MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Navigates role transitions for MCP work items using advanceitem.
$ npx skills add jpicklyk/task-orchestrator --skill status-progression -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jpicklyk/task-orchestrator status-progression --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jpicklyk/task-orchestrator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/claude-plugins/task-orchestrator/skills/status-progression .claude/skills/status-progression && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "status-progression" agent skill from https://github.com/jpicklyk/task-orchestrator/tree/main/claude-plugins/task-orchestrator/skills/status-progression into .claude/skills/status-progression/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status-progression", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jpicklyk/task-orchestrator/tree/main/claude-plugins/task-orchestrator/skills/status-progressionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jpicklyk/task-orchestrator --skill status-progression -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jpicklyk/task-orchestrator status-progression --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jpicklyk/task-orchestrator.git skills-src && mkdir -p .agents/skills && cp -r skills-src/claude-plugins/task-orchestrator/skills/status-progression .agents/skills/status-progression && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "status-progression" agent skill from https://github.com/jpicklyk/task-orchestrator/tree/main/claude-plugins/task-orchestrator/skills/status-progression into .agents/skills/status-progression/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status-progression", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jpicklyk/task-orchestrator --skill status-progression -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jpicklyk/task-orchestrator status-progression --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jpicklyk/task-orchestrator.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/claude-plugins/task-orchestrator/skills/status-progression .cursor/skills/status-progression && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "status-progression" agent skill from https://github.com/jpicklyk/task-orchestrator/tree/main/claude-plugins/task-orchestrator/skills/status-progression into .cursor/skills/status-progression/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status-progression", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jpicklyk/task-orchestrator.git --path claude-plugins/task-orchestrator/skills/status-progression--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jpicklyk/task-orchestrator --skill status-progression -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jpicklyk/task-orchestrator status-progression --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jpicklyk/task-orchestrator.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/claude-plugins/task-orchestrator/skills/status-progression .gemini/skills/status-progression && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "status-progression" agent skill from https://github.com/jpicklyk/task-orchestrator/tree/main/claude-plugins/task-orchestrator/skills/status-progression into .gemini/skills/status-progression/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status-progression", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jpicklyk/task-orchestrator status-progressionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jpicklyk/task-orchestrator --skill status-progression -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jpicklyk/task-orchestrator.git skills-src && mkdir -p .github/skills && cp -r skills-src/claude-plugins/task-orchestrator/skills/status-progression .github/skills/status-progression && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "status-progression" agent skill from https://github.com/jpicklyk/task-orchestrator/tree/main/claude-plugins/task-orchestrator/skills/status-progression into .github/skills/status-progression/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status-progression", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jpicklyk/task-orchestrator --skill status-progression -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jpicklyk/task-orchestrator status-progression --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jpicklyk/task-orchestrator.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/claude-plugins/task-orchestrator/skills/status-progression .opencode/skills/status-progression && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "status-progression" agent skill from https://github.com/jpicklyk/task-orchestrator/tree/main/claude-plugins/task-orchestrator/skills/status-progression into .opencode/skills/status-progression/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status-progression", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
status-progressionNavigates role transitions for MCP work items using advanceitem.
Status Progression is an agent skill from jpicklyk/task-orchestrator. Navigates role transitions for MCP work items using advanceitem. Shows current role, gate status, required notes, and the correct trigger to use. Use when a user says: advance this item, move to work, start this task, complete this item, what's the next status, why can't I advance, unblock this, cancel this item, or check gate status.
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. It works with Model Context Protocol. The repository describes itself as: Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what… The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 3e83170. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Status Progression loads about 3.3k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 1,306 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from jpicklyk/task-orchestrator at commit 3e83170, republished under its MIT licence (© jpicklyk). 1,306 words, ~3,269 tokens.
.claude/skills/status-progression/SKILL.md (or your agent's skills folder).Guides role transitions for a WorkItem: identify the item, check gate status, fill missing notes, and advance. Handles all triggers including block, resume, and cancel.
Resolve $ARGUMENTS to a UUID via query_items search (operation="search", query=$ARGUMENTS, limit=5); if ambiguous, present matches via AskUserQuestion. If $ARGUMENTS is empty, ask for a UUID or title fragment.
