Agent skill

Feature Implementation

by jpicklyk in jpicklyk/task-orchestrator

Guides the full lifecycle of a feature-implementation tagged MCP item (the feature container) — from queue through review.

MITAuto-check passedAgent Workflows

Install Feature Implementation

skills CLI
$ npx skills add jpicklyk/task-orchestrator --skill feature-implementation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jpicklyk/task-orchestrator feature-implementation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jpicklyk/task-orchestrator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/feature-implementation .claude/skills/feature-implementation && rm -rf skills-src

Use ~/.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/

Facts

Skill name
feature-implementation
GitHub stars
207
Token cost
~2.2k tokens
SKILL.md length
938 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Guides the full lifecycle of a feature-implementation tagged MCP item (the feature container) — from queue through review.

  • Works in 4 steps: Setup → Queue: Define the Feature Summary → Work: Implement and Document → …
  • The user says: implement a feature
  • SKILL.md covers Phase 0 — Setup, Phase 1 — Queue: Define the…, Phase 2 — Work: Implement and… and Phase 3 — Review: Verify,…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Feature Implementation is an agent skill from jpicklyk/task-orchestrator. Guides the full lifecycle of a feature-implementation tagged MCP item (the feature container) — from queue through review. Creates or resumes the feature container, fills gate-enforced notes at each phase (feature-summary, implementation-notes, session-tracking, review-checklist), dispatches implementation subagents, and advances through queue, work, and review to terminal. Use when the user says: implement a feature, start a new feature, feature workflow, resume feature work, guide feature lifecycle, or…

Its SKILL.md is about 2.2k 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.

When your agent uses it

  • The user says: implement a feature
  • Start a new feature
  • Feature workflow
  • Resume feature work

Example prompts

  • “Use the feature-implementation skill to guide the full lifecycle of a feature-implementation tagged MCP item (the feature container) — from queue…”
  • “/feature-implementation”

Requirements

  • Docker

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Setup
  2. Queue: Define the Feature Summary
  3. Work: Implement and Document
  4. Review: Verify, Deploy, and Close

What it can do on your machine

Read from SKILL.md and the folder at commit b688ea0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    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.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Feature Implementation loads about 2.2k tokens when it runs. Until then it costs about 145 tokens; SKILL.md has 938 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~145
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from jpicklyk/task-orchestrator at commit b688ea0, republished under its MIT licence (© jpicklyk). 938 words, ~2,214 tokens.

Download SKILL.mdSave it as .claude/skills/feature-implementation/SKILL.md (or your agent's skills folder).
name
feature-implementation
description
Guides the full lifecycle of a feature-implementation tagged MCP item (the feature container) — from queue through review. Creates or resumes the feature container, fills gate-enforced notes at each phase (feature-summary, implementation-notes, session-tracking, review-checklist), dispatches implementation subagents, and advances through queue, work, and review to terminal. Use when the user says: implement a feature, start a new feature, feature workflow, resume feature work, guide feature lifecycle, or references a feature-implementation item UUID.

Feature Implementation Workflow

End-to-end workflow for a feature-implementation tagged item — the feature container that holds the plan and holistic review. Child work items under this container use the feature-task tag with lighter gates (task-scope instead of the feature-level feature-summary, and no review phase by default — task-level review is opt-in via the needs-task-review trait, which adds a review-checklist note to that child). A second child-level trait, needs-test-author, is opt-in the same way (applied per the /implement Step 1 trigger rule) and adds its own gate-enforced notes.

Covers all three phases (queue → work → review) with gate-enforced notes at each transition.

Usage: /feature-implementation [item-uuid]

  • If item-uuid is provided: load the existing item and resume from its current phase
  • If omitted: create a new item and start from the beginning

Phase 0 — Setup

If an item UUID was provided, call:

get_context(itemId="<uuid>")

Check canAdvance and missingRequiredNotes to determine which phase the item is in, then jump to the appropriate phase below.

If no UUID was provided, create the item:

manage_items(
  operation="create",
  items=[{ title: "<feature title>", tags: "feature-implementation", priority: "medium" }]
)

Note the returned UUID and expectedNotes list. Confirm the item is in queue role, then continue to Phase 1.


Phase 1 — Queue: Define the Feature Summary

Goal: Fill the single required queue-phase note before advancing to work.

1a. Fill feature-summary

Use manage_notes to upsert the feature-summary note:

manage_notes(
  operation="upsert",
  notes=[{
    itemId: "<uuid>",
    key: "feature-summary",
    role: "queue",
    body: "<content>"
  }]
)

What to write: Keep this note lean (target under 2k chars) — it stays at the feature level, not the child-task level where the full spec-quality disciplines apply. Cover:

  • Goal — the problem this solves and who benefits.
  • Findings → tasks table — a table mapping each finding or requirement to the child task that will address it.
  • Dependency edges — ordering constraints between child tasks, if any.
  • Non-goals pointer — a reference to where non-goals are documented per child (each child's task-scope note carries its own alternatives/non-goals/blast-radius/risk/test strategy per the spec-quality framework); this note does not repeat that analysis.
1b. Enter plan mode

After filling the note, use EnterPlanMode to explore the codebase and produce a concrete implementation plan. The pre-plan hook will inject additional guidance.

