langbot-eba-adapter-dev

Build, refactor, and test LangBot platform adapters for the Event-Based Agents architecture. Use when adding or migrating Telegram, Discord, or other messaging platform adapters to the EBA adapter layout, validating unified event/message conversion, writing live adapter probes, or using standalone plugin runtime plus Computer Use for end-to-end platform testing.

Quality

91%

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

Quality

Content

85%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.

Highly actionable and clearly sequenced content with explicit validation and destructive-operation gating, held back by a monolithic single-file structure with no reference bundle and some repeated lists. Splitting the acceptance, runtime-setup, and documentation-record material into reference files would lift both structure and conciseness.

Suggestions

Move the message component list (Source, Plain, At, AtAll, Image, Voice, File, Quote, Face, Forward, Unknown) into a single reference file and cite it once, instead of repeating the full enumeration in Unit Tests, Conversion Contract, and Required EBA Acceptance Coverage.

Extract the standalone runtime setup (terminal commands, env vars, probe sweeps) and the documentation record format into references/ files (e.g. references/runtime-setup.md, references/adapter-doc-format.md), keeping SKILL.md as a workflow overview.

Consolidate the evidence-level taxonomy (plugin-e2e-ui, plugin-e2e-protocol, plugin-e2e-outbound, adapter-live, unit, not-supported, blocked) into one section — it is currently defined in Live Test Workflow and re-explained across the acceptance sections.

Dimension	Reasoning	Score
Conciseness	The body is dense and project-specific with no generic concept explanations, but the message component list (Source, Plain, At, AtAll…) is repeated in three sections and the evidence-level taxonomy spans two sections. Not 5: those repetitions and overlaps are tokens that do not earn their place.	4 / 5
Actionability	Provides copy-paste-ready commands (pytest invocations, the three-terminal standalone runtime block with ports and env vars), exact file paths, a directory layout, and an executable conversion-contract code block. Not 4: the commands are complete and cover the common cases, with only appropriate <platform> placeholders.	5 / 5
Workflow Clarity	A numbered 'Start Here' sequence, implementation and test checklists, destructive APIs gated behind flags and "run them last", and a 'Before Finishing' validation list (run tests, git diff --check, stop runtimes, confirm no secrets staged). Not 4: validation checkpoints for the destructive/live operations are explicit and complete, satisfying the cap exception.	5 / 5
Progressive Disclosure	The file is well-sectioned with clear headers and clear pointers into LangBot repo docs, but there is no references/scripts/assets bundle at all — ~300 lines including acceptance-coverage lists, the docs-record format, and repeated component tables are inlined in a single file. Not 4: content that should live in reference files is inline; not 2: structure and external signposting are good.	3 / 5
	Total	17 / 20 Passed

Description

92%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.

A strong description: it names concrete capabilities across build, migration, validation, probing, and E2E testing, and provides an explicit multi-trigger 'Use when' clause with natural platform keywords. The only gap is a few missing synonyms for trigger terms.

Dimension	Reasoning	Score
Specificity	"Build, refactor, and test LangBot platform adapters… validating unified event/message conversion, writing live adapter probes, or using standalone plugin runtime plus Computer Use for end-to-end platform testing" lists multiple specific concrete actions with comprehensive coverage of the skill's domain. Not 4: the action list spans build, migration, validation, probing, and E2E testing with no meaningful coverage gap.	5 / 5
Completeness	Explicitly answers both what ("Build, refactor, and test LangBot platform adapters for the Event-Based Agents architecture") and when ("Use when adding or migrating Telegram, Discord, or other messaging platform adapters…") with concrete trigger phrases. Not 4: the 'when' clause is explicit, multi-trigger, and specific — matching the top anchor.	5 / 5
Trigger Term Quality	Natural terms a user would say include "Telegram, Discord", "messaging platform adapters", "EBA adapter layout", and "live adapter probes". Not 5: good but not exhaustive — common variations such as "port", "message chain", or other platform names are missing.	4 / 5
Distinctiveness Conflict Risk	"LangBot platform adapters" under the "EBA adapter layout" is a clear niche with distinct platform-name triggers, unlikely to fire for unrelated skills. Not 4: the combination of project name, architecture name, and platform names leaves minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: langbot-app/LangBot
Path: skills/skills/langbot-eba-adapter-dev/SKILL.md
Commit: 40a3a94

Reviewed: 3 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.