skill-contract-reviewer

Validate an Agent Skill package and choose the right instruction, capability, or lifecycle primitive before implementation.

Quality

77%

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 ./phases/13-tools-and-protocols/22-skills-and-agent-sdks/outputs/skill-contract-reviewer/SKILL.md

Quality

Content

100%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 an exemplary lean, executable, well-sequenced skill body with an explicit validation feedback loop and clean one-level-deep file references. It requires no changes.

Dimension	Reasoning	Score
Conciseness	The body is a lean numbered procedure with specific paths and one concrete command, containing no concept over-explanation or padding; every token earns its place.	5 / 5
Actionability	It gives fully executable guidance: explicit env var setup, exact file paths to read, and a copy-paste-ready command 'python3 "$SKILL_ROOT/scripts/check_skill.py" "$TARGET_SKILL"'.	5 / 5
Workflow Clarity	A clear 7-step sequence includes an explicit validation checkpoint (step 6: inspect the JSON report and fix every error before proceeding) with a fix-before-continue feedback loop.	5 / 5
Progressive Disclosure	The body is a concise overview that points to one-level-deep bundle files (references/contract.md, references/decision-model.md, scripts/check_skill.py, assets/task-shapes.json), all of which exist, with no nested reference chains.	5 / 5
	Total	20 / 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 states a clear purpose and niche but is missing an explicit 'Use when...' trigger and leans on technical jargon over natural user phrases. It is competent but not maximally discoverable.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when converting a workflow into a reusable agent skill or before implementing an agent artifact.'

Replace abstract terms ('instruction, capability, or lifecycle primitive') with more natural synonyms a user would say, and name the file types or signals that should prompt the skill (e.g. SKILL.md, references/, scripts/).

List one or two more specific concrete actions to broaden coverage and lift specificity from a 3 toward a 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Agent Skill package') and two concrete actions ('Validate...', 'choose the right instruction, capability, or lifecycle primitive'), but the actions remain somewhat abstract rather than a comprehensive list of specific operations.	3 / 5
Completeness	The 'what' is clear (validate a skill package and select the right primitive), but there is no 'Use when...' clause or equivalent explicit trigger, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Terms like 'Agent Skill package', 'lifecycle primitive', and 'capability' are technical jargon; the description lacks the natural phrases a user would actually say and offers only one or two generic keywords.	2 / 5
Distinctiveness Conflict Risk	'Agent Skill package' and lifecycle primitives carve a fairly specific niche with only minor overlap risk against related skills, though trigger phrases are not fully concrete enough for 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rohitg00/ai-engineering-from-scratch
Path: phases/13-tools-and-protocols/22-skills-and-agent-sdks/outputs/skill-contract-reviewer/SKILL.md
Commit: c02ca08

Reviewed: 4 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.