When the plan is approved, post-plan hook fires — proceed directly to Phase 2 without pausing.

1c. Advance to work
advance_item(transitions=[{ itemId: "<uuid>", trigger: "start" }])

Gate check: feature-summary must be filled. If gate rejects, fill the missing note and retry. If instead the response has errorCode: "resource_unavailable" (errorKind: "transient"), this is resource-lease contention, not a note gate failure — see Quick Reference below.

Confirm newRole: "work" in the response before dispatching implementation subagents.


Phase 2 — Work: Implement and Document

Goal: Delegate implementation, then fill work-phase notes before advancing to review.

2a. Materialize any child items

If the feature has sub-tasks, create them now using create_work_tree with the feature UUID as parentId and the feature-task tag. Each child fills a task-scope queue note (the full spec-quality disciplines — alternatives, non-goals, blast radius, risk flags, test strategy — apply there, not in the feature-level feature-summary). Dispatch implementation subagents with each child item UUID.

Each subagent must:

  • Call advance_item(trigger="start") on their item to enter work phase
  • Fill work-phase notes following the JIT progression loop (the subagent-start hook provides guidance via guidancePointer and skillPointer)
  • Return to the orchestrator — do NOT call advance_item again. The orchestrator handles all further transitions.

By default, feature-task items have no review phase — advance_item(trigger="start") from work goes straight to terminal. A child only gets a review phase if it (or its schema's default_traits) carries the needs-task-review trait, which adds the review-checklist note back in, or the needs-test-author trait, which adds test-independence-audit.

Show full SKILL.md (375 more words)Show less
2b. Fill implementation-notes

After implementation agents return:

manage_notes(
  operation="upsert",
  notes=[{
    itemId: "<uuid>",
    key: "implementation-notes",
    role: "work",
    body: "<content>"
  }]
)

What to write: Key decisions made during implementation. Deviations from the plan. Any surprises (wrong class names, API differences, test isolation issues). Files changed with line counts. If an observation was fixed, reference its item ID.

2c. Fill session-tracking
manage_notes(
  operation="upsert",
  notes=[{
    itemId: "<uuid>",
    key: "session-tracking",
    role: "work",
    body: "<content>"
  }]
)

What to write: Run ./gradlew :current:test. Report total count and any failures, new test classes or cases added, and a summary of what changed this session. This note comes from the session-tracked default trait and feeds /session-retrospective.

2d. Advance to review
advance_item(transitions=[{ itemId: "<uuid>", trigger: "start" }])

Gate check: both implementation-notes and session-tracking must be filled. Confirm newRole: "review" in the response.


Phase 3 — Review: Verify, Deploy, and Close

Goal: Fill the required review-checklist note (per the review-quality skill), deploy and verify in the running MCP server, then close the item.

3a. Fill review-checklist

Follow the review-quality skill's framework — plan alignment against feature-summary and each child's task-scope, test quality, and (if /simplify ran) test coverage of its changes.

manage_notes(
  operation="upsert",
  notes=[{
    itemId: "<uuid>",
    key: "review-checklist",
    role: "review",
    body: "<content>"
  }]
)

What to write: A feature-level verdict aggregating across children — reference each child's own review-checklist if the needs-task-review trait produced one. See the review-quality skill for the full findings format and verdict types (Pass / Fail — blocking issues / Pass with observations).

3b. Deploy to Docker (if needed)

Run /deploy_to_docker --current to rebuild the image with the new code. Reconnect MCP after deploy: /mcp.

3c. Smoke test the change

Exercise the new capability via MCP tool calls. Confirm it behaves as described in the feature-summary note's goal.

3d. Fill deploy-notes (optional)
manage_notes(
  operation="upsert",
  notes=[{
    itemId: "<uuid>",
    key: "deploy-notes",
    role: "review",
    body: "<content>"
  }]
)

What to write: Whether a Docker rebuild was done and what image tag was used. Plugin version bump (if any). MCP reconnect required. Any smoke test results.

3e. Close the item
advance_item(transitions=[{ itemId: "<uuid>", trigger: "start", summary: "<one-line summary>" }])

Confirm newRole: "terminal". Run get_context() health check to verify no stalled items.


Quick Reference

PhaseRequired notesAdvance trigger
queuefeature-summarystart → work
workimplementation-notes, session-trackingstart → review
reviewreview-checkliststart → terminal

Gate error pattern: "required notes not filled for <phase> phase: <keys>" → Fill the listed notes, then retry advance_item.

Resource-lease contention pattern: applied: false, errorCode: "resource_unavailable", errorKind: "transient", contendedResources: [...] on a start into work — a different failure mode than the gate error above. Do NOT fill notes or spin-retry; the resource is held by another item. Work a different item and retry later, or report contention upstream.

