CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-mattermost

Add a self-hosted or cloud Mattermost bot channel through the Chat SDK bridge, reusing a healthy server when available and linking to official server setup guidance when needed.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-mattermost/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 exemplar of executable, validated workflow writing: concrete commands, pinned versions, explicit checkpoints, and thorough error-recovery guidance. Its only real weaknesses are repeated warnings that could be consolidated and one dangling reference to a missing SERVER_SETUP.md file.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — it never explains what Mattermost or WebSocket is — but repeats guidance: the 'Do not change AllowCorsFrom' warning appears three times, WEBHOOK_HOST=0.0.0.0 instructions twice, and the troubleshooting section restates the step-2 SiteURL settings. This fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the every-token-earns-its-place anchor at 5.

4 / 5

Actionability

Every step is copy-paste executable: exact curl/mmctl/pnpm commands, precise regex validators for each prompt, pinned dependency versions (ws@8.21.3, @types/ws@8.18.1), and script invocations that resolve to real files in scripts/ (discover-server.mjs, select-server.mjs, read-response.mjs, configure.ts, remove-config.mjs, verify-runtime.ts). This matches the fully-executable anchor.

5 / 5

Workflow Clarity

A clear discovery-first phase plus seven explicitly numbered steps, each with a validation checkpoint: the config-client check ('must print {{base_url}} and then a blank line'), build, tests, restart, and a runtime verifier that creates and cleans up a diagnostic card. The troubleshooting section supplies feedback loops (401 → replacement token; verification timeout → remove diagnostic card), matching the top anchor with explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

Sections are clear, references are one level deep, and six script paths all resolve to real bundle files — but SERVER_SETUP.md is linked and absent from the bundle (the official URLs are duplicated inline, which mitigates it), and the long troubleshooting section is entirely inline. This fits 'good structure; references mostly clear; minor organization gaps' rather than the clean split of the 5 anchor.

4 / 5

Total

18

/

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 is distinctive and names a clear, concrete purpose, but it lacks any explicit 'when to use' trigger clause and has thin keyword coverage beyond the word 'Mattermost'. It reads as a one-action summary of a multi-capability skill.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to connect Mattermost to NanoClaw, add a Mattermost bot or channel, or mentions Mattermost DMs, channels, or approval cards.'

Enumerate the concrete capabilities (DMs, channels, threads, files, reactions, interactive approval cards) so the 'what' matches what the skill actually delivers.

Include natural synonyms users would say — 'connect Mattermost', 'Mattermost integration', 'self-hosted chat' — and drop or de-emphasize internal jargon like 'Chat SDK bridge' from the trigger-facing text.

DimensionReasoningScore

Specificity

The description names the domain ('Mattermost bot channel', 'Chat SDK bridge') and one concrete action ('Add'), but does not enumerate the concrete capabilities the skill delivers (DMs, threads, reactions, approval cards), matching the '1-2 concrete actions, not comprehensive' anchor rather than the several-actions anchor at 4.

3 / 5

Completeness

The 'what' is clear ('Add a self-hosted or cloud Mattermost bot channel through the Chat SDK bridge'), but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'when available' and 'when needed' are behavioral conditions, not usage triggers. Per the rubric guideline, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

'Mattermost' and 'bot channel' are natural user terms, but coverage stops there — no synonyms or phrasings users would naturally say ('connect Mattermost', 'Mattermost integration', 'Mattermost DMs'), and 'Chat SDK bridge' is internal jargon. This fits the 'some relevant keywords but missing common variations' anchor, not the good-coverage anchor at 4.

3 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche — adding a Mattermost bot channel through a specific SDK bridge with server-reuse behavior — and is unlikely to trigger for unrelated skills; only sibling channel-adding skills are adjacent. It matches the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

nanocoai/nanoclaw

Path

.claude/skills/add-mattermost/SKILL.md

Reviewed

Table of Contents

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.