Once you have the item ID, call:
get_context(itemId="<item-uuid>")Parse the response and display a status card. Use this format:
◉ "Implement authentication module"
Role: work
Gate: ⊘ blocked — 2 required notes missing
Missing: implementation-notes (work, required)
session-tracking (work, required)
Guidance: "Describe what was implemented, which files changed, and why
the approach was chosen..."◉ "Design API schema"
Role: queue
Gate: ✓ open — all required notes filled (or no schema)
Next: advance_item(trigger="start") → workFields to surface from get_context response:
| Response Field | What to Show |
|---|---|
item.role | Current role label |
gateStatus.canAdvance | ✓ open or ⊘ blocked |
gateStatus.missing | List each missing note key + role |
guidanceKey | Key of first unfilled required note with guidance; resolve its text via query_items(operation="schema", itemId="<uuid>") to show as "Guidance:" |
noteSchema | List all schema notes with exists status |
If the item has no schema (no tags matching a schema key), noteSchema will be empty and the gate is always open.
If gateStatus.canAdvance = false, the item cannot advance until required notes are filled.
For each missing note, check whether its content can be inferred from the conversation context. If yes, fill it directly. If not, ask the user what to capture.
Use guidanceKey to prompt the user — resolve its guidance text via query_items(operation="schema", itemId=...). Only one guidanceKey is returned — for the first unfilled required note. See schema entries list for all unfilled notes.
Fill notes with:
manage_notes(
operation="upsert",
notes=[
{ itemId: "<uuid>", key: "implementation-notes", role: "work", body: "<content>" },
{ itemId: "<uuid>", key: "session-tracking", role: "work", body: "<content>" }
]
)After filling, re-check gate status:
get_context(itemId="<uuid>")Confirm gateStatus.canAdvance = true before proceeding to Step 4. If notes are still missing after the upsert, show the updated status card and repeat for any remaining gaps.
With the gate open, call advance_item with the appropriate trigger (trigger semantics are documented in the advance_item tool description):
advance_item(transitions=[{ itemId: "<uuid>", trigger: "start" }])Parse the response and report the transition result:
✓ Advanced: queue → work
↳ Cascade: "Feature: Auth System" also moved queue → work
↳ Unblocked: "Write integration tests" (was waiting on this item)
↳ Next phase notes:
implementation-notes (work, required)
session-tracking (work, required)Fields to check in the advance response:
| Response Field | What to Report |
|---|---|
newRole | The core transition (previousRole is omitted from success results) |
cascadeEvents | Parent or ancestor items that auto-transitioned |
unblockedItems | Sibling items that are now actionable |
expectedNotes | Notes for the next phase — show as "Next phase notes:" |
If cascadeEvents is empty, omit the cascade line. If unblockedItems is empty, omit the unblocked line. If expectedNotes is empty or absent (no schema), omit the next phase notes line.
Problem: advance_item fails with "required notes not filled"
Cause: The current phase has required notes that have not been upserted yet. Gate enforcement runs before the transition executes.
Solution: The gate-failure error already lists the missing note keys. Fill each one with manage_notes(operation="upsert"), then retry advance_item. Call get_context only if you need broader item state.
Problem: Item cannot advance — it is blocked by a dependency
Cause: Another item has a BLOCKS edge pointing to this item, and that blocking item has not yet reached terminal role.
Solution: Find the blocker:
query_dependencies(operation="get", itemId="<uuid>", direction="incoming", includeItemInfo=true)Identify the blocking item (role will be non-terminal). Advance the blocking item to terminal first. When it completes, the current item appears in unblockedItems.
Problem: Item is in BLOCKED role and start fails
Cause: The item is in the BLOCKED role (was explicitly blocked with trigger: "block"). The start trigger is not valid from BLOCKED — it is only valid from QUEUE, WORK, or REVIEW.
Solution: Use trigger: "resume" to return the item to its previous role:
advance_item(transitions=[{ itemId: "<uuid>", trigger: "resume" }])After resuming, check get_context and then advance normally with start if the gate is open.
Problem: Want to skip the review phase and go directly to terminal
Cause: The item is in WORK role and has a review-phase schema, but verification is already done or not applicable.
