Name: closed-loop-delivery
Rating: 62.4 (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

74%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/closed-loop-delivery/SKILL.md

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 content is a tight, well-sequenced process skill with explicit validation checkpoints and feedback loops, scoring strongly on workflow clarity and actionability. The main improvement is progressive disclosure: it is a dense single file that could split peripheral policies into reference files.

Suggestions

Move the PR Comment Polling Policy and Human Gate Rules into separate reference files (e.g. references/polling-policy.md, references/human-gates.md) referenced one level deep from the main body, to push progressive_disclosure toward 5.

Add a few copy-paste-ready command skeletons for the most common steps (e.g. a deploy/verify one-liner pattern) to move actionability from concrete guidance to fully executable.

Trim the minor restatements between the Overview 'Core rule' and the Output Contract's 'Do not claim success without evidence' to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is efficient with short bullets and no concept-explanation padding, but a few restatements (the DoD core rule vs. 'Do not claim success without evidence' in the Output Contract) could be trimmed.	4 / 5
Actionability	Concrete, specific guidance throughout — polling windows (3m/6m/10m), defaults (dev, max rounds 2), a concrete DoD example, and explicit escalation/output-contract fields — but no copy-paste-ready commands or scripts, which is the main gap versus a 5.	4 / 5
Workflow Clarity	A clear 6-step numbered sequence with explicit validation checkpoints (verify locally, re-run after fixes, only report done when DoD passes), feedback loops in the review loop and completion steps, and checklists via Required Inputs and the Output Contract; the destructive/batch validation cap does not apply because validation is present.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and no nested references, but at ~107 lines it exceeds the simple-skill 50-line threshold as a monolithic file with no external split; sections like PR Comment Polling Policy or Human Gate Rules could live in separate reference files.	4 / 5
	Total	17 / 20 Passed

Description

67%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 well-structured with a clear 'Use when' trigger and a concrete multi-stage scope, but its trigger-term coverage is moderate rather than comprehensive. Adding common synonyms and a sharper trigger would lift the weaker dimensions.

Suggestions

Add common trigger synonyms users actually say, e.g. 'Use when the user wants a task fully shipped end-to-end, closed-loop, or to definition of done (DoD) without being prompted to test/deploy/re-check.'

Make the 'when' more explicit with multiple concrete trigger phrases (e.g. 'when the user says ship it, close the loop, or asks to verify against acceptance criteria').

List the discrete concrete actions more crisply (e.g. 'implements, runs tests, addresses PR review comments, deploys to dev, and verifies runtime behavior') to push specificity toward a clean 5.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete stages — 'implementation, review feedback, deployment, and runtime verification' — but describes the scope of completion rather than a clean list of discrete actions, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (end-to-end completion across impl/review/deploy/verify) and 'when' (the 'Use when' clause), though the 'when' is a single condition rather than multiple concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes a natural trigger ('Use when a coding task must be completed against explicit acceptance criteria') but misses common synonyms a user might say such as 'definition of done', 'ship it', or 'close the loop'.	3 / 5
Distinctiveness Conflict Risk	'minimal user re-intervention across implementation, review feedback, deployment, and runtime verification' carves a distinct closed-loop-delivery niche with only minor overlap risk against generic delivery skills.	4 / 5
	Total	15 / 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-claude/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.