id), **use that id on every write this session** — do not wait for the human to name it. Optional durable bind (full-access `*` credential): `cm_library {id, sourceDir: \u003Cabsolute cwd>}` so later ambient cwd-matches. When `library=(none)` and no suggestion: pick from `libraries=` or mint (`cm_library`), same turn as the first Non-Micro write. `cm_health` only when tools are missing, connect is needed, or ambient is unhealthy \u002F unreachable. Unreachable: say once — no bootstrap. Named shelf for writes.\n\n**Host parity before the first card.** `centricmem doctor` names this host and what it can do: `parity` carry on; `armed-off` say the one command that fixes it and do not claim the hook fired; `stale` = local copy older than the CLI; `ceiling` \u002F `unprobed` are normal. Only the CLI sees this — `cm_doctor` cannot read host config. An inject surface that exists but is not live = a session that will not remember itself — fix before filing, not after.\n\n**Resume = new session.** Compress, checkpoint restore, or new chat on same task → ambient first (health only if needed).\n\nOnce after ambient (or health): refresh if `skill_latest` newer. **Load path ≠ refresh path** — read the version of the copy **this host loads**, not a sibling skills dir (plugin-tree hosts: `\u003Chost-plugins-dir>\u002Fcentricmem-skill\u002Fpackage.json`; npx `-g` \u002F `~\u002F.agents` does not update that tree). Install morphologies: REFERENCE Skill refresh — adapt, never invent a fourth shared hub. After a disk refresh: **re-read this SKILL.md and Do not** before the next write — installing newer ≠ acting on it. Name the credential once (`mode=read` → view-only). Don't log → skip sweep.\n\n## 3. During\n\n**chunk** = accepted unit (verified fragment, locked decision, evidenced lesson, delivery). Any in this reply → same-turn sweep. Not the whole task.\n**yield** = any reply end (incl. progress).\n\nSearch\u002Fshow\u002Fambient while working; hold half-finished. **Chunk done → sweep before you yield.** Cards need summary + key points — keep stubs ≠ cards (REFERENCE Writes). Voice\u002Fdensity: theirs + yours (REFERENCE **Card contract**), not a CentricMem template.\n\n## 4. Sweep — single source\n\nNo wrap-up wait; Agent close does not run this; Don't log \u002F Skill done → skip. **Gate:** an unfiled Non-Micro chunk in this reply and zero `cm_*` writes for it, no Don't log → **sweep before you yield**.\n\n| File now | File at wrap-up |\n|---|---|\n| Locked decision; method-changing lesson; finished chunk | Version-tied stats; unverified conclusions |\n| Shipped deliverable (design, artifact, doc, deploy) — tag it `deliverable`; durable user facts (hardware, accounts, preferences) | Session stats |\n\nSame `lessons.md` title → 409; rewrite = `cm_delete` then write (REFERENCE). Early wrong write costs more. Writes carry **`task=` \u002F `outcome=`** when you have them — `outcome=friction` when the work hit a pit (lands in next session's `Warnings:` lane); `task=` defaults to the last session heading.\n\nMCP down: hold **CentricMem deferred sweep**; connect (REFERENCE); file after health. Say so once, keep working without memory, and never fake a card, pick a local hub, or treat a leftover copy of the hub as the shelf.\n\n`shelf=` \u002F `library=` (REFERENCE **Shelf routing**):\n1. Transcript plaintext exists → Shell-read → `cm_keep` (no paste \u002F `path=`). Else skip keep.\n2. Same batch: `cm_note` \u002F `cm_log_decision` \u002F `cm_done` (+ `attach`) as needed.\n3. Copy\u002Fmove\u002Fdelete\u002Frename leftovers: REFERENCE Writes.\n",{"name":5,"license":15,"metadata":49,"description":7,"requirements":53,"compatibility":56},{"version":50,"changelog_url":51,"compatible_cli":52},"1.0.50","https:\u002F\u002Fgithub.com\u002Fzeyu-j\u002Fcentricmem-skill\u002Fblob\u002Fmain\u002FCHANGELOG.md",">=1.0.38",{"mcps":54},[55],"centricmem","Requires host MCP at https:\u002F\u002Fmem.centricmem.com\u002Fmcp. Floors use the pre-1.0 0.21.x numbering; every 1.0.x satisfies them all. librarian >=0.21.50: a card is summary + key points (a keep stub is not a card); a folder is cm_keep card:false then cm_import items; archive zip is optional; share: shelf ids; cm_move takes whole paths (never lessons.md or #); cm_delete {file,shelf} a card, heading= for one ##; cm_rename {file,shelf,title}; omitting the cm_library id lists shelves; skipExisting and copy-aside FTS skip. >=0.21.51 Codex OAuth. >=0.21.55 applicant HTTPS callbacks. >=0.21.56 OAuth credential picker and the ChatGPT Approve hop. >=1.0.6 host-ops detail (cm_ops).","cebc3dce495d7eb80d3b1d5841f877a4a92e162d","plugins\u002Fzeyu-j\u002Fcentricmem-skill\u002Fskills\u002Fcentricmem-agent",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill centricmem-agent",{"tool":72,"command":73},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill centricmem-agent",{"tool":75,"command":76},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill centricmem-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzeyu-j\u002Fcentricmem-skill\u002Fskills\u002Fcentricmem-agent\u002FSKILL.md",true,[80,86],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"agents\u002Fopenai.yaml","REFERENCE","参考文档",591,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzeyu-j\u002Fcentricmem-skill\u002Fskills\u002Fcentricmem-agent\u002Fagents\u002Fopenai.yaml",{"path":87,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":88,"sourceHtmlUrl":89},"REFERENCE.md",57023,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzeyu-j\u002Fcentricmem-skill\u002Fskills\u002Fcentricmem-agent\u002FREFERENCE.md",[91,100,108,116,124,132],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":99},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":99},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":99},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":99},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":128,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":99},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":136,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":99},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]