© jpicklyk, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/feature-implementation of jpicklyk/task-orchestrator.

Open the folder on GitHubat commit b688ea0

Compare with similar skills

Feature Implementation 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.

Feature Implementation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Feature Implementation this skilljpicklyk/task-orchestrator207—~2.2kAutomated safety check: PassMIT
Agent QA Authoringvostride/agent-qa902—~569Automated safety check: PassCustom licence
Agent QA Result Triagevostride/agent-qa902—~394Automated safety check: PassCustom licence
Lightpandalightpanda-io/agent-skill101—~6kAutomated safety check: PassApache-2.0
Opik Comparecomet-ml/opik-mcp219—~2.6kAutomated safety check: NotesApache-2.0
Cao Providerawslabs/cli-agent-orchestrator1.4k—~2.3kAutomated safety check: PassApache-2.0

Similar skills

  • Agent QA Authoring

    vostride/agent-qa

    A skill your agent uses when creating, editing, validating, or running agent-qa tests, suites, or hooks.

    902 GitHub stars~569 tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Agent QA Result Triage

    vostride/agent-qa

    A skill your agent uses when investigating failed agent-qa runs, inspecting artifacts, classifying failures, or comparing recent runs.

    902 GitHub stars~394 tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Lightpanda

    lightpanda-io/agent-skill

    Lightpanda browser, drop-in replacement for Chrome-based browsing in any AI agent - faster and lighter for tasks without graphical rendering like data retrieval.

    101 GitHub stars~6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Opik Compare

    comet-ml/opik-mcp

    Run a candidate against the baseline over an Opik test suite and read the numbers back — which cases broke, which got fixed, the per-metric deltas, worst rows, and whether the two runs are…

    219 GitHub stars~2.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Cao Provider

    awslabs/cli-agent-orchestrator

    Official

    Create a new CLI agent provider for CAO (CLI Agent Orchestrator).

    1.4k GitHub stars~2.3k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Waza Interactive

    microsoft/waza

    Official

    Walks you through creating, running and reading waza evals for an agent skill, then proposes concrete fixes when tasks fail or the score is low.

    1.4k GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from jpicklyk/task-orchestrator

All 28 skills in this repo
  • Task Orchestrator Server Setup

    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.

    207 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed
  • Run Wave

    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.

    207 GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed
  • Adopt Project Scope Migration

    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.

    207 GitHub stars~3.7k tokensUpdated yesterday
    Auto-check passed
  • Bulk Task Completion

    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.

    207 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed
  • Task Orchestrator Item Creator

    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.

    207 GitHub stars~4k tokensUpdated yesterday
    Auto-check passed
  • Work Item Dependency Manager

    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.

    207 GitHub stars~3.5k tokensUpdated yesterday
    Auto-check passed

Questions about Feature Implementation

What does Feature Implementation do?

Guides the full lifecycle of a feature-implementation tagged MCP item (the feature container) — from queue through review. Feature Implementation is an agent skill from jpicklyk/task-orchestrator. Guides the full lifecycle of a feature-implementation tagged MCP item (the feature container) — from queue through review.

When should I use Feature Implementation?

Feature Implementation fits situations like: the user says: implement a feature; start a new feature; feature workflow; resume feature work.

How do I install Feature Implementation in Claude Code?

Run `npx skills add jpicklyk/task-orchestrator --skill feature-implementation -a claude-code`. Or copy the skill folder (.claude/skills/feature-implementation in jpicklyk/task-orchestrator) into .claude/skills/feature-implementation in your project. Claude Code loads it when a task matches its description.

How do I install Feature Implementation in Codex?

Run `npx skills add jpicklyk/task-orchestrator --skill feature-implementation -a codex`. Or copy the skill folder (.claude/skills/feature-implementation in jpicklyk/task-orchestrator) into .agents/skills/feature-implementation in your project. Codex loads it when a task matches its description.

Can I use Feature Implementation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jpicklyk/task-orchestrator --skill feature-implementation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feature-implementation, .gemini/skills/feature-implementation, .github/skills/feature-implementation and .opencode/skills/feature-implementation in your project.

What does Feature Implementation need to run?

SKILL.md names no scripts, command-line tools or credentials: Feature Implementation is instructions for the agent only. Our summary lists: Docker.

Does Feature Implementation access the network?

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.

Is Feature Implementation safe to install?

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.

What licence does Feature Implementation use?

Feature Implementation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Feature Implementation use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Feature Implementation?

Skills that share tags, products or a category with Feature Implementation: Agent QA Authoring (vostride/agent-qa, 902 stars), Agent QA Result Triage (vostride/agent-qa, 902 stars), Lightpanda (lightpanda-io/agent-skill, 101 stars) and Opik Compare (comet-ml/opik-mcp, 219 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Feature Implementation?

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 6, 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.