Tessl • The package manager for agent skills

The body delivers strongly on workflow clarity and actionability — the TDD pipeline, blocking conditions, and worked example are exemplary. Its weaknesses are token efficiency (rules stated three times, basics Claude already knows, redundant per-stack command blocks) and structure (a monolithic file whose external references point to files that don't exist in this bundle).

Suggestions

State each simplicity limit once and cross-reference it (drop the Anti-Patterns entries and Enforcement Protocol steps that merely restate the 20-line/3-param/200-line rules), and trim anti-patterns Claude already knows (global state, dead code, premature optimization).

Collapse the Node/Python/React command blocks into one generic pattern with a small stack-to-command table — the RED and GREEN commands are currently identical strings, and Claude can derive the per-stack variants.

Move the bulky templates (todo format, bug report format, documentation tree) into reference files in the bundle and fix or remove the dangling references to credentials.md, security.md, and session-management.md so each 'See X' resolves to a real file.

Dimension	Reasoning	Score
Conciseness	The simplicity limits are stated three times (Simplicity Rules, Enforcement Protocol, Anti-Patterns), the Anti-Patterns section restates basics Claude already knows ("❌ Global state", "❌ Dead code", "❌ Premature optimization"), and the three per-stack command blocks repeat the identical RED and GREEN command — several padded/duplicative sections beyond the 'could be tightened' level.	2 / 5
Actionability	Guidance is mostly executable — exact per-stack commands (e.g. "ruff check . && mypy . && pytest --cov --cov-fail-under=80"), a fully worked example todo, and concrete key patterns — but "See credentials.md", "See security.md", and "See session-management.md" point to files absent from the bundle, and a few directives are abstract ("Design APIs where misuse is impossible").	4 / 5
Workflow Clarity	The TDD and bug-fix workflows are explicitly sequenced (RED → GREEN → VALIDATE → PROVE/COMPLETE) with hard validation gates, blocking conditions, and a BLOCKED feedback template for error recovery — a clear match for the top anchor with explicit validation steps and feedback loops.	5 / 5
Progressive Disclosure	Section structure is good, but this is a monolithic ~530-line SKILL.md with no bundle files, and its references (credentials.md, security.md, session-management.md, iterative-development) do not resolve to anything in the bundle, while template-heavy content (todo format, three stack command sets) is inlined rather than split out.	3 / 5
	Total	14 / 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 names its domain and a few concrete topics but reads as a noun-phrase tag list rather than an action statement, and it entirely lacks a 'when to use' trigger clause. Its breadth ('Universal', 'all projects') creates high conflict risk with other coding skills. It is serviceable but below the bar set by the good examples.

Suggestions

Rewrite in third-person action voice listing concrete capabilities, e.g. "Enforces simplicity limits (20-line functions, 200-line files), runs the TDD RED/GREEN/VALIDATE workflow, tracks work as atomic todos, and manages session state."

Add an explicit 'Use when...' clause with natural trigger phrases, e.g. "Use when writing or refactoring code, fixing bugs, planning todos, or resuming a work session."

Narrow the scope claim so it is distinguishable from other coding skills — 'Universal ... for all projects' will match nearly any coding request and starve more specific skills of triggers.

Dimension	Reasoning	Score
Specificity	"Universal coding patterns, constraints, TDD workflow, atomic todos" names the domain plus concrete topics (TDD workflow, atomic todos) but contains no action verbs, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor rather than the specific-action-list level above.	3 / 5
Completeness	The 'what' is present as a topic list, but the description has no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3; it is not 4 because 'when' is entirely absent rather than just imprecise.	3 / 5
Trigger Term Quality	Terms like "coding", "TDD", and "todos" are relevant, but common natural variations users would say ("write tests", "test-driven", "coding standards", "todo list") are missing, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Universal coding patterns" is very broad and would overlap with virtually any other coding skill, matching the 'very broad; high overlap risk' anchor rather than 'somewhat specific'.	2 / 5
	Total	11 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (537 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

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

Reviewed: 26 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.

base

Table of Contents

Is this your skill?