Name: closed-loop-delivery
Rating: 68 (1 reviews)
Author: administrakt0r

closed-loop-delivery

Use when a coding task must be completed against explicit acceptance criteria with minimal user re-intervention across implementation, review feedback, deployment, and runtime verification.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is closed-loop-delivery in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

81%Weight 40%Scale 1-5

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

The body is a well-structured, actionable process skill with strong sequencing, validation checkpoints, and feedback loops, and it avoids over-explaining concepts Claude already knows. The main room for improvement is splitting some detail sections into one-level-deep reference files.

Suggestions

Move the PR Comment Polling Policy and Iteration/Stop Conditions detail into a one-level-deep reference file (e.g. references/polling-policy.md) and link to it from the body, keeping the main flow under ~50 lines.

Add a few literal commands or a minimal example block for the verify/deploy steps so the guidance is copy-paste ready rather than purely descriptive.

Tighten the polling-policy prose into a compact table (round | wait | action) to trim tokens further.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's intelligence (no padding about what CI, deploys, or PRs are), with only minor phrasing that could be tightened (e.g. the polling-policy prose), so it sits above the midpoint but not at fully lean.	4 / 5
Actionability	Provides concrete, executable guidance — specific polling windows (3m/6m/10m), defaults (max 2 rounds, dev environment), a numbered workflow, and an output checklist — but, as an instruction-only skill, offers no literal commands, leaving minor gaps versus copy-paste-ready instruction.	4 / 5
Workflow Clarity	A clear 6-step sequenced workflow with explicit validation checkpoints ('Verify locally', 'Only report done when all DoD checks pass'), a fix→re-verify feedback loop in the review step, and stop/escalation conditions, matching the anchor for explicit validation plus feedback loops.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and no nested references, and no bundle files exist to mis-signal; at ~108 lines it exceeds the under-50-line simple-skill exception, and a few sections (e.g. PR Comment Polling Policy) could live in a reference, so it is good but not perfectly split.	4 / 5
	Total	17 / 20 Passed

Description

83%Weight 40%Scale 1-5

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: third-person voice, explicit 'Use when' trigger, concrete scope across the delivery lifecycle, and a distinct closed-loop framing. It is held below a perfect score by slightly abstract action language and missing natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates several concrete phases ('implementation, review feedback, deployment, and runtime verification') with only minor coverage gaps; it does not catalog the exact actions the skill performs (verify, deploy, check), so it stops short of a 5.	4 / 5
Completeness	Explicitly answers both 'what' (complete against acceptance criteria across implementation, review, deployment, runtime verification) and 'when' via a concrete 'Use when a coding task must be completed...' trigger phrase, matching the anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	Includes several natural terms a user might say ('coding task', 'acceptance criteria', 'deployment', 'review feedback') but misses common synonyms a user would naturally voice ('end-to-end', 'definition of done', 'verify'), so it is good but not comprehensive.	4 / 5
Distinctiveness Conflict Risk	The end-to-end DoD-verified delivery framing is a clear niche with distinct triggers, but 'coding task' is broad enough to risk minor overlap with general development skills, placing it just below the minimal-conflict anchor.	4 / 5
	Total	17 / 20 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/closed-loop-delivery/SKILL.md
Commit: 57c135b

Reviewed: 2 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.