Automated summary

Manages the full task lifecycle in a markdown repository (TASKS.md index plus tasks/ files) by delegating to the gald3r engine through its CLI or MCP tools.

Strengths

Single source of truth: ID allocation, file placement, status-to-folder moves, index regeneration and validation are all owned by the engine.
Concurrency-safe routing: during multi-agent runs, new tasks land as id-less drafts in tasks/inbox/ and intake assigns IDs atomically, preventing collisions.
A documented manual fallback in SKILL.full.md plus the task-file schemas keeps installs working even without the engine.
Goes beyond task creation to cover complexity scoring and sprint planning.

Limitations

Tightly bound to .gald3r/ conventions (paths, run-state markers, environment variables), so it does not port to other task trackers.
The preferred path assumes the gald3r engine is provisioned; otherwise you must follow the longer manual procedure.
Inbox routing relies on correctly detecting an active run — a misconfiguration can send drafts to the wrong location.

When to use it

Use it whenever you need to create, update, move or plan tasks inside a gald3r-managed repository.

When not to use it

Avoid it if the project does not use the .gald3r/ task layout or the team works out of a hosted tracker like Jira.

Security analysis

Safe

Quality score82/100

The skill is a declarative shim describing task lifecycle management via a bundled engine and manual fallback. It contains no destructive commands, no network exfiltration, no obfuscated payloads, and no instruction to disable safety. It references a CLI and MCP tools but does not execute arbitrary shell or system commands directly.

No concerns found

How this analysis is made

Examples

Create and score a task

Create a new task for adding rate limiting to the /api/login endpoint, score its complexity, and place it in the correct tasks/ folder.

Sprint planning

Run sprint planning: pull all open tasks from TASKS.md, score their complexity, and propose a scope for the next two-week sprint.

Status transition with validation

Move task T142 to in-progress, regenerate the TASKS.md index, then validate that every task file matches the task-file schema.

name: g-skl-tasks maturity: production description: Own and manage all task data — TASKS.md index, tasks/ individual files, status transitions, sync validation, complexity scoring, and sprint planning. Single source of truth for everything task-related. token_budget: low subsystem_memberships: [TASK_MANAGEMENT]

g-skl-tasks — thinned shim (engine-backed)

Name: Complete Task Management
Author: Skills Guide Bot

Handled by the bundled gald3r engine (.gald3r_sys/engine, pure Mode-A, no LLM). Full original procedure retained in SKILL.full.md so an install without the engine still works.

What it does: task lifecycle over TASKS.md + tasks/<status>/.

Preferred — invoke the engine

CLI: gald3r task … (or the installed gald3r)
MCP tools: gald3r_task_* · facade Gald3r(...).tasks

The engine owns ID allocation, file placement, status→folder moves, index regeneration, and validation. .gald3r/ markdown stays the data source of truth.

Active agent run → inbox routing (T585)

During a multi-agent / autopilot run (marker .gald3r/logs/ggo_run_state.json active: true, or env GALD3R_AGENT_RUN=1), the engine create() auto-routes a new task to tasks/inbox/ as an id-less draft (uuid-suffixed filename) instead of assigning an id directly. The hot-inbox intake (run at each iteration boundary) is the single ID-assigning authority and assigns ids atomically — so concurrent agents can never collide on the next id. Idle (no run) → direct create, unchanged. Hand-writing agents (manual fallback) MUST drop new-task drafts in tasks/inbox/ during a run — never write tasks/open/ + regenerate the index directly.

Manual fallback (engine not provisioned)

Follow SKILL.full.md (full procedure) + the schema in .gald3r_sys/schemas/ (task-file). Everything needed ships in the install — nothing external.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/complete-task-management-mrwakfth/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/complete-task-management-mrwakfth' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/complete-task-management-mrwakfth/download' --output '.skill-downloads/complete-task-management-mrwakfth/SKILL.md.part' && mv '.skill-downloads/complete-task-management-mrwakfth/SKILL.md.part' '.skill-downloads/complete-task-management-mrwakfth/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/complete-task-management-mrwakfth/SKILL.md' && test -s '.skill-downloads/complete-task-management-mrwakfth/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/g-skl-tasks' && cp -R '.skill-downloads/complete-task-management-mrwakfth' '.claude/skills/g-skl-tasks'

Cursor

test -f '.skill-downloads/complete-task-management-mrwakfth/SKILL.md' && test -s '.skill-downloads/complete-task-management-mrwakfth/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/g-skl-tasks' && cp -R '.skill-downloads/complete-task-management-mrwakfth' '.cursor/skills/g-skl-tasks'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/complete-task-management-mrwakfth'

openskills read 'complete-task-management-mrwakfth'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/complete-task-management-mrwakfth/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

PDF Reader

Productivity

Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.

Claude CodeCursorCodexbeginnerSafe 20,122

Skills Guide Bot