improve-loop

Systematically review and improve every shell feature and builtin command. Iterates through each feature/command, runs code-review, fixes issues, and re-reviews until clean.

1.56x

Quality

43%

Does it follow best practices?

Impact

91%

1.56x

Average score across 3 eval scenarios

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/improve-loop/SKILL.md

Quality

Content

55%Scale 1-3

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

This skill excels at actionability and workflow clarity — it provides precise, executable commands and a rigorously sequenced multi-step process with proper validation gates and feedback loops. However, it is severely undermined by its extreme verbosity (~500+ lines in a single file) and complete lack of progressive disclosure. The review dimensions, agent instructions, and pentest checklists should be extracted into separate reference files, with the main SKILL.md serving as a concise orchestration overview.

Suggestions

Extract the detailed review dimensions (A through K) and pentest checks into a separate REVIEW_DIMENSIONS.md file, referencing it from the main skill with a one-line pointer.

Extract the agent launch instructions and output format into a separate AGENT_INSTRUCTIONS.md file that agents can be pointed to.

Remove explanatory text that Claude already knows (e.g., what exit codes mean, how gofmt works, what streaming vs buffering means) — keep only the project-specific constraints.

Consolidate the PR comment templates into a separate TEMPLATES.md file or reduce them to minimal format specifications rather than full heredoc examples.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~500+ lines. It over-explains execution protocols, repeats gating checks, includes extensive boilerplate for PR comments, and provides exhaustive review checklists that could be split into reference files. Many sections explain things Claude already knows (how to run bash commands, what exit codes mean, basic Go testing patterns).	1 / 3
Actionability	The skill provides fully executable bash commands, specific file paths, concrete code examples, exact commit message formats, and detailed review dimensions with specific checks. Every step has copy-paste ready commands and clear expected outputs.	3 / 3
Workflow Clarity	The workflow is exceptionally well-sequenced with explicit gate checks between steps, a clear loop structure (2A→2G), validation checkpoints (run tests after every fix, re-run on failure with max 3 attempts), and explicit decision tables for loop continuation. Feedback loops for error recovery are clearly defined.	3 / 3
Progressive Disclosure	The entire skill is a monolithic wall of text with no references to external files for detailed content. The extensive review dimensions (A through K), pentest checks, and agent instructions should be split into separate reference files. No bundle files are provided despite the content clearly needing decomposition into multiple documents.	1 / 3
	Total	8 / 12 Passed

Description

32%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 conveys a general sense of the skill's purpose — iterative code review of shell builtins — but lacks explicit trigger guidance ('Use when...'), concrete action details, and natural keyword variations. It would benefit from specifying when Claude should select this skill and listing more specific actions and file/technology triggers.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to audit, review, or improve shell builtin implementations or shell feature code.'

Include natural trigger terms and variations such as 'bash', 'zsh', 'shell script', 'builtin', 'lint shell code', 'audit shell features'.

Make the actions more concrete — specify what 'fixes issues' means (e.g., 'fixes error handling, POSIX compliance issues, edge cases in argument parsing').

Dimension	Reasoning	Score
Specificity	Names the domain (shell features and builtin commands) and describes a process (iterate, run code-review, fix issues, re-review), but the actions are somewhat generic — 'fixes issues' and 'runs code-review' lack concrete detail about what kinds of issues or what the review entails.	2 / 3
Completeness	Describes what it does (review and improve shell features/builtins) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2 — and since the 'what' is also somewhat vague, this falls to 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'shell', 'builtin command', 'code-review', but misses common user-facing variations (e.g., 'bash', 'zsh', 'shell script', 'lint', 'audit'). The phrase 'systematically review' is somewhat natural but not a strong trigger term.	2 / 3
Distinctiveness Conflict Risk	The focus on shell builtins specifically is somewhat distinctive, but 'code-review' and 'fixes issues' are generic enough to overlap with general code review or linting skills. The niche is partially defined but not sharply delineated.	2 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (552 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: DataDog/rshell
Path: .claude/skills/improve-loop/SKILL.md
Commit: 7518a70

Reviewed: 6 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.