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

46%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/closed-loop-delivery/SKILL.md

Quality

Content

63%Scale 1-5

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

This is a well-structured process/workflow skill that clearly defines a closed-loop delivery methodology with good iteration controls, human gates, and output contracts. Its main weakness is the lack of concrete executable examples (commands, code snippets, tool invocations) that would make the guidance immediately actionable rather than procedural. The reference to 'create-issue-gate' without a link or bundle file is a minor but notable gap in progressive disclosure.

Suggestions

Add concrete executable examples for key steps — e.g., specific CLI commands for fetching PR comments, running tests, deploying to dev, and checking runtime evidence.

Link or define the 'create-issue-gate' reference — either provide the referenced skill/tool as a bundle file or inline a brief description of what it is and how to invoke it.

Consider extracting the PR Comment Polling Policy and Human Gate Rules into separate referenced files to keep the main SKILL.md as a leaner overview.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and avoids explaining concepts Claude already knows. Minor verbosity in the 'When to Use' / 'Do not use' sections and the PR Comment Polling Policy could be tightened slightly, but overall each section earns its place.	4 / 5
Actionability	The skill provides a clear process-oriented framework with concrete policies (polling windows, iteration limits, escalation reports), but lacks executable code examples, specific commands, or copy-paste ready snippets. The guidance is structural/procedural rather than directly executable, which is appropriate for a workflow skill but still leaves gaps in specificity (e.g., how to 'fetch PR comments', how to 'deploy to dev').	3 / 5
Workflow Clarity	The workflow is clearly sequenced with six numbered steps, explicit stop conditions, human gate rules, and an iteration cap. There are validation checkpoints (local verification, runtime verification against DoD, completion decision). Minor gap: the feedback loop between steps 4-6 could be more explicitly diagrammed, and the relationship between the Issue Gate Dependency and the main workflow entry could be clearer.	4 / 5
Progressive Disclosure	The content is well-structured with clear section headers and logical organization. However, there are no bundle files and no references to external files. The PR Comment Polling Policy and Human Gate Rules sections could potentially be split into separate reference files for a cleaner overview. The reference to 'create-issue-gate' is not linked or explained, creating a navigation gap.	3 / 5
	Total	14 / 20 Passed

Description

28%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.

This description is almost entirely a trigger condition ('Use when...') without explaining what the skill actually does. It uses abstract process terminology rather than concrete actions or natural user language. The description would benefit greatly from stating specific capabilities and including terms users would naturally use.

Suggestions

Add a concrete 'what' clause before the 'Use when' that describes specific actions (e.g., 'Implements code changes, iterates on review feedback, deploys, and verifies runtime behavior in an autonomous workflow.')

Replace abstract jargon like 'minimal user re-intervention' with natural trigger terms users would say, such as 'end-to-end', 'autonomous coding', 'hands-off implementation', or 'auto-complete task'

Include specific examples of what 'acceptance criteria' means in practice to distinguish this from other coding skills (e.g., 'test-driven development', 'spec-based implementation', 'automated verification')

Dimension	Reasoning	Score
Specificity	Names a broad domain ('coding task') and mentions phases (implementation, review feedback, deployment, runtime verification) but these are abstract process stages rather than concrete actions. No specific capabilities like 'writes code', 'runs tests', 'deploys to server' are stated.	2 / 5
Completeness	Has a 'when' clause but the 'what' is essentially missing - it only says 'a coding task must be completed' without describing what the skill actually does. The description is almost entirely a 'when' statement with no concrete 'what'.	2 / 5
Trigger Term Quality	Contains some relevant terms like 'acceptance criteria', 'deployment', and 'runtime verification', but these are more process/methodology jargon than natural user phrases. Users are unlikely to say 'explicit acceptance criteria with minimal user re-intervention'.	2 / 5
Distinctiveness Conflict Risk	The emphasis on 'acceptance criteria', 'minimal user re-intervention', and the full lifecycle (implementation through runtime verification) provides some distinctiveness from simple coding skills, but 'coding task' is very broad and could overlap with many development-related skills.	3 / 5
	Total	9 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: 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.