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

75%

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

100%

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

The body is a tight, well-structured enforcement skill: concise, concrete, with a clear sequenced workflow and explicit validation/escalation checkpoints. No bundle files exist, and the simple, organized content fully satisfies progressive disclosure for a skill of this size.

Dimension	Reasoning	Score
Conciseness	The body is lean and instructive throughout, with no concept-explaining fluff and every section earning its tokens (numbered MUST steps, a one-line output template, a concrete default denylist). It is not a 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	It gives concrete, executable guidance: specific re-read triggers ('Before pushing: re-read the Push & Merge section'), a copy-ready output line, and exact denylist paths ('.env', '.env.*', 'auth/', 'payments/', 'secrets/'). As an instruction-only skill this is fully actionable, not a 2 with vague or pseudocode guidance.	3 / 3
Workflow Clarity	It provides a clear numbered sequence (1-4 MUST steps) plus explicit validation checkpoints and feedback loops ('If ANY rule blocks it, stop', 'Human must approve', 'Escalate after 3 failed fix attempts'). It is above a 2 because checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	No bundle files exist in references/scripts/assets, and the body is under 50 lines with well-organized sections (enforcement, output, interactions, defaults). Per the rubric's simple-skill guidance, this scores 3 on well-organized sections alone; the only referenced files (loop-constraints.md, docs/safety.md) are runtime data, not nested bundle references.	3 / 3
	Total	12 / 12 Passed

Description

50%

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 the skill's purpose and ordering constraint clearly but relies on internal jargon and omits an explicit user-invocation trigger, so it lands in the middle of the scale across all dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use at the start of every loop run before triage or any action skill') to lift completeness to 3.

Replace internal jargon with natural user-facing terms so trigger_term_quality reflects what a user would actually say.

List 2-3 concrete enforcement actions (e.g., 'block pushes, deny edits to secret paths, require human merge approval') to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and a few concrete actions ('Read loop-constraints.md', 'enforce every rule', 'runs BEFORE triage or any action skill'), but does not enumerate multiple distinct concrete capabilities. It is above a 1 (not vague like 'Helps with documents') but below a 3, which requires a list of multiple specific concrete actions.	2 / 3
Completeness	It states what the skill does and gives an implied when ('at the start of every run', 'BEFORE triage or any action skill'), but lacks an explicit 'Use when...' trigger clause. Per the rubric, a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant skill-ecosystem terms ('loop-constraints', 'triage', 'action skill', 'binding') but leans on internal jargon rather than natural phrases a user would spontaneously say. Above a 1 because some keywords are relevant, but below a 3 due to missing common user-facing variations.	2 / 3
Distinctiveness Conflict Risk	The enforcer-before-other-skills niche is somewhat specific, but it overlaps with the triage/budget/verifier skills it references and the 'enforce every rule' framing is generic. Distinctive enough to avoid a 1, but could still overlap with similar skills.	2 / 3
	Total	8 / 12 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: ffa5bf8

Reviewed: 1 day 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.