CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-github

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

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

81%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 a strong, highly actionable runbook with explicit validation and error-recovery loops — among the better executable skills. Its main weaknesses are mild token inefficiency (redundant explanations of known GitHub concepts and repeated @-mention behavior) and a single-file structure that is slightly long for a SKILL.md overview.

DimensionReasoningScore

Conciseness

The body is mostly efficient, direct instruction, but contains unnecessary explanation: "GitHub has 'repositories' containing 'pull requests' and 'issues'" teaches concepts Claude already knows, the nc:prompt/vault design rationale is tangential, and the GITHUB_BOT_USERNAME @-mention behavior is explained twice (Wiring and Channel Info). Not 4: there are several, not just minor, instances that could be trimmed.

3 / 5

Actionability

Fully executable throughout: concrete nc: directive fences, a pinned dependency (@chat-adapter/github@4.41.1), real ncl/gh/launchctl/systemctl commands, and specific token permissions ("Pull requests (Read & Write), Issues (Read & Write)"). Placeholders like <policy> and <mg-id> are appropriate parameterization, and copy-paste-ready commands cover the common cases.

5 / 5

Workflow Clarity

Clear sequence (Apply → Credentials → Wiring → Next Steps) with explicit validation checkpoints: the build guards the typed core call and the vitest run proves the barrel import and dependency are intact. Troubleshooting provides feedback loops (red registration test → re-run Apply steps; webhook redelivery to retest). Not 4: validation is explicit and error recovery is covered end-to-end.

5 / 5

Progressive Disclosure

No bundle files exist; the skill is a single self-contained runbook with well-organized sections (Apply, Credentials, Wiring, Channel Info, Troubleshooting) and no nested references. Not 5: at ~185 lines it exceeds overview scope — the Troubleshooting and Channel Info sections could plausibly live in a referenced file; not 3: structure is genuinely good and navigation is easy.

4 / 5

Total

17

/

20

Passed

Description

53%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 clearly states what the skill does with a distinct GitHub-channel niche, but it lacks any "Use when..." trigger guidance and misses common keyword variations like "pull requests" and "repos". It sits at the midpoint: specific enough to distinguish, incomplete enough to under-trigger.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to add GitHub integration, connect PRs/issues to the agent, or set up a GitHub bot that replies in comment threads."

Spell out natural keyword variations: "pull requests (PRs)", "repositories/repos", and "GitHub bot" to improve trigger-term coverage.

Mention one more concrete capability (e.g., webhook-driven @-mention responses in PR/issue threads) to raise specificity beyond a single action verb.

DimensionReasoningScore

Specificity

"Add GitHub channel integration via Chat SDK" and "PR and issue comment threads as conversations" name the domain and 1-2 concrete actions, but coverage is not comprehensive (no webhooks, bot account, or wiring mentioned). Not 4: only one real action verb and several gaps in capability coverage.

3 / 5

Completeness

The "what" is clear (add GitHub channel integration; PR and issue comment threads become conversations), but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description. Per the judging guideline, a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

"GitHub", "PR", and "issue comment threads" are natural user terms, but common variations like "pull requests" (unabbreviated), "repos", and "GitHub integration" are absent. Not 4: keyword coverage has noticeable gaps rather than just a few missing synonyms.

3 / 5

Distinctiveness Conflict Risk

"GitHub channel integration via Chat SDK" carves a clear niche with distinct triggers (GitHub, PR, issue comments), with only minor overlap risk against closely related channel-adapter skills (e.g., adding a Slack or Discord channel). Not 5: a family of similar channel-add skills could compete for the same phrasing.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

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.