Solution: Use trigger: "complete" instead of start. This jumps from any non-terminal role directly to TERMINAL, but it checks ALL required notes across all phases first:
advance_item(transitions=[{ itemId: "<uuid>", trigger: "complete" }])If any required notes across queue, work, or review phases are unfilled, the gate will block this call and list the missing notes. Fill them, then retry.
Problem: advance_item fails with errorCode: "resource_unavailable"
Cause: The item declares a shared resource (via a resources: trait, mode: exclusive) that
another item currently holds — a real resource-lease conflict, not a note-schema gate failure.
errorKind is "transient", distinct from the gate-block/ownership/policy error codes above.
Do NOT treat this like a gate failure — do not "fill in more notes" and do not spin-retry the
same advance_item call. The fix is to wait (retryAfterMs names a backoff hint) or work a
different item; retrying immediately will almost always fail again since the response never
discloses when — only that — the key is contended. contendedResources names the contended key(s)
only; the current holder's identity is never included in this response by design.
Solution:
get_context(itemId="<uuid>") → resourceLeases block (shows
holderItemId/acquiredByActorId/expiresAt for the contended key), or the REST route
GET /api/v1/resources/leases for a fleet-wide view (ADMIN capability needed to see the
holder's actor identity).DELETE /api/v1/resources/leases/{key} (ADMIN capability) rather than waiting out the TTL.See Workflow Guide §11 — Resource Leasing for the full contention/retry model and the guarantees-vs-non-guarantees statement.
Problem: Parent item cascaded unexpectedly
Cause: Cascade is by design. When the first child of a container starts (queue → work), the container cascades to work automatically. When the last child reaches terminal, the container cascades to terminal automatically.
Solution: This is expected behavior — no action needed. Check cascadeEvents in the advance_item response to see exactly which ancestors transitioned and why. If the cascade is unwanted, you can manually adjust the parent's role using advance_item with trigger: "block" or trigger: "complete" depending on the desired state.
Problem: advance_item returns "no valid transition" or "item already terminal"
Cause: The item is already in TERMINAL role (completed or cancelled). Terminal is a final state — no triggers are valid from terminal.
Solution: The item cannot be advanced further. If the item was completed in error, you would need to create a new item. To verify the item's current state:
query_items(operation="get", itemId="<uuid>")Check the role field. If role = "terminal", the item's lifecycle is complete.
For items with no matching note schema, there are no gates. Items flow freely through roles.
Step 1: Check state
get_context(itemId="abc-123")Response shows role: "queue", gateStatus.canAdvance: true, noteSchema: [].
Status card:
◉ "Refactor database connection pool"
Role: queue
Gate: ✓ open (no schema)
Next: advance_item(trigger="start") → workStep 2: Start work
advance_item(transitions=[{ itemId: "abc-123", trigger: "start" }])Result:
✓ Advanced: queue → workStep 3: Complete work (skip review)
After the refactor is done, complete directly:
advance_item(transitions=[{ itemId: "abc-123", trigger: "complete" }])Result:
✓ Advanced: work → terminalNo gates — no notes required. Items without a schema move freely at any time using any valid trigger.
feature-implementation TagItems tagged feature-implementation have a schema with required notes at each phase. The gate blocks advancement until notes are filled.
Step 1: Check state
get_context(itemId="def-456")Response shows role: "queue", gateStatus.canAdvance: false, missing: ["feature-summary"].
Status card:
◉ "Add OAuth2 login flow"
Role: queue
Gate: ⊘ blocked — 1 required note missing
Missing: feature-summary (queue, required)
Guidance: "Document the acceptance criteria and scope of this feature.
Include: what the feature does, what it does not do, and
the definition of done."Step 2: Fill the missing note
Ask the user (or extract from conversation context) what the requirements are, then upsert:
manage_notes(
operation="upsert",
notes=[{
itemId: "def-456",
key: "feature-summary",
role: "queue",
body: "Implement OAuth2 login via GitHub and Google providers. Users should
be redirected to provider, authenticated, and returned to the app
with a session token. Out of scope: social sign-up flow, profile
linking. Done when: login button visible on /login, both providers
work in staging, session persists across page reload."
