Tessl • The package manager for agent skills

SkillPublic

icpg

Intent-Augmented Code Property Graph — tracks WHY code exists via ReasonNodes with formal contracts, 6-dimension drift detection, and 3 canonical pre-task queries for autonomous development

Quality

66%

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/icpg/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.

The content is actionable and well-sequenced with concrete CLI commands and validation checkpoints, but it is a monolithic wall of text with no bundle files to offload detail, and some sections could be tightened.

Suggestions

Move the full CLI reference, hook-integration JSON, and agent-teams pipeline into separate reference files under references/ and link to them one level deep, turning SKILL.md into a lean overview.

Trim the agent-teams pipeline section, which largely restates the earlier 'Before Any Code Change' workflow.

Add a single end-to-end worked example (create intent → record symbols → drift check) to close the minor actionability gap.

Dimension	Reasoning	Score
Conciseness	The ~320-line body is mostly dense reference material and assumes Claude's intelligence (it does not belabor what SQLite/AST/CFG are), but sections like the agent-teams pipeline restate the earlier workflow and some tables could be trimmed, matching the 'mostly efficient but could be tightened' anchor 3 rather than 4.	3 / 5
Actionability	It provides concrete, copy-paste-ready CLI commands ('icpg init', 'icpg query prior "<goal>"'), JSON hook configs, and example outputs covering common cases — mostly executable with only minor gaps, fitting anchor 4; not 5 because no single end-to-end create→record→drift example ties them together.	4 / 5
Workflow Clarity	The 'Before Any Code Change' workflow is an explicit 8-step numbered sequence with validation checkpoints (DRIFT CHECK, VERIFY) and a feedback notion ('resolve or create new intents'), matching anchor 4; not 5 because error-recovery detail for failed drift checks is brief.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets directories are absent), so the body is a monolithic single file with clear section headers but content that could live in separate files (full CLI reference, agent-teams integration, hook configs) is inlined, fitting anchor 3; in-path references like './scripts/icpg' point to nonexistent files.	3 / 5
	Total	14 / 20 Passed

Description

55%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 is specific and clearly distinct, but it is heavy on internal jargon and omits an explicit 'Use when' trigger clause, which caps its completeness and hurts trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use before modifying code, when checking for duplicate prior work, or when investigating why a function exists').

Replace or pair technical terms ('ReasonNodes', 'Code Property Graph') with plain-language keywords users would actually say, such as 'intent tracking', 'code drift', or 'why was this code written'.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities — 'ReasonNodes with formal contracts', '6-dimension drift detection', '3 canonical pre-task queries' — listing multiple specific actions with only minor coverage gaps, matching the anchor for score 4 rather than 5 which requires more comprehensive enumerated actions.	4 / 5
Completeness	It gives a clear 'what' (tracks WHY code exists via ReasonNodes...) but the description field itself contains no 'Use when...' trigger clause, and the rubric caps completeness at 3 when explicit trigger guidance is missing; the separate when-to-use field is not part of the evaluated target.	3 / 5
Trigger Term Quality	The description leans on technical jargon ('ReasonNodes', 'Code Property Graph', 'formal contracts', '6-dimension drift detection') with only a couple of generic keywords and is missing the natural phrases a user would actually say, fitting anchor 2; it is not score 1 because it does name a recognizable domain.	2 / 5
Distinctiveness Conflict Risk	'Intent-Augmented Code Property Graph' occupies a clear, narrow niche with distinct triggers and minimal conflict risk with other skills, matching the score 5 anchor; voice is appropriately third person.	5 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: alinaqi/maggy
Path: skills/icpg/SKILL.md
Revision: 55aabe2

Reviewed: 20 days ago

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.

icpg

Table of Contents

Is this your skill?