Name: canny
Rating: 60.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

canny

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

Quality

71%

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/canny/SKILL.md

Quality

Content

82%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 highly actionable with concrete executable Membrane commands and a clearly sequenced connection workflow including state branches and a polling feedback loop. Its main weaknesses are mild over-explanation in the intro and the absence of explicit validation guidance before destructive actions such as delete-post.

Suggestions

Trim the opening paragraph explaining what Canny is and who uses it, since Claude already knows the product; keep only the integration-relevant context.

Add an explicit validation/checklist step before destructive operations such as delete-post (e.g. retrieve-post to confirm the target, then confirm with the user) so the workflow clears the destructive-ops bar.

Consider moving the full 'Popular actions' table into a separate reference file and keeping only the most common actions inline to reduce the inline reference bulk.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean CLI commands and tables, with only minor over-explanation such as the opening paragraph describing what Canny is and who uses it and a bit of prose around auth plumbing, fitting 'efficient; minor instances of over-explanation that could be trimmed'.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands throughout (install, login, connection ensure, polling, action list/run with JSON input, request proxy with flags) covering the common cases, matching 'fully executable; copy-paste ready code or commands'.	5 / 5
Workflow Clarity	The install→login→connect→poll→search→run sequence is clearly laid out with state-based branching (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a poll-again feedback loop, but it lacks an explicit pre-proceed validation checklist for destructive actions like delete-post, fitting 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	Content is a single well-organized file with clear section headers and no nested references; the inline 'Popular actions' table is a sizable reference that could be split out, but overall structure is good with minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

61%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 correctly answers both what and when and is clearly distinct to Canny, but it is held back by generic action phrasing ('manage data, records') and thin trigger-term coverage that omits Canny's core concepts like posts, votes, and feedback. Tightening the capability list to concrete Canny operations and adding natural synonyms would lift it toward the top anchors.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Canny operations such as 'collect and prioritize user feedback, manage posts, votes, boards, and changelog entries'.

Expand trigger terms beyond 'Canny data' to include natural user phrases like 'feedback, feature requests, votes, or roadmap' so the skill matches how users actually phrase the need.

Add a concrete 'when' clause naming the artifacts users mention (e.g. 'Use when the user wants to manage Canny posts, votes, boards, or changelog entries').

Dimension	Reasoning	Score
Specificity	Names the Canny domain and a couple of actions ('Manage data, records, and automate workflows'), but the actions are minimal and generic rather than concrete Canny-specific operations, fitting 'names the domain but actions are minimal or generic' below the midpoint of 3.	2 / 5
Completeness	Both 'what' ('Canny integration. Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Canny data') are present, though the 'what' is somewhat generic and the 'when' could be more specific, matching 'has both what and when; when could be more explicit'.	4 / 5
Trigger Term Quality	Includes the natural keyword 'Canny' via 'Use when the user wants to interact with Canny data', but lacks common synonyms or variations (feedback, posts, votes, boards), matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	Targets a single named SaaS tool (Canny) with a Canny-specific trigger, giving it a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	14 / 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/canny/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.