add-github

Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-github/SKILL.md

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a strong, highly actionable skill body with concrete commands, explicit validation, and tight prose. The only gap is progressive disclosure: everything lives inline in one file when some sections could be offloaded to reference files.

Suggestions

Move the Troubleshooting and Channel Info sections into separate reference files (e.g. references/TROUBLESHOOTING.md, references/CHANNEL_INFO.md) linked from the body, keeping SKILL.md an overview with one-level-deep references.

Consider extracting the Credentials/webhook walkthrough into a reference file so the core Apply + Wiring flow stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is dense and instructional with no padding explaining concepts Claude already knows (no 'what is a PR' filler), and every section earns its tokens with directives, exact versions, and commands.	3 / 3
Actionability	It provides copy-paste-ready guidance: exact pinned version '@chat-adapter/github@4.29.0', concrete 'nc:' directives, specific 'ncl' commands, and precise env-var names and webhook settings.	3 / 3
Workflow Clarity	The Apply steps are numbered 1-4 with an explicit build/test validation checkpoint in step 4, and the troubleshooting section gives a clear feedback loop (test red -> re-run Apply steps), matching the score-3 anchor.	3 / 3
Progressive Disclosure	Sections are well-organized, but the document is a single ~180-line monolith with no bundle references; content like Troubleshooting and Channel Info could be split into one-level-deep reference files, so it sits at the score-2 anchor rather than 3.	2 / 3
	Total	11 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 clearly states what the skill does and occupies a distinct niche, but it omits an explicit 'Use when...' trigger and leans on product jargon over natural user phrasing. It is solid but not exemplary.

Suggestions

Add an explicit trigger clause, e.g. 'Use when adding GitHub as a channel to an agent so it can reply in PR and issue comment threads.'

Swap jargon-heavy phrasing for natural terms users would say: spell out 'pull requests' alongside 'PR' and phrase it as 'add GitHub support' rather than 'channel integration via Chat SDK'.

List one or two more concrete actions (e.g. '@-mention detection, webhook setup') to lift specificity from a partial list toward the score-3 anchor.

Dimension	Reasoning	Score
Specificity	Quotes 'Add GitHub channel integration via Chat SDK' and 'PR and issue comment threads as conversations' name the domain and a couple of concrete behaviors, but the description lists fewer distinct actions than the score-3 anchor and is not comprehensive.	2 / 3
Completeness	The 'what' is explicit (add GitHub channel integration, treat PR/issue comment threads as conversations) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It surfaces 'GitHub', 'PR', and 'issue' but reads as product jargon ('Chat SDK', 'channel integration') rather than the natural phrasing a user would say, and is missing common variations like 'pull requests' spelled out or 'add GitHub support'.	2 / 3
Distinctiveness Conflict Risk	'GitHub channel integration via Chat SDK' carves out a clear, narrow niche with distinct triggers that is unlikely to fire for unrelated skills.	3 / 3
	Total	9 / 12 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: nanocoai/nanoclaw
Path: .claude/skills/add-github/SKILL.md
Commit: 641963c

Reviewed: 6 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.