discord-clawd

Discord-backed OpenClaw agent/session relay; not archive search.

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/discord-clawd/SKILL.md

The canonical home for this skill is discord-clawd in openclaw/openclaw

Quality

Content

86%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 an exemplary lean operational skill: concrete relay commands, a sensible escalation policy across ask/publish/force-send, and explicit guardrails including secret hygiene and scope boundaries. The only meaningful improvement would be showing the publish/force-send syntax and a recovery step when resolution or delivery fails.

Dimension	Reasoning	Score
Conciseness	The ~35-line body explains nothing Claude already knows; every section ('Transport', 'Guardrails') carries only operational content — commands, mode guidance, and four terse guardrail bullets. This matches 'lean and efficient; assumes Claude's competence; every token earns its place'.	5 / 5
Actionability	The transport commands are concrete and copy-paste ready ('cd ~/Projects/agent-scripts', 'python3 .../openclaw_relay.py targets', the full 'ask' invocation with --target and --message), matching mostly-executable guidance. It falls short of 5 because 'publish' and 'force-send' are named as delivery modes but no invocation syntax is shown for them — a minor gap.	4 / 5
Workflow Clarity	The sequence targets → resolve → ask/publish/force-send is clear, and the guardrails provide explicit checkpoints ('Resolve the target before sending real content', 'Report the target and delivery mode used'), plus the OK-probe 'Reply with exactly OK' acts as a lightweight validation. It does not reach 5 because there is no feedback loop for what to do when resolution or delivery fails (e.g., re-check 'targets' output or report the error).	4 / 5
Progressive Disclosure	At under 50 lines with no need for external reference files (none exist in references/, scripts/, or assets/ of this bundle), the well-organized 'Transport' and 'Guardrails' sections fully satisfy the simple-skill exception: score 5 with just well-organized sections. Navigation is trivial.	5 / 5
	Total	18 / 20 Passed

Description

52%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 is admirably concise and clearly disambiguated from archive-search skills, but it omits what the skill actually does (ask, post, publish, force-send) and any 'Use when' trigger guidance. As written it functions more as a boundary declaration than a capability description.

Suggestions

Add one or two concrete actions to the description, e.g. 'Relays questions and posts to the Discord-backed OpenClaw agent/session (ask, publish, force-send)' — this would lift specificity from 2 toward 4.

Append a 'Use when...' clause with natural trigger terms, e.g. 'Use when the task is to message the Discord agent, ask it a question, or post through the relay' — this addresses both completeness and trigger_term_quality.

Include the natural synonyms users would say ('message', 'post to Discord', 'send to the agent') so the skill triggers on phrasing beyond 'Discord-backed'.

Dimension	Reasoning	Score
Specificity	The description names the domain — 'Discord-backed OpenClaw agent/session relay' — but states no concrete actions (no mention of asking, posting, resolving targets, or messaging), matching the anchor 'names the domain but actions are minimal or generic'. It does not reach 3 because no 1-2 concrete actions are actually listed, and it is above 1 because the domain is specific rather than pure abstract language.	2 / 5
Completeness	There is a clear 'what' (an OpenClaw agent/session relay over Discord) but no 'when' clause at all — the disambiguation 'not archive search' is a boundary, not a trigger. Per the guideline, a missing 'Use when...' clause caps completeness at 3, and it cannot score 4 since the 'when' is entirely absent rather than just imprecise.	3 / 5
Trigger Term Quality	'Discord-backed' and 'archive search' are relevant keywords a user might mention, but common natural phrases users would say are missing — 'message', 'post to', 'send', 'Discord server', or 'relay' variations. This fits 'some relevant keywords but missing common variations or synonyms' rather than 4 ('good coverage, a few natural terms missing') because most natural trigger phrasings are absent.	3 / 5
Distinctiveness Conflict Risk	'Discord-backed OpenClaw agent/session relay; not archive search' carves out a clear niche and explicitly negates the nearest competing trigger (archive/history/search), minimizing conflict risk — matching 'clear niche with distinct triggers; minimal conflict risk'. It is not below 5 because the explicit negation directly addresses the one plausible overlap.	5 / 5
	Total	13 / 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: steipete/agent-scripts
Path: skills/discord-clawd/SKILL.md
Commit: 3f8c6a3

Reviewed: 2 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.