python-sdk

Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/python-sdk/SKILL.md

Quality

Content

65%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 exemplary on token efficiency and progressive disclosure — a minimal overview pointing to a real, well-scoped reference file. Its weakness is substance: the body itself provides almost no actionable or workflow guidance, delegating everything to the reference, which caps actionability and workflow clarity at 3.

Suggestions

Replace the redundant line 'Use this skill for Python SDK implementation work.' with one or two concrete anchors that are always needed (e.g., the run-checks command from references/sdk-layout.md) so the body is self-sufficient for the most common task.

Add a minimal 2–3 step workflow (read layout → make change → run the setup/check commands) with an explicit validation checkpoint so edits are verified before finishing.

Inline one high-value convention (e.g., 'keep provider-specific behavior out of core') so the body delivers guidance even before the reference is read.

Dimension	Reasoning	Score
Conciseness	The body is three lines and assumes Claude's competence, but "Use this skill for Python SDK implementation work." merely restates the title and frontmatter description, so not quite every token earns its place. This is anchor 4 ('minor instances... that could be trimmed') rather than 5.	4 / 5
Actionability	There is one concrete, verifiable directive ("Read `references/sdk-layout.md` before editing `python/composio`"), but the body itself contains no commands, code, conventions, or examples — all substance is delegated to the reference. That is 'some concrete guidance but incomplete', anchor 3, not anchor 4's 'mostly executable guidance'.	3 / 5
Workflow Clarity	The single precondition (read the layout reference before editing) is unambiguous, but for a skill covering 'implement or modify' work the body offers no sequence of steps, no edit/verify checkpoints, and no guidance on what to do after reading. Anchor 3 ('sequence present but checkpoints missing') fits better than 4, since the body defers the entire workflow to the referenced file.	3 / 5
Progressive Disclosure	The body is a clear overview with a well-signaled, one-level-deep reference: `references/sdk-layout.md` exists, is concise (27 lines), and matches the body's pointer. Content is appropriately split with easy navigation, matching anchor 5 exactly.	5 / 5
	Total	15 / 20 Passed

Description

80%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, specific description with a clear what, an explicit when-clause, and comprehensive sub-area enumeration. Its weaknesses are minor: the trigger section lacks concrete user-facing trigger phrases and common synonyms, and the 'Python core runtime/API work' phrasing leaves some overlap risk with adjacent skills.

Suggestions

Add concrete trigger phrases to the when-clause, e.g., 'Use when the user asks to add or change a tool, toolkit, session handling, auth config, or connected-account flow in the Python SDK'.

Include natural synonyms users would actually say, such as 'composio' or 'Python client', to broaden keyword coverage beyond technical sub-area names.

Tighten 'Use for Python core runtime/API work' to reference the specific directory or component so it cannot fire on general Python work outside python/composio.

Dimension	Reasoning	Score
Specificity	The description states concrete actions ("Implement or modify Python SDK behavior") and comprehensively enumerates the SDK's sub-areas: "tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models". Coverage is comprehensive within the stated scope, matching the anchor-5 example's level of concrete enumeration rather than anchor 4's 'minor gaps'.	5 / 5
Completeness	Both parts are explicit: the what ("Implement or modify Python SDK behavior under python/composio, including...") and the when ("Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity..."). The when-clause could be more specific with concrete user trigger phrases (e.g., "when the user asks to add a tool or fix a toolkit"), which is exactly anchor 4's 'when could be more explicit or specific'.	4 / 5
Trigger Term Quality	Natural domain terms are present ("Python SDK", "tools", "toolkits", "sessions", "auth configs", "connected accounts", "Python core runtime/API"), so it clears the good-coverage bar, but it misses common variations and synonyms a user might say, such as "composio", "Python client", or "SDK library", which anchor 5 expects.	4 / 5
Distinctiveness Conflict Risk	"under python/composio" pins a clear niche and the description even names adjacent skills (python-testing, cross-sdk-parity) to reduce confusion. However "Python core runtime/API work" is broad enough that general Python requests could match, so minor overlap risk with closely related skills remains — anchor 4 rather than 5.	4 / 5
	Total	17 / 20 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: ComposioHQ/composio
Path: .agents/skills/python-sdk/SKILL.md
Commit: 98b10d7

Reviewed: 3 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.