base

Universal coding patterns, constraints, TDD workflow, atomic todos

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Risky

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/base/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete limits, executable per-stack commands, and a rigorous TDD workflow with validation checkpoints. Its weaknesses are length/repetition and a monolithic structure that signals external files which are not actually bundled.

Suggestions

Collapse the three repeated RED/GREEN/VALIDATE explanations (atomic-todo workflow, bug-fix workflow, response format) into one canonical definition referenced by the others to cut tokens.

Move the Credentials, Security, Session Management, and Quality Gates sections into the referenced files (credentials.md, security.md, session-management.md) so the body is a lean overview and the bundle matches what is cited.

Trim Claude-known basics (what bcrypt is, that secrets must not be committed) down to the project-specific thresholds and commands only.

Dimension	Reasoning	Score
Conciseness	Concrete limits ("Maximum 20 lines per function", "Maximum 200 lines per file") earn their tokens, but the ~534-line body repeats the RED/GREEN/VALIDATE cycle three times and explains Claude-known basics ("No secrets in code", bcrypt rounds), so it is mostly efficient yet padded rather than lean.	2 / 3
Actionability	It provides fully executable, copy-paste-ready guidance: exact numeric limits, per-stack commands ("npm test -- --grep", "pytest -k", "ruff check . && mypy ."), and complete todo/bug templates, matching the score-3 anchor.	3 / 3
Workflow Clarity	The TDD and bug-fix workflows are explicitly sequenced (RED→GREEN→VALIDATE→COMPLETE) with validation checkpoints, blocking conditions, and validate→fix→retry feedback loops, matching the score-3 anchor with explicit error recovery.	3 / 3
Progressive Disclosure	References are signaled one level deep ("See credentials.md", "See security.md skill", "See session-management.md"), but no bundle files exist and the 534-line monolith keeps credentials, security, and session content inline that should be split out, matching the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 identifies the skill's domain (coding patterns, TDD, atomic todos) but stays at a category level without concrete actions or an explicit "Use when" trigger. It is distinguishable from pure fluff but generic enough to risk overlap with other coding skills.

Suggestions

Add an explicit "Use when..." clause naming the situations that should activate this skill (e.g., "Use when starting a new project, writing tests, or structuring todos").

Replace generic nouns with concrete actions, e.g., "Enforces 20-line function limits, drives TDD red-green-validate loops, tracks work as atomic todos".

Tighten distinctiveness by dropping "Universal" and leading with the skill's unique differentiator (TDD workflow + atomic todos).

Dimension	Reasoning	Score
Specificity	Names domains and concepts ("Universal coding patterns, constraints, TDD workflow, atomic todos") but lists no concrete actions like the score-3 anchor; it categorizes rather than instructs, so it sits above the vague score-1 anchor.	2 / 3
Completeness	The description answers "what" (coding patterns, TDD, atomic todos) but contains no explicit "Use when..." trigger clause; per the guidelines a missing trigger caps completeness at 2, and it is above the score-1 anchor which lacks both.	2 / 3
Trigger Term Quality	"TDD workflow" and "atomic todos" are natural terms developers say, but "Universal" and "constraints" are generic and common variations are missing, matching the score-2 anchor rather than the full coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	"Universal coding patterns" is generic and would overlap with many coding skills, but "TDD workflow, atomic todos" carve a partial niche, placing it between the very-generic score-1 and the clearly-distinct score-3 anchors.	2 / 3
	Total	8 / 12 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 (534 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/claude-bootstrap
Path: skills/base/SKILL.md
Commit: bb6195f

Reviewed: 6 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.