Tessl • The management layer for AI agent skills

The body delivers concrete, executable CLI guidance with good connection-state handling and a clean single-file structure. Its main weaknesses are padding in the intro/overview sections and broken workflow numbering ('Step 2' and '1b' referenced but never defined), which leaves the intended sequence ambiguous.

Suggestions

Fix the broken numbering: either label the workflow as numbered steps (Step 1: Install, Step 2: Connect, ...) so the two 'skip to Step 2' references and the '1b' section resolve, or drop the step references entirely.

Cut the marketing intro paragraph and the 'Overview' section with 'Use action names and parameters as needed' — they add tokens without actionable content.

Add one worked end-to-end example: show `membrane action list` output, pick an actionId, then run it with a real `--input` payload so the list → run flow is fully demonstrated.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-focused and efficient, but contains unnecessary padding: the marketing-style intro ('Bot9 is a platform for building and deploying conversational AI chatbots... Developers and non-technical users can use Bot9...'), a filler 'Overview' section ending with the vacuous 'Use action names and parameters as needed', and a rambling Agent Types aside. This fits 'Mostly efficient but includes some unnecessary explanation or could be tightened'; not 4 because the intro and overview sections add nothing the commands don't already convey.	3 / 5
Actionability	Nearly every section gives copy-paste-ready commands (npm install, membrane login, connection ensure, action list/run with --input JSON, request proxy with a flags table) and the Popular actions table names concrete actions. Not 5 because a few spots stay high-level — the dangling 'Step 2', the vague 'Use action names and parameters as needed', and no worked end-to-end example showing a real actionId from list to run.	4 / 5
Workflow Clarity	A rough sequence exists (install → login → connection ensure → poll state → search actions → run / proxy) and the connection-state handling (READY / BUILDING / CLIENT_ACTION_REQUIRED with re-polling) is a decent feedback loop, but the numbering is broken: it references 'Step 2' twice and a '1b' section with no Step 1 or Step 2 ever defined. That incoherent sequencing plus no numbered top-level steps fits 'sequence present but checkpoints missing or implicit'; not 4 because the dangling step references make the intended flow genuinely ambiguous.	3 / 5
Progressive Disclosure	A single SKILL.md with clear section headers (Install, Authentication, Connecting, Searching, Popular actions, Proxy, Best practices), no nested or dangling file references, and appropriately scoped content for a ~145-line CLI skill. Fits 'Good structure; most content is appropriately placed; minor organization gaps' — not 5 because the proxy flag table and popular-actions list could live in a reference file, and the broken step numbering slightly hurts navigation.	4 / 5
	Total	14 / 20 Passed

Description

48%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 has an explicit 'Use when' clause and a distinctive app name, but the capability statement is generic ('manage data, records, automate workflows') with no concrete actions and thin natural trigger terms for a chatbot platform. It reads as a template placeholder rather than a description of what this skill actually enables.

Suggestions

Replace the generic capability clause with the skill's real operations, e.g. 'Send chat messages, initiate chatbot conversations, and retrieve account and chatbot details via the Bot9 API.'

Enrich the trigger clause with natural user phrasing: 'Use when the user mentions Bot9, chatbots, chat conversations, or wants to automate Bot9 customer-service workflows.'

Avoid circularity between 'what' and 'when' — the current 'when' (interact with Bot9 data) restates the vague 'what' instead of naming concrete use cases.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Bot9 integration") but the stated actions — "Manage data, records, and automate workflows" — are generic verbs with no concrete operations (no mention of chat messages, conversations, or account actions that the skill actually supports). This matches the anchor 'Names the domain but actions are minimal or generic' ("Processes PDF files"), and does not reach level 3 because it never lists concrete actions like the PDF example 'extracts content'.	2 / 5
Completeness	The 'when' is explicitly present ("Use when the user wants to interact with Bot9 data"), but the 'what' is vague ("Manage data, records, and automate workflows") and the 'when' is circular ('interact with Bot9 data' restates the domain rather than giving concrete triggers). It sits below anchor 4 ('when' could be more explicit / concrete what) and above anchor 3's 'when missing' — netting out at 3 because the what-side offers no concrete capability to anchor on.	3 / 5
Trigger Term Quality	"Bot9" is a distinct natural keyword and "data"/"records" give some coverage, but common terms a user would actually say for this skill — chatbot, chat, conversation, messages, init-chat, send message — are missing. This fits 'Some relevant keywords but missing common variations or synonyms'; not 4 because the generic 'data/records/workflows' phrasing omits most natural triggers for a chatbot platform.	3 / 5
Distinctiveness Conflict Risk	The app-specific name "Bot9" gives a clear niche with minimal risk of triggering the wrong skill, matching 'Mostly distinct; minor overlap risk with closely related skills'. Not 5 because the generic tail ('Manage data, records, and automate workflows') could pull triggers from any data-integration skill if a sibling Bot9-related skill existed.	4 / 5
	Total	12 / 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/bot9/SKILL.md
Revision: f484c82

Reviewed: 16 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.

bot9

Table of Contents

Is this your skill?