}]
)Step 3: Re-check gate
get_context(itemId="def-456")Updated status card:
◉ "Add OAuth2 login flow"
Role: queue
Gate: ✓ open — all queue notes filled
Next: advance_item(trigger="start") → workStep 4: Advance to work
advance_item(transitions=[{ itemId: "def-456", trigger: "start" }])Result:
✓ Advanced: queue → work
↳ Next phase notes:
implementation-notes (work, required)
session-tracking (work, required)The expectedNotes in the response shows what must be filled during the work phase before the next start will succeed. Fill these notes as implementation progresses, then return control to the orchestrator. The orchestrator calls advance_item(trigger="start") to advance the item to the next phase (review if the schema has review-phase notes, or terminal otherwise).
| Situation | Action |
|---|---|
| Item is in queue, no gate | advance_item(trigger="start") |
| Item is in queue, gate blocked | Fill missing queue notes → advance_item(trigger="start") |
| Item is in work, ready for review | advance_item(trigger="start") |
| Item is in work, skip review | advance_item(trigger="complete") — checks all gates |
| Item is in review, verified | advance_item(trigger="start") |
| Item needs to be paused | advance_item(trigger="block") |
| Item is in BLOCKED role | advance_item(trigger="resume") first |
| Item should be abandoned | advance_item(trigger="cancel") — no gates |
| Item is terminal | No further transitions possible |
| Blocker is another item | Advance the blocking item first |
© jpicklyk, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in claude-plugins/task-orchestrator/skills/status-progression of jpicklyk/task-orchestrator.
Open the folder on GitHubat commit 3e83170
Status Progression next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Status Progression this skilljpicklyk/task-orchestrator | 207 | — | ~3.3k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Fastmcp Client CLIPrefectHQ/fastmcp | 28k | 1 repos | ~823 | Automated safety check: Pass | Apache-2.0 | |
| MemPalace Memory SearchMemPalace/mempalace | 59k | — | ~1.4k | Automated safety check: Pass | MIT |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
MemPalace/mempalace
Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
jpicklyk/task-orchestrator
Walks through how to launch and reach the MCP Task Orchestrator server container: transport, REST API, port publishing, config mounts and config-sync.
jpicklyk/task-orchestrator
Resolves ready MCP work items into a run plan, shows it to you, then executes it through the Workflow tool or direct subagent dispatch, with post-run verification.
jpicklyk/task-orchestrator
Migrates an existing unscoped Task Orchestrator database to the project-scoping convention in place, creating one project anchor root and re-parenting work trees under it after a mandatory dry run.
jpicklyk/task-orchestrator
Completes or cancels a whole feature subtree, a named list of items, or a batch of stale work items at once, previewing the impact and warning before force-completing anything active.
jpicklyk/task-orchestrator
Creates an MCP work item from conversation context, anchoring it under the right container, inferring type and priority and pre-filling the required notes.
jpicklyk/task-orchestrator
Views, creates, deletes and diagnoses BLOCKS, IS_BLOCKED_BY and RELATES_TO links between MCP work items, including why an item cannot start.
Works with
Categories
Navigates role transitions for MCP work items using advanceitem. Status Progression is an agent skill from jpicklyk/task-orchestrator. Navigates role transitions for MCP work items using advanceitem.
Status Progression fits situations like: A user says: advance this item; start this task; complete this item; whats the next status.
Run `npx skills add jpicklyk/task-orchestrator --skill status-progression -a claude-code`. Or copy the skill folder (claude-plugins/task-orchestrator/skills/status-progression in jpicklyk/task-orchestrator) into .claude/skills/status-progression in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jpicklyk/task-orchestrator --skill status-progression -a codex`. Or copy the skill folder (claude-plugins/task-orchestrator/skills/status-progression in jpicklyk/task-orchestrator) into .agents/skills/status-progression in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jpicklyk/task-orchestrator --skill status-progression -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/status-progression, .gemini/skills/status-progression, .github/skills/status-progression and .opencode/skills/status-progression in your project.
SKILL.md names no scripts, command-line tools or credentials: Status Progression is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Status Progression is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Status Progression: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jpicklyk (a GitHub user) maintains it in jpicklyk/task-orchestrator, which has 207 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 8, 2026.
Source: jpicklyk/task-orchestrator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.