skill-iterative-loop

Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-iterative-loop/SKILL.md

Quality

Content

62%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.

A thorough, highly actionable skill body with excellent workflow sequencing and validation, but it is hampered by significant verbosity from duplicated safety sections and by a monolithic single-file structure that should offload the Metric Verification and Self-Regulation material into reference files.

Suggestions

Remove the 'Safety Mechanisms' section (lines 492-536) — it duplicates Self-Regulation, sliding-window detection, and progress detection already covered in detail above; keep a one-line pointer instead.

Move the Metric Verification Mode (lines 550-689) and Self-Regulation (lines 413-489) into separate reference files under references/ and link to them from SKILL.md, reducing the body to an overview.

Collapse the Common Patterns (197-293), Best Practices (336-394), and Quick Reference table (539-547) into a single section to eliminate overlapping restatements of the same guidance.

Dimension	Reasoning	Score
Conciseness	The ~700-line body is noticeably verbose with duplicated sections: 'Safety Mechanisms' (lines 492-536) restates Self-Regulation, sliding-window, and progress detection already detailed at lines 415-489, and the Quick Reference table plus Common Patterns overlap with Best Practices. It avoids explaining concepts Claude already knows, so it is above level 1, but the padding is more than minor.	2 / 5
Actionability	Provides concrete executable guidance including exact bash commands (mkdir, git add, git commit, git revert HEAD --no-edit), a precise JSONL log schema, config file format, and a step-by-step Metric Verification contract; the standard-loop mode relies on fill-in-the-blank template blocks with placeholders, a minor gap keeping it below level 5.	4 / 5
Workflow Clarity	Multi-step processes are explicitly sequenced (Phase 1/2/3 for the standard loop; Iteration 0 plus Steps 1-9 for Metric mode) with explicit validation checkpoints (Safety Validation checklist, guard commands, metric comparison) and feedback loops (revert on regression, re-validate on failure), matching the level-5 anchor of clear sequences with checklists and error-recovery loops.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and all content is inlined in a single ~700-line SKILL.md; large self-contained sections (Metric Verification Mode, Self-Regulation, Common Patterns) that clearly belong in separate reference files are inline, and the few external paths (codex-host-adapter.md, loop-config.conf) are not signaled as skill-internal references. This is below level 4 because content that should be split out is not.	3 / 5
	Total	14 / 20 Passed

Description

70%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.

A concise, third-person description that clearly conveys both purpose and trigger context with natural keywords. It is held back from the top band by abstract use-case phrasing instead of concrete actions and concrete user trigger sentences.

Dimension	Reasoning	Score
Specificity	Names the domain ('Run tasks in a loop until goals are met') and a few use-patterns ('iterative refinement, polling, or convergence'), but these are abstract use cases rather than concrete executable actions, so it sits at the 'names domain and 1-2 concrete actions, not comprehensive' anchor rather than the multi-action level 4.	3 / 5
Completeness	It states both what ('Run tasks in a loop until goals are met') and when ('use for iterative refinement, polling, or convergence'), satisfying the explicit-trigger requirement so it is not capped at 3; the 'when' lists use cases rather than concrete user phrasings, so it falls at level 4 rather than 5.	4 / 5
Trigger Term Quality	'loop', 'iterative refinement', 'polling', and 'until goals are met' are natural phrases users would say, giving good keyword coverage; a few common variations (e.g. 'retry', 'keep trying until') are absent, keeping it just below the comprehensive level 5.	4 / 5
Distinctiveness Conflict Risk	Iterative-loop execution is a fairly distinct niche with clear triggers, but 'polling'/'refinement' overlap slightly with retry/debug skills, giving minor overlap risk with closely related skills rather than the minimal-risk level 5.	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
skill_md_line_count	SKILL.md is long (700 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: skills/skill-iterative-loop/SKILL.md
Commit: 242e51d

Reviewed: 3 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.