Automated summary
Analyzes a list of tasks to detect file overlap and dependencies, then proposes safe parallel execution groups with an estimated speedup.
Strengths
- Emits a structured, directly actionable report: parallel groups, sequential ordering, recommendation and warnings
- Ships an explicit decision table (parallelize / mixed / sequential) that makes the verdict predictable
- Falls back to scanning the `.manifold/` directory to infer candidate tasks when the user supplies none
- Repackages a Claude Code hook-style auto-suggester as an on-demand, invokable skill
Limitations
- Overlap detection relies only on reading task descriptions, with no actual inspection of code or the repository
- The skill only advises: it does not execute, launch, or validate the groups it proposes
- The stated speedup is a rough estimate, and low-confidence predictions surface only as a warning line
Use it when planning multi-task or multi-step work and you need to know which tasks can safely run at the same time.
Avoid it for a single task, or when you need a real code-level impact analysis rather than a heuristic based on descriptions.
Security analysis
SafeThis skill is purely analytical: it instructs the agent to parse task descriptions, compare likely file paths, and emit a recommendation in a markdown template. There is no declared tool usage, no shell commands, no network access, no credential handling, and no file modification beyond optionally reading a .manifold/ directory to inspect the current phase. Worst-case behavior is an inaccurate parallelization suggestion, which is a planning risk rather than a security one.
No concerns found
How this analysis is madeExamples
I have four tasks: add OAuth login, write auth integration tests, refactor the billing service, and update the billing README. Which ones can I run in parallel?Use manifold-suggest on the tasks in my current .manifold plan before I start executing them in parallel.Are these tasks safe to parallelize? Migrate the users table, add a migration test, and update the API docs for /users.name: manifold-suggest description: Analyze current tasks and suggest parallelization opportunities. Examines task descriptions for file overlap and dependency patterns to recommend safe parallel execution groups. Use when planning multi-task work.
/manifold-suggest
Purpose
Satisfies: RT-4 (Codex hooks via skills), TN1 (skills-as-hooks pattern)
This skill provides auto-suggestion equivalent to Claude Code's auto-suggester hook. Since Codex CLI does not have lifecycle hooks, this skill packages the same functionality as an on-demand capability.
When to Use
- When you have 2+ tasks that might be parallelizable
- Before executing a multi-task plan from
/manifold:m4-generate - When planning implementation of multiple artifacts
Instructions
When the user invokes this skill with a list of tasks (or you detect multiple tasks in the current plan):
-
Parse task descriptions to identify:
- Which files each task is likely to modify
- Dependencies between tasks (e.g., "implement auth" must precede "add auth tests")
- Estimated scope (single file, module, cross-cutting)
-
Detect file overlap between tasks:
- Tasks modifying the same files CANNOT run in parallel
- Tasks in different directories are usually safe to parallelize
- Test files can often run in parallel with implementation
-
Form safe parallel groups:
- Group tasks that have NO file overlap
- Identify sequential dependencies that must be preserved
- Calculate estimated speedup
-
Output a suggestion in this format:
## Parallelization Analysis
### Safe Parallel Groups
- **Group 1**: Task A, Task B (no file overlap)
- **Group 2**: Task C, Task D (independent modules)
### Sequential (must be ordered)
- Task E → Task F (dependency: E creates files F needs)
### Recommendation
<Parallelize / Sequential / Mixed> — Estimated speedup: <n>x
### Warnings
- <any overlap concerns or low-confidence predictions>
Decision Criteria
| Condition | Recommendation | |-----------|---------------| | 2+ tasks, no overlap | Parallelize | | Some overlap, safe groups exist | Mixed (parallel groups + sequential) | | All tasks overlap | Sequential | | Single task | N/A |
If the user hasn't specified tasks, check for a .manifold/ directory and look at
the current phase to suggest what tasks might be parallelizable in the next phase.
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 filesThis 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.mdFrom the root of a test project, save the file as .skill-downloads/parallelization-suggester-mma3jsgg/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/parallelization-suggester-mma3jsgg' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/parallelization-suggester-mma3jsgg/download' --output '.skill-downloads/parallelization-suggester-mma3jsgg/SKILL.md.part' && mv '.skill-downloads/parallelization-suggester-mma3jsgg/SKILL.md.part' '.skill-downloads/parallelization-suggester-mma3jsgg/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/parallelization-suggester-mma3jsgg/SKILL.md' && test -s '.skill-downloads/parallelization-suggester-mma3jsgg/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/manifold-suggest' && cp -R '.skill-downloads/parallelization-suggester-mma3jsgg' '.claude/skills/manifold-suggest'Codex
test -f '.skill-downloads/parallelization-suggester-mma3jsgg/SKILL.md' && test -s '.skill-downloads/parallelization-suggester-mma3jsgg/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/manifold-suggest' && cp -R '.skill-downloads/parallelization-suggester-mma3jsgg' '.agents/skills/manifold-suggest'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 installationopenskills install './.skill-downloads/parallelization-suggester-mma3jsgg'openskills read 'parallelization-suggester-mma3jsgg'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 syncManual 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/parallelization-suggester-mma3jsgg/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.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.