agentleFS
jasonmichaelbell78-creatorjasonmichaelbell78-creator/sonash-v0/.claude/skills/task-next/SKILL.md

task-next

Skill2 starsChanged 9 months agoApache-2.0View on GitHub

Show dependency-resolved next tasks from ROADMAP.md active sprint

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the task doesn't match this skill's scope -- check related skills

    line 17
  2. Distinctive:

    When a more specialized skill exists for the specific task

    line 18
  3. Distinctive:

    If the user wants to work on a task:

    line 60
  4. Distinctive:

    When a task is done:

    line 68
  5. Very specific:

    Check off the item in ROADMAP.md (- [ ] -> - [x])

    line 70
  6. Very specific:

    Add [depends: X1, X2] to any task item in ROADMAP.md:

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Task Next - Dependency-Aware Task Selection

Shows which tasks are ready to work on based on dependency resolution.

When to Use

  • Tasks related to task-next
  • User explicitly invokes /task-next

When NOT to Use

  • When the task doesn't match this skill's scope -- check related skills
  • When a more specialized skill exists for the specific task

Usage

/task-next              # Show ready (unblocked) tasks
/task-next --all        # Show ready, blocked, and completed
/task-next --blocked    # Show only blocked tasks

How It Works

  1. Reads ROADMAP.md and finds all task items (- [ ] **ID:** Description)
  2. Parses [depends: X1, X2] annotations on each task
  3. Builds a directed acyclic graph (DAG) of dependencies
  4. Runs Kahn's topological sort to determine execution order
  5. Reports which tasks are ready (all dependencies completed) vs blocked

Steps

1. Run the dependency resolver

node scripts/tasks/resolve-dependencies.js

2. Present results to the user

Format the output clearly:

Ready tasks — these can be started now:

  • List each with its ID, description, and satisfied dependencies
  • Suggest the highest-priority one based on track ordering

Blocked tasks — these are waiting on other tasks:

  • List each with what it's waiting for
  • Highlight if a blocker is close to completion

3. Help the user pick

If the user wants to work on a task:

  1. Confirm the task ID
  2. Mark it as the active task in TodoWrite
  3. Begin implementation

4. After completing a task

When a task is done:

  1. Check off the item in ROADMAP.md (- [ ] -> - [x])
  2. Re-run the resolver to see what's newly unblocked
  3. Tell the user what tasks are now available

Dependency Annotation Format

Add [depends: X1, X2] to any task item in ROADMAP.md:

- [ ] **B3:** Lighthouse CI Integration [depends: B1, B2]
- [ ] **B5:** Lighthouse Dashboard Tab [depends: B3, B4]

Rules:

  • Dependencies reference task IDs (B1, B3, CANON-0011, DEBT-0944, etc.)
  • Multiple dependencies separated by commas
  • Annotation must be in square brackets at the end of the line
  • Tasks without [depends:] are considered independent (always ready)
  • Circular dependencies are detected and reported as errors

Version History

VersionDateDescription
1.02026-02-25Initial implementation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.