Name: cody
Rating: 56.00000000000001 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

cody

Cody integration. Manage data, records, and automate workflows. Use when the user wants to interact with Cody data.

Quality

64%

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 ./skills/cody/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 content is highly actionable with executable Membrane CLI commands and a clear, validated connection workflow, but it carries marketing padding and inlines bulk reference material (the actions table) that would benefit from a separate file. Overall a strong, practical skill body with modest conciseness and disclosure improvements available.

Suggestions

Cut the introductory marketing paragraph and the cryptic 'Cody Overview' bullet list; Claude does not need to be told what an AI coding assistant is.

Move the 18-row popular actions table and the clientAction field reference into a references/ file (e.g. ACTIONS.md) and link to it from a short summary, applying progressive disclosure.

Fix the dangling 'Step 2' reference and the '1b' sub-numbering so the connection workflow has a clean, explicit step sequence.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete CLI commands, but the marketing-style opening ('Cody is an AI coding assistant that helps developers write code and understand code faster... Developers of all skill levels use Cody to improve their productivity and code quality.') and the cryptic 'Cody Overview' bullet list are unnecessary padding Claude does not need, fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It provides copy-paste-ready, fully executable commands for every common case (npm install, membrane login, connection ensure/get with --wait, action list/run with --input, request proxy) with flags explained, matching the level-5 anchor for fully executable guidance covering common cases.	5 / 5
Workflow Clarity	The install→auth→connect→search→run sequence is clear and the connection section has explicit validation via state polling (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) with re-poll feedback loops, but the dangling 'skip to Step 2' reference and the odd '1b' numbering leave minor gaps, fitting level 4 rather than the fully-checkpointed level 5.	4 / 5
Progressive Disclosure	No bundle files exist and the body references no separate files; the 18-row popular actions table and the detailed clientAction field reference are bulk content inlined in SKILL.md that could live in a reference file, fitting 'some structure but content that should be separate is inline' rather than level 4 (which expects bulk content split out) — the under-50-line exception does not apply to this ~160-line skill.	3 / 5
	Total	15 / 20 Passed

Description

57%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 clearly names the Cody niche and includes an explicit use-when clause, but its action verbs are generic and it lacks the concrete triggers and synonyms that would make it crisp. It is functional but leaves specificity and trigger coverage on the table.

Suggestions

Replace generic verbs with concrete operations the skill actually performs, e.g. 'Create and search Cody conversations, send and list messages, and manage documents and folders.'

Broaden trigger terms to include natural phrasings users would say, such as 'Cody, Sourcegraph, conversations, messages, bots, or documents'.

Tighten the use-when clause to reference specific Cody objects ('Use when the user wants to read or send Cody messages, manage Cody conversations, or organize Cody documents and folders.')

Dimension	Reasoning	Score
Specificity	Phrases like 'Manage data, records, and automate workflows' name the Cody domain plus a few actions, but the verbs (manage, automate) are generic rather than concrete operations, matching the 'names the domain but actions are minimal or generic' anchor better than the level-3 anchor which expects a genuinely concrete action.	2 / 5
Completeness	It states what ('Manage data, records, and automate workflows') and an explicit when ('Use when the user wants to interact with Cody data'); both are present but the when could be more specific, matching the level-4 anchor rather than level 3 (when is explicit, not merely implied) or level 5 (trigger phrases are not concrete enough).	4 / 5
Trigger Term Quality	'Cody' and 'interact with Cody data' give some relevant natural keywords a user would say, but common synonyms and surface features from the body (Sourcegraph, conversations, bots, code completion) are absent, fitting 'some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product 'Cody' gives a clear niche with low conflict risk, but the generic 'Manage data, records, and automate workflows' phrasing leaves minor overlap risk with adjacent data/integration skills, fitting 'mostly distinct; minor overlap risk' rather than the fully-distinct level-5 anchor.	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: membranedev/application-skills
Path: skills/cody/SKILL.md
Commit: f484c82

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.