CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

composio

Show the app connection picker or setup widget when users ask to connect apps, reopen setup, or need an app that isn't connected yet. Use QM’s authenticated backend for app discovery, consent, and execution without exposing project keys.

Quality

85%

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

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.

An exceptionally actionable, well-validated procedural skill: concrete code, exact directives, explicit verification steps, and feedback loops for every failure mode. Its only weaknesses are mild Slack-related redundancy across sections and a length that could push API detail into reference files.

DimensionReasoningScore

Conciseness

The body is dense and operational with no explanations of concepts Claude already knows, but at ~85 lines it carries minor redundancy (Slack directives and admin-install steps restated across two sections) and detail that could be trimmed, matching 'efficient; minor instances of over-explanation that could be trimmed' rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Fully executable throughout: a copy-paste `apps()` fetch helper, exact directives (`::connect-apps{toolkit="notion"}`), exact endpoints and parameters, and concrete failure modes with numbers (`providerStatus: 413`, batches of about 25, 5 MB media cap) — squarely the 'copy-paste ready; specific examples cover the common cases' anchor.

5 / 5

Workflow Clarity

The numbered 5-step API sequence includes explicit validation checkpoints ('only claim success once the returned account ID is listed', 'Inspect `successful` and `error`'), feedback loops for error recovery (403 → missingScopes → offer reconnect; 502 → back off and shrink the page), and guards on the destructive disconnect operation ('can't be undone', 'never before'), matching the top anchor.

5 / 5

Progressive Disclosure

Sections are clearly headed and there are no nested or buried references (no bundle files exist), but the ~85-line body inlines substantial API detail (bulk reads, X media upload) that could sit in one-level-deep reference files, and it exceeds the under-50-line simple-skill threshold — fitting 'good structure; most content appropriately placed; minor organization gaps'.

4 / 5

Total

18

/

20

Passed

Description

75%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 third-person description with concrete actions and an explicit trigger clause. Its main weakness is incomplete coverage: reconnect/disconnect flows and natural app-name or synonym triggers that the body handles are absent from the description.

Suggestions

Add trigger phrases for the reconnect/disconnect flows the body covers, e.g. 'or when an app needs reconnecting due to missing permissions'.

Include natural synonyms and concrete app names users would say, such as 'integrations', 'link an account', or 'Slack, Gmail, Notion', to broaden trigger-term coverage.

Consider briefly naming the disconnect capability ('disconnect connected accounts') so the 'what' matches the skill's full scope.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Show the app connection picker or setup widget', 'app discovery, consent, and execution', 'without exposing project keys' — but omits the reconnect/disconnect actions the skill body covers, matching the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor 5.

4 / 5

Completeness

Both 'what' (show the connection/setup widget via QM's authenticated backend) and 'when' (users ask to connect apps, reopen setup, or need an unconnected app) are explicit; however, the 'when' clause omits reconnect/disconnect triggers that make up a large part of the skill, so it falls short of the 'clearly and explicitly answers both with concrete trigger phrases' full-coverage anchor 5.

4 / 5

Trigger Term Quality

Natural user phrases like 'connect apps', 'reopen setup', and 'need an app that isn't connected yet' are present, but common variations such as 'integration', 'link account', or any app names (Slack, Gmail) are missing, fitting 'good keyword coverage; a few natural terms missing' rather than the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The QM-specific framing ('QM's authenticated backend', 'project keys') carves a distinct niche with minimal conflict risk, though the generic phrase 'connect apps' leaves minor overlap with other integration skills, matching 'mostly distinct; minor overlap risk'.

4 / 5

Total

16

/

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

yc-software/qm

Path

skills-seed/composio/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.