CtrlK
BlogDocsLog inGet started
Tessl Logo

task-orchestrator

Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.

71

Quality

88%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with concrete executable commands, a clear phased workflow, and self-healing feedback loops, but it is a long monolithic file with redundant manifest examples that hurt conciseness and progressive disclosure.

Suggestions

Consolidate the manifest JSON to a single canonical example and reference it elsewhere instead of repeating the full block in Setup, Core Concepts, and the Example section.

Split the large check_progress.sh script and the 'Lessons Learned' retrospective into separate reference files (e.g., scripts/ or references/) so SKILL.md reads as an overview with one-level-deep navigation.

Trim the 'Tips' and 'Integration with Other Skills' sections, which restate guidance already covered in the workflow and core concepts, to reduce token cost.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands, but the full manifest JSON is repeated across three sections and the 'Tips'/'Integration with Other Skills' sections restate earlier content; not a 3 because of this redundancy and length beyond necessity.

2 / 3

Actionability

Provides copy-paste-ready bash (tmux send-keys, gh pr create, git worktree add), a complete check_progress.sh with real grep detection patterns, and concrete manifest schema; not a 2 because the bulk is fully executable rather than pseudocode.

3 / 3

Workflow Clarity

Clear 6-step sequence with explicit phase gates ('Don't start Phase N+1 until Phase N is 100% complete') and self-healing feedback loops (stuck/error/stall detection → retry); not a 2 because validation checkpoints are present for the batch operation.

3 / 3

Progressive Disclosure

No bundle files exist, so the ~400-line skill is a single monolithic file with the example manifest, full check_progress.sh, and 'Lessons Learned' all inline; matches the score-2 anchor where content that should be separate is inline.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that covers concrete capabilities, a natural 'Use for' trigger, and a distinctive niche. It satisfies the what/when requirement without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring' — matching the score-3 anchor for several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (the three capabilities) and when via a clear 'Use for ...' trigger clause, matching the score-3 anchor with explicit triggers.

3 / 3

Trigger Term Quality

The 'Use for large projects with multiple issues/tasks that need coordinated parallel execution' clause uses natural user phrasing a person would actually say; not a 2 because the trigger wording is genuinely natural rather than jargon-only.

3 / 3

Distinctiveness Conflict Risk

The multi-agent tmux/Codex orchestration niche is highly distinctive with trigger terms unlikely to fire for other skills; not a 2 because the scope is unambiguous.

3 / 3

Total

12

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
jdrhyne/agent-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.