CtrlK
BlogDocsLog inGet started
Tessl Logo

implementing-agent-modes

Guidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what conditions. Achieve better results using your plan mode.

54

Quality

60%

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 ./.agents/skills/implementing-agent-modes/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.

The body is a well-structured, actionable workflow with concrete commands and file paths. It is slightly verbose in its conceptual opening and lacks an explicit validation checkpoint, but it navigates clearly and is mostly copy-paste ready.

Suggestions

Trim the opening paragraph that re-explains what a mode is; assume Claude understands the concept after the description.

Add an explicit validate-then-proceed checkpoint (e.g., run schema build/tests and confirm before moving to the next step).

Consider moving the detailed feature-flag code example into a referenced file to keep the main flow lean.

DimensionReasoningScore

Conciseness

Mostly efficient step-by-step instructions, but it opens by re-explaining what a mode is ('A mode is a way to manage the context...') and includes explanatory asides that Claude could infer.

3 / 5

Actionability

Provides concrete file paths and executable commands ('hogli build:schema', 'pnpm run schema:build') plus a code example, with only minor gaps in how each step's edits are specified.

4 / 5

Workflow Clarity

A clear, sequenced multi-step process with headers and a user loop-back checkpoint for tool dependencies; validation is implicit (tests/feature-flag rules) rather than an explicit validate-then-proceed loop.

4 / 5

Progressive Disclosure

Well-organized into logical sections with no nested references and no bundle files, though the single file runs longer than ideal and could split reference details out.

4 / 5

Total

15

/

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 the skill's purpose but explains what modes are instead of stating when to invoke the skill, and it lacks natural trigger phrases. It is specific enough to avoid most conflicts but would benefit from an explicit 'Use when...' clause.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when creating or updating a PostHog AI agent mode').

Replace the conceptual explanation of modes with more concrete capability verbs (create, update, scaffold, feature-flag, test a mode).

Add natural trigger synonyms users might say, such as 'agent mode', 'toolkit mode', or 'PostHog chat agent mode'.

DimensionReasoningScore

Specificity

Names the domain ('new mode for PostHog AI agent') and a concrete action ('create/update') but does not list several specific actions, and much of the text explains the concept rather than capabilities.

3 / 5

Completeness

Gives a clear 'what' (guidelines to create/update a mode) but lacks any 'Use when...' trigger; 'Achieve better results using your plan mode' is not a usage trigger, so completeness is capped at 3.

3 / 5

Trigger Term Quality

Contains relevant keywords ('mode', 'PostHog AI agent') but offers few natural user phrases and no synonyms or file extensions a user would actually say.

3 / 5

Distinctiveness Conflict Risk

The niche is fairly specific (PostHog AI agent modes), making overlap risk low, though the generic word 'mode' could mildly overlap with other agent-config skills.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
PostHog/posthog
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.