loop-constraints

Read loop-constraints.md at the start of every run and enforce every rule. This skill runs BEFORE triage or any action skill. Constraints are binding.

Quality

62%

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/loop-constraints/SKILL.md

Quality

Content

78%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 well-structured, actionable guardrail skill with clear sequencing and appropriate escalation checkpoints. The main improvement is consolidating the repetitive 're-read section' enforcement template and inlining a few key rules so guidance does not depend entirely on an external file.

Suggestions

Consolidate the repeated 'Before X: re-read Y section' bullets into a single concise enforcement table to trim template redundancy.

Inline the most critical default rules (denylist paths, no auto-merge) into the enforce steps so core guidance is self-contained.

Add an explicit post-load validation checkpoint, e.g. 'After loading, confirm each rule is parseable before proceeding.'

Dimension	Reasoning	Score
Conciseness	The body is lean with short imperative lists and no padding about what constraints are, but the four-fold repeated 'Before X: re-read Y section' template is slightly heavier than necessary, keeping it just below a 5.	4 / 5
Actionability	Guidance is concrete (denylist paths, 'Human must approve', 'One fix per run', an exact output line), but the actual rule content is deferred to loop-constraints.md so execution still depends on an external file, leaving minor gaps.	4 / 5
Workflow Clarity	A clear numbered startup sequence and per-action checkpoints (stop and tell the human, escalate, human approval, escalate-after-3) are present, with only minor validation gaps such as no explicit validate-after-load step.	4 / 5
Progressive Disclosure	As a simple, single-purpose skill under 50 lines with no external documentation references, it is well organized into clear sections and is appropriately self-contained, meeting the simple-skill exception for a 5.	5 / 5
	Total	17 / 20 Passed

Description

46%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 communicates a distinct, well-scoped purpose and clear sequencing, but relies on project jargon rather than natural trigger terms and omits an explicit 'Use when...' clause. Tightening trigger phrasing would lift the completeness and trigger_term_quality dimensions.

Suggestions

Add an explicit trigger clause such as 'Use when a loop run is starting, before triage or any action skill executes.'

Replace or supplement jargon ('loop-constraints', 'triage') with natural user-facing phrasing users would actually say.

List 1-2 more concrete enforcement actions (e.g., 'blocks pushes, edits, and merges that violate a rule') to broaden specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (loop-constraints enforcement) and concrete actions ('Read loop-constraints.md', 'enforce every rule', 'runs BEFORE triage'), but coverage is narrow rather than comprehensive, matching the score-3 anchor.	3 / 5
Completeness	It has a clear 'what' (enforce every rule) and timing-based 'when' ('at the start of every run', 'BEFORE triage'), but lacks an explicit user-facing trigger clause, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Keywords are project-specific jargon ('loop-constraints', 'triage', 'constraints') rather than natural phrases a user would say, and no 'Use when...' guidance is present, placing it noticeably below the midpoint.	2 / 5
Distinctiveness Conflict Risk	It carves a clear niche (guardrail running before triage/action skills) with minimal conflict risk, though it conceptually overlaps with sibling loop-* skills, keeping it just below a 5.	4 / 5
	Total	12 / 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: cobusgreyling/loop-engineering
Path: skills/loop-constraints/SKILL.md
Commit: 0dc0f3f

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.