CtrlK
BlogDocsLog inGet started
Tessl Logo

aris-feishu-notify

Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Supports push-only (webhook) and interactive (bidirectional) modes. Use when user says "发飞书", "notify feishu", or other skills need to send status updates.

62

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/aris-feishu-notify/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, actionable skill body with clear mode-branched workflows and concrete curl examples. The main drag is conciseness — the zero-impact/no-op guarantee is repeated across four sections — and unresolved placeholders in the code examples.

Suggestions

State the 'config absent = mode off, fail open silently' guarantee once in Key Rules and reference it from other sections instead of restating it in Overview, Configuration, and Helper Function.

Add one fully-resolved push-mode example (real title/color/body JSON for e.g. review_scored) so the placeholders become copy-paste ready.

Move the Event Catalog table and the Helper Function template into a reference file (e.g. references/events.md) and link to it one level deep, tightening the main body toward the progressive-disclosure ideal.

DimensionReasoningScore

Conciseness

The body is mostly lean — tables and curl blocks with no padding about what Feishu is — but the 'config absent = no-op' guarantee is restated four times (Overview 'Zero-impact guarantee', Configuration, Helper Function, Key Rules) and the Helper Function section re-derives logic already covered in Workflow. Matches 'Mostly efficient but includes some unnecessary explanation or could be tightened'; not a 4 because the redundancy is repeated rather than minor.

3 / 5

Actionability

Provides concrete, mostly executable curl commands for both push (webhook POST) and interactive (send + poll) modes, plus a config schema and an event→title/color/body catalog. Matches 'Mostly executable guidance; concrete code or commands with minor gaps'; not a 5 because placeholders (TITLE, BODY, COLOR, $WEBHOOK_URL, $BRIDGE_URL, AUTO_PROCEED) are never shown resolved into a complete worked example.

4 / 5

Workflow Clarity

Steps 1–4 are clearly sequenced with explicit mode branching (off/push/interactive), file-not-found handling, and a Step 4 delivery verification (curl exit code, bridge-unreachable fallback). Matches 'Clear sequence with most checkpoints present; minor validation gaps'; not a 5 because verification is light (exit-code check only) and there is no validate→fix→retry loop, though the fail-open design somewhat justifies that.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ all absent) and the skill is self-contained with well-organized sections (Overview, Configuration, Workflow, Helper Function, Event Catalog, Key Rules). Matches 'Good structure; most content is appropriately placed'; not a 5 because at ~150 lines the inlined Event Catalog and Helper Function template are candidates for a one-level-deep reference file, and the body exceeds the <50-line simple-skill exception.

4 / 5

Total

15

/

20

Passed

Description

82%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 strong, well-targeted description that clearly states both capability and trigger conditions with natural multilingual phrases. The only weakness is modest action specificity — it names modes more than concrete verbs.

Suggestions

Add 1-2 concrete action verbs to the description (e.g. 'fires webhook cards' and 'polls for approve/reject replies') to lift specificity above 3.

Consider adding 'Lark message' or 'send a Lark/Feishu message' as an additional natural trigger synonym for fuller keyword coverage.

DimensionReasoningScore

Specificity

Names the domain (Feishu/Lark notifications) and two concrete capability modes ('push-only (webhook)' and 'interactive (bidirectional)'), but the only stated action verb is 'Send notifications' — it does not enumerate multiple concrete actions like webhook firing, reply polling, or status updates. This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'; it is not a 4 because several specific actions present in the body are absent from the description.

3 / 5

Completeness

Explicitly answers both 'what' ('Send notifications to Feishu/Lark... Supports push-only (webhook) and interactive (bidirectional) modes') and 'when' ('Use when user says "发飞书", "notify feishu", or other skills need to send status updates') with concrete trigger phrases, matching the anchor for clearly and explicitly answering both. Voice is third person ('Send', 'Supports', 'Use when'), so no voice penalty applies.

5 / 5

Trigger Term Quality

Includes natural trigger phrases users would actually say — '"发飞书"', '"notify feishu"', 'send status updates' — plus the Feishu/Lark synonym pair. Good keyword coverage matching 'a few natural terms missing'; not a 5 because the anchor expects comprehensive synonym/extension coverage and a few plausible natural variants (e.g. 'send a Lark message') are not present.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Feishu/Lark integration) with distinct, product-specific triggers ('发飞书', 'notify feishu', /feishu-notify) and minimal overlap risk with generic notification skills. Matches the 'Clear niche with distinct triggers; minimal conflict risk' anchor; not lowered because the platform specificity makes misfiring unlikely.

5 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
OpenLAIR/dr-claw
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.