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.

62

Quality

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

65%

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

The content is highly actionable with concrete executable commands and scripts, but it is verbose with redundant repeated sections and bundles everything inline rather than progressively disclosing detail into reference files. The destructive push/PR step also lacks an explicit validation gate despite a safety boundary forbidding self-pushing.

Suggestions

Extract the full check_progress.sh script and the example manifests into reference files (e.g. references/check_progress.sh, references/manifest-example.json) and link to them from a lean overview, removing the duplicated manifest and launch blocks.

Reconcile the Safety Boundaries with Step 5: either add an explicit human-review validation gate before pushing/creating PRs, or clarify when autonomous pushing is permitted.

Collapse the redundant dependency/phase explanations (Core Concepts, Setup, Workflow, Example) into a single canonical section to reduce token cost.

DimensionReasoningScore

Conciseness

The ~400-line body is mostly actionable but repeats the manifest JSON, Codex launch incantation, and phase logic across Core Concepts, Setup, and Workflow sections, and restates dependency concepts Claude already knows; it could be tightened without losing clarity.

2 / 3

Actionability

Provides fully executable bash (tmux, git worktree, gh, codex), a complete check_progress.sh script, full manifest JSON, and copy-paste-ready PR creation — concrete and specific throughout.

3 / 3

Workflow Clarity

The Steps 1-6 sequence and self-healing feedback loops are clear, but the destructive push/PR step (Step 5) lacks an explicit validation gate and contradicts the Safety Boundaries ('Do not push branches, merge work'), leaving a checkpoint gap for a batch/destructive operation.

2 / 3

Progressive Disclosure

No bundle files exist and all content — full scripts, example manifests, status tables — lives inline in a single ~400-line SKILL.md; material that should be split into separate reference files is embedded rather than organized one level deep.

2 / 3

Total

9

/

12

Passed

Description

85%

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

The description is specific and complete with an explicit 'Use for' trigger, and occupies a distinctive niche. Its main weakness is trigger-term naturalness, which leans technical rather than reflecting how users actually phrase the need.

Suggestions

Add user-natural trigger phrasings alongside the technical ones, e.g. 'Use when the user has many open issues or a backlog of tasks to work in parallel.'

Soften jargon like 'coordinated parallel execution' and 'self-healing heartbeat monitoring' in the trigger clause to mirror real user requests.

DimensionReasoningScore

Specificity

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

3 / 3

Completeness

Explicitly answers both what it does (the orchestration capabilities) and when to use it via an explicit 'Use for large projects with multiple issues/tasks...' trigger clause.

3 / 3

Trigger Term Quality

The trigger 'large projects with multiple issues/tasks that need coordinated parallel execution' includes some relevant keywords but leans on technical phrasing ('coordinated parallel execution', 'multi-agent task orchestration') and omits common natural variations a user might say.

2 / 3

Distinctiveness Conflict Risk

The distinctive combination of tmux/Codex parallel execution with self-healing heartbeat monitoring carves a clear niche unlikely to trigger for the wrong skill.

3 / 3

Total

11

/

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.