Tessl • The management layer for AI agent skills

SkillPublic

buildbuddy

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

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

67%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 delivers strong, executable Membrane CLI guidance with a genuinely well-instrumented connection state machine (polling, client actions, error states). Its weaknesses are cosmetic but real: a dangling 'Step 2' reference with no numbered steps, a duplicated/empty 'Popular actions' section, and a cryptic overview list that add tokens without guidance value.

Suggestions

Fix the dangling references: either add explicit numbered step headings (1. Connect, 2. Discover actions, 3. Run actions) or drop the 'skip to **Step 2**' and '1b' labels.

Remove or flesh out the 'Popular actions' section — it currently repeats the discovery command without listing any actual BuildBuddy actions; either enumerate 3-5 concrete actions or delete the section.

Replace the bare 'BuildBuddy Overview' bullet list and 'Use action names and parameters as needed.' with one line stating what each entity (Build, Invocation, Test Result, Artifact) maps to in BuildBuddy, or delete them.

Dimension	Reasoning	Score
Conciseness	The CLI guidance is mostly tight and command-first, but there is real padding: the cryptic 'BuildBuddy Overview' bullet list ('Build', 'Artifact', 'Invocation', 'Test Result') with no descriptions, the filler line 'Use action names and parameters as needed.', and the 'Popular actions' section that merely repeats the action-list command from 'Searching for actions' without listing any popular actions.	3 / 5
Actionability	Concrete, copy-paste-ready commands throughout (install, login, connection ensure, polling with --wait, action run with --input, proxy flag table). Minor gaps: no example invoking a real BuildBuddy action with its output, and inconsistent invocation styles ('membrane' vs 'npx @membranehq/cli@latest') without noting they are interchangeable.	4 / 5
Workflow Clarity	The connection workflow is well sequenced with explicit validation checkpoints — poll state with --wait, branch on READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR, and re-poll after user action. Not a 5 because 'skip to Step 2' is referenced twice yet no Step 2 (or Step 1/1a) heading exists, leaving the numbered sequence incoherent.	4 / 5
Progressive Disclosure	A single-file skill with no bundle files and clearly headed sections that are mostly appropriately placed for a ~140-line overview. Not a 5 because the Membrane auth/connection boilerplate and the proxy flags table are generic across integrations and arguably belong in a shared reference file, slightly bloating the main file.	4 / 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 correctly anchors triggering on the BuildBuddy product name and includes an explicit 'Use when...' clause, so it answers both what and when. However, the capability statement is generic ('Manage data, records, and automate workflows') and misses the concrete BuildBuddy operations (invocations, test results, artifacts) that would make it specific and reduce trigger-term gaps.

Suggestions

Replace 'Manage data, records, and automate workflows' with concrete BuildBuddy capabilities, e.g., 'Query build invocations, fetch test results, and manage build artifacts'.

Broaden the 'Use when' clause with natural trigger variations: 'Use when the user mentions BuildBuddy, build invocations, CI build results, or test reports'.

Drop the vague term 'records' — it is not a BuildBuddy concept and adds trigger-term noise without specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('BuildBuddy integration') but the actions are generic — 'Manage data, records, and automate workflows' could describe almost any integration skill, with no concrete BuildBuddy operations (e.g., querying invocations, fetching test results, managing artifacts) that the body clearly supports.	2 / 5
Completeness	Both parts are present: what ('BuildBuddy integration. Manage data, records, and automate workflows') and an explicit when ('Use when the user wants to interact with BuildBuddy data'). Not a 5 because the 'what' lacks concrete capabilities and the 'when' is a single narrow clause rather than concrete trigger phrases; not a 3 because the 'when' is explicit, not merely implied.	4 / 5
Trigger Term Quality	'BuildBuddy' / 'BuildBuddy data' is the natural keyword a user of this platform would say, but there are no variations or synonyms such as 'builds', 'CI', 'invocations', 'test results', or 'artifacts' that would broaden natural triggering.	3 / 5
Distinctiveness Conflict Risk	The product-name trigger ('BuildBuddy') carves a clear niche with minimal conflict risk, but the generic phrases 'manage data' and 'automate workflows' create minor overlap risk with general data-management or automation skills. Not a 5 because those generic phrases could plausibly pull the wrong skill.	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/buildbuddy/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.

buildbuddy

Table of Contents

Is this your skill?