Name: arn-code-execute-task
Rating: 68.8 (1 reviews)
Author: AppsVortex

arn-code-execute-task

This skill should be used when the user says "execute task N", "run task N", "implement task N", "re-run task N", "retry task N", "run single task", or wants to execute a single specific task from the task list with optional review. This is for ONE task only — for executing the full plan (all tasks), use arn-code-execute-plan instead.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

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

The content is a well-sequenced, highly actionable orchestration workflow with explicit checkpoints and feedback loops. Its weaknesses are token efficiency (some repetition and prose to tighten) and progressive disclosure (a monolithic file with no bundle, despite sizable branching logic that could be externalized).

Suggestions

De-duplicate the Layer 1 visual-config note (currently restated across Steps 4, 5, and 6) into a single defined location referenced by each step to improve conciseness.

Extract the multi-branch error-handling section and the PROGRESS_TRACKER update logic into a referenced file (e.g. references/error-handling.md) to move from monolithic to one-level-deep progressive disclosure.

Tighten prose in Step 1 config extraction and Step 4 model-override logic into tighter bullet/checklist form to reduce token overhead while preserving the actionable detail.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely procedural-earn-its-place, but ~150 lines include repeated notes (e.g., Layer 1 visual config restated across Step 4, Step 5, and Step 6) and some prose that could be tightened, landing at mostly efficient rather than lean.	2 / 3
Actionability	Concrete, copy-paste-ready guidance throughout: exact project paths, literal Task-tool parameters and model-override logic, verbatim AskUserQuestion prompts with numbered options, and specific TaskUpdate/PROGRESS_TRACKER field operations, plus inline pointers to real reference docs.	3 / 3
Workflow Clarity	A clearly sequenced Step 1–6 pipeline with explicit validation checkpoints (verify task exists, verify project dir exists, warn when blocked) and well-defined feedback loops (max 2 review cycles, then escalate) for the risky review/execution operations.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), and the body is a single monolithic file whose error-handling branches and config-extraction detail could reasonably be split into referenced files; sections are well-organized and external references are signaled inline, but content that should be separate is inline.	2 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 strong: explicit, natural trigger phrases; clear what-and-when; and explicit disambiguation from the related full-plan skill. It uses appropriate third-person voice throughout. The only mild gap is capability specificity, which lists the domain and review option rather than several distinct concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and the core actions ("execute a single specific task from the task list with optional review"), but does not enumerate multiple distinct concrete actions, so it falls short of the comprehensive 3-anchor.	2 / 3
Completeness	Explicitly answers both what ("execute a single specific task… with optional review") and when ("should be used when the user says…"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural user phrasings broadly — "execute task N", "run task N", "implement task N", "re-run task N", "retry task N", "run single task" — matching the good coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Clear single-task niche plus explicit disambiguation from the sibling plan skill ("for executing the full plan… use arn-code-execute-plan instead"), making wrong-skill triggering unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: AppsVortex/arness
Path: plugins/arn-code/skills/arn-code-execute-task/SKILL.md
Commit: 7f87870

Reviewed: 14 days ago

Table of Contents

Discovery Implementation Validation

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.