code-import

Read an existing repository's structure into the project cwd as a normalised snapshot the agent can analyse without re-walking the tree on every turn.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/_official/atoms/code-import/SKILL.md

Quality

Content

71%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 body is a well-structured, concise spec with clear inputs, outputs, convergence criteria, and anti-patterns, making it easy to navigate and reason about. Its main gap is actionability: it describes the contract precisely but provides no executable walk/import code or commands inside the skill.

Suggestions

Add a short executable snippet or concrete command illustrating how the walk/import is invoked and how index.json is produced, to move actionability from spec-level to copy-paste-ready.

Spell out the error-recovery feedback loop when the walk exceeds budgetMs (e.g. narrow scope and re-walk, or record partial results) to make workflow checkpoints fully explicit.

Clarify how a consumer should trigger a re-import after upstream changes, since the skill's premise is trusting the snapshot until an explicit re-import.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding about what repos or frameworks are; only brief rationale ('stop re-walking the tree on every turn') and spec citations keep it just shy of the fully lean level-5 anchor.	4 / 5
Actionability	Concrete artifacts are specified precisely (inputs table, output file schemas, anti-patterns with config-file evidence), but there is no executable code or command sequence for performing the walk itself, fitting the 'some concrete guidance but incomplete' anchor rather than the copy-paste-ready level 4-5.	3 / 5
Workflow Clarity	A clear sequence (walk respecting budget -> write index.json -> convergence check -> abort on empty repo) is present with an explicit validation checkpoint for the empty-repo failure case, matching 'clear sequence with most checkpoints present'; it is not level 5 because error-recovery feedback loops beyond the empty-repo abort are only implicit.	4 / 5
Progressive Disclosure	A single, well-organized file with clearly signaled sections (Inputs, Output, Convergence, Anti-patterns, Status) and no nested references; per the simple-skill scoring note, a short single-purpose skill with clean sectioning can score 5 without external file references.	5 / 5
	Total	16 / 20 Passed

Description

53%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 gives a clear, specific statement of what the skill does but omits any 'when to use it' trigger guidance, which caps its completeness and limits natural trigger-term coverage. Adding an explicit 'Use when...' clause with user-facing terms would lift the weakest dimensions.

Suggestions

Append a 'Use when...' clause naming natural triggers, e.g. 'Use when importing an existing repo for a code-migration run or when the user asks to snapshot a codebase for analysis.'

Surface user-facing terms like 'import a repo', 'code migration', and 'codebase snapshot' alongside the technical phrasing to improve trigger-term quality.

Optionally list a second concrete action (e.g. 'records framework, routing, and component evidence') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('repository's structure') and one concrete action ('Read...into...a normalised snapshot') but does not enumerate several specific actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action level 4.	3 / 5
Completeness	Provides a clear 'what' (read the repo into a normalised snapshot) but has no 'Use when...' or equivalent trigger clause, which per the guidelines caps completeness at 3; it is not level 2 because the 'what' is concrete rather than vague.	3 / 5
Trigger Term Quality	Uses some relevant technical keywords ('repository's structure', 'normalised snapshot', 'project cwd') but omits natural user-facing phrases like 'import a repo' or 'code migration', fitting the 'some relevant keywords but missing common variations' anchor; it is not level 2 because it is not purely generic.	3 / 5
Distinctiveness Conflict Risk	Targets a specific code-migration import niche with minimal overlap risk versus general skills, matching 'mostly distinct; minor overlap risk'; it is not level 5 because no explicit trigger phrases sharpen the niche further.	4 / 5
	Total	13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: plugins/_official/atoms/code-import/SKILL.md
Commit: 1a7a23d

Reviewed: about 6 hours 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.