CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

commonly

Use a Commonly pod as shared context, and post short replies, handoffs or files to it through the commonly MCP tools. Load whenever commonly_* MCP tools are available.

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

Excellent content: lean, non-obvious, and fully actionable, with a correctly ordered workflow and a genuine validate-retry feedback loop for the 409 case, plus prudent security guidance about never handling the runtime token in chat. Nothing in the body is wasted or missing for the skill's scope.

DimensionReasoningScore

Conciseness

The 18-line body is lean and every sentence carries non-obvious operational information: where the token lives ('COMMONLY_AGENT_TOKEN, which Hermes keeps in the profile's .env'), what a 409 means, and that 'Installing the plugin does not make Hermes watch the pod'. No padding and no explanation of concepts Claude already knows, matching 'every token earns its place'.

5 / 5

Actionability

It names the exact tool calls to use in order (commonly_get_started, commonly_list_pods, commonly_get_context, commonly_get_messages, commonly_catch_up, commonly_attach_file) and gives concrete failure handling ('If a post comes back 409 unseen_messages, the pod has messages you haven't read: read them with commonly_get_messages and retry'). For an instruction-only skill this is copy-paste-ready guidance, matching anchor 5.

5 / 5

Workflow Clarity

The sequence is explicit (get_started conventions, then list_pods unless the ID is known, then get_context before any post) and includes a real feedback loop: 409 unseen_messages -> get_messages and retry, escalating to commonly_catch_up 'when the backlog is larger than one read returns'. It also adds pre-reply checkpoints ('read the messages around the mention before replying') and clear silence criteria, matching anchor 5's error-recovery pattern.

5 / 5

Progressive Disclosure

This is a simple skill under 50 lines with no bundle files; the two sections ('First connection', 'Pod workflow') cleanly separate setup from operation and all content genuinely belongs inline. Per the simple-skill exception, well-organized sections with no need for external references score 5.

5 / 5

Total

20

/

20

Passed

Description

66%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 solid description with a clear what/when pair and strong distinctiveness thanks to product-specific terminology. Its weaknesses are one-sided capability coverage (posting only, not reading/catching up) and a trigger clause phrased around tool availability rather than natural user language.

Suggestions

Enumerate the main capabilities more completely, e.g. 'read pod messages and context, catch up on backlogs, and post short replies, handoffs or files' so the 'what' covers both reading and posting.

Add natural user-facing trigger phrasing alongside the tool-availability condition, e.g. 'Use when the user mentions a Commonly pod, asks to check or reply in the pod, or wants to share a file with teammates'.

Include common synonyms/variations of the trigger terms (pod, shared channel, team channel, handoff) to improve recall when users phrase the need differently.

DimensionReasoningScore

Specificity

Names the domain ('Use a Commonly pod as shared context') and one concrete action ('post short replies, handoffs or files to it through the commonly MCP tools'), but omits the read/catch-up/context-checking capabilities the body documents. This matches 'Names domain and 1-2 concrete actions, but not comprehensive', not level 4's 'several specific actions'.

3 / 5

Completeness

It answers both questions: what ('Use a Commonly pod as shared context, and post short replies, handoffs or files to it') and when ('Load whenever commonly_* MCP tools are available'). Not 5 because the 'when' is tool-conditional rather than concrete user trigger phrases, which is exactly anchor 4's 'when could be more explicit or specific'.

4 / 5

Trigger Term Quality

Relevant domain keywords exist ('Commonly pod', 'shared context', 'replies', 'handoffs', 'files'), but the trigger relies solely on tool availability ('Load whenever commonly_* MCP tools are available') and misses natural user phrases like 'check the pod' or 'share with the team'. Some relevant keywords but missing common variations, matching anchor 3 rather than 4.

3 / 5

Distinctiveness Conflict Risk

The description is anchored to a unique product ('Commonly pod', 'commonly MCP tools', 'commonly_*') and only fires when those specific MCP tools are present, giving it a clear niche with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

15

/

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

Team-Commonly/commonly

Path

plugins/commonly-hermes-plugin/skills/commonly/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.