alignment-checkpoint

Create, review, and validate an alignment checkpoint. Use when a request is ambiguous, high-stakes, multi-step, or requires explicit approval before tool use.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Skills/agent-ops/alignment-checkpoint/SKILL.md

Quality

Content

63%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 concise, well-structured instruction skill with a clear gated workflow and validation feedback loops, but its guidance is abstract and its progressive-disclosure signaling is broken: real bundle references go unnamed while a non-existent archived path is cited.

Suggestions

Reference the actual bundle files (contract.yaml, evals.yaml, task-profile.json) by name in the Progressive Disclosure section instead of the non-existent Infrastructure/... archived path.

Add a concrete output template or example alignment-checkpoint artifact so the workflow steps are executable rather than abstract directives.

Remove the verbatim repeat of the frontmatter description at the top of the body to trim the one redundant block.

Dimension	Reasoning	Score
Conciseness	The body is lean, well-structured, and assumes Claude's competence with tight bullets; the only trimmable instance is the verbatim repeat of the frontmatter description at the top of the body, keeping it just below a 5.	4 / 5
Actionability	The Outputs list and Examples give some concrete shape, but the workflow steps are abstract directives ("Inspect 2-3 focused surfaces", "Take the smallest action") with no concrete output template or commands, leaving key execution details missing.	3 / 5
Workflow Clarity	A clear 5-step sequence with explicit validation gates (step 4 stop at first failed gate; step 5 rerun validation after fixes) and a reinforcing Validation section; not a 5 because the steps lack concrete executable detail.	4 / 5
Progressive Disclosure	A Progressive Disclosure section exists and the body is well sectioned, but the actual bundle references (contract.yaml, evals.yaml, task-profile.json) are never mentioned in the body and the signaled archived path does not exist in the bundle, so references are not clearly signaled.	3 / 5
	Total	14 / 20 Passed

Description

83%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 strong, third-person description that answers both what and when with concrete trigger phrases and distinct niche framing. Minor gains are possible from adding a few synonyms or shorthand variants of the trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete actions ("Create, review, and validate an alignment checkpoint"), matching the several-specific-actions anchor; falls short of 5 because coverage of checkpoint sub-tasks is not exhaustive.	4 / 5
Completeness	Clearly states both what (create/review/validate an alignment checkpoint) and when (explicit "Use when a request is ambiguous, high-stakes, multi-step, or requires explicit approval before tool use"), matching the concrete-trigger-phrase anchor.	5 / 5
Trigger Term Quality	"ambiguous, high-stakes, multi-step, requires explicit approval" are natural phrases a user would say, giving good keyword coverage; not a 5 because no synonyms or shorthand variants are included.	4 / 5
Distinctiveness Conflict Risk	The "alignment checkpoint" / approval-gate niche with approval-posture triggers is mostly distinct; not a 5 because it can still overlap with general ask-before-acting behaviors.	4 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Skills/agent-ops/alignment-checkpoint/SKILL.md
Commit: 2f91362

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.