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 body is a tight, well-structured guardrail skill with concrete per-action checkpoints, validation gates, and sensible fallback defaults; its main limitation is gate-based rather than retry-loop feedback for destructive operations.

Dimension	Reasoning	Score
Conciseness	The body is lean and instruction-focused with no padding or explanations of concepts Claude already knows; the only minor trim opportunity is the repeated "re-read the X section" pattern across the four enforcement bullets, keeping it just below a 5.	4 / 5
Actionability	Guidance is concrete and actionable for an instruction-only skill — specific file paths, a denylist (.env, auth/, payments/, secrets/, credentials/), an exact output line, and per-action gate conditions; minor gaps remain in the abstract "Apply these rules to EVERY action" step.	4 / 5
Workflow Clarity	A clear numbered setup sequence (read, load, check pause flag, apply) is paired with per-action checkpoints that include validation ("If ANY rule blocks it, stop", "Human must approve", escalate on denylist match); it stops short of 5 because the feedback is gate-based rather than an explicit validate-fix-retry loop.	4 / 5
Progressive Disclosure	At ~40 lines with a single purpose and well-organized sections (How to enforce, Output, Interaction, Default constraints), it fits the simple-skill exception; its only external references (loop-constraints.md, docs/safety.md) are clearly signaled one level deep with a documented fallback.	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 clearly states what the skill does and anchors it in a specific loop-runner ecosystem, but it lacks natural user-facing trigger terms and an explicit "Use when..." clause, relying on run-ordering instead of trigger conditions.

Suggestions

Add an explicit "Use when..." clause naming the user situations that should trigger this skill (e.g., 'Use at the start of every loop run before triage or any action skill').

Replace internal jargon ("triage", "action skill", "binding") with natural trigger terms a user would actually say, such as "loop run", "guardrails", or "safety rules".

Spell out the concrete enforcement actions (read, check pause flag, apply per-action) instead of the generic "enforce every rule".

Dimension	Reasoning	Score
Specificity	It names the domain and one concrete action ("Read loop-constraints.md at the start of every run") plus a generic "enforce every rule", matching the anchor for 1-2 concrete actions that are not comprehensive; the second action is too generic to push it to 4.	3 / 5
Completeness	It gives a clear "what" (read and enforce the constraints file) but the only "when" is run ordering ("at the start of every run", "runs BEFORE triage"), not an explicit user trigger; per the guideline, a missing "Use when..." clause caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords are system jargon ("loop-constraints.md", "triage", "action skill", "binding") rather than natural phrases a user would say; there is no "Use when..." trigger language, fitting the anchor for one or two generic/technical keywords missing the natural phrases users say.	2 / 5
Distinctiveness Conflict Risk	It carves a clear niche as the constraint-enforcing guardrail within a named loop ecosystem and references specific sibling skills, giving it mostly distinct triggers with only minor overlap risk against closely related safety skills.	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: 804a4e9

Reviewed: about 13 hours 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.