analyze-context

Estimate total token usage and cost across conversation history, system prompts, and active rules. Use when the user asks how much context or how many tokens are in use, to audit context size, or to estimate session cost.

Quality

77%

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 ./plugins/flowai-engineering/skills/analyze-context/SKILL.md

Quality

Content

71%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 compact, actionable estimation guide with a real supporting script and a worked example. Its main weakness is moderate repetition of the formula and multiplier across sections, which inflates token cost without adding clarity.

Suggestions

State the multiplier (0.3) and character-count formula once in Estimation Method; have the Tools section reference it rather than restating "Total Chars * 0.3".

Show how to pass the full conversation/system context into count_tokens.ts (e.g., via stdin) so the executable path matches the described scope, not just a text snippet.

Add a brief sanity-check step in the Procedure (e.g., compare estimated tokens against the model's known context limit) to give the workflow a verification checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but restates the 0.3 multiplier and the character-count formula in both the Estimation Method and Tools sections, and the Procedure recapitulates guidance that could be tightened.	3 / 5
Actionability	It provides an executable command (`deno run scripts/count_tokens.ts "TEXT_snippet"`) backed by a real script, plus a manual formula and a fully worked numeric example, with only minor gaps such as how to feed large history into the script.	4 / 5
Workflow Clarity	The Procedure lays out a clear numbered sequence (Conversation, System/Rules, Overhead, Total, Report) culminating in a report step; this is a read-only estimation task so absent validation checkpoints are not disqualifying, though no verification of the estimate is suggested.	4 / 5
Progressive Disclosure	At roughly 45 lines with well-organized sections and a single one-level-deep reference to a real bundled script (scripts/count_tokens.ts), it fits the simple-skill exception of well-organized sections scoring 5.	5 / 5
	Total	16 / 20 Passed

Description

83%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 is well-constructed: third person, explicit trigger guidance, and concrete enumeration of the components it analyzes. It is strong on completeness and only slightly soft on specificity and trigger-term breadth.

Dimension	Reasoning	Score
Specificity	"Estimate total token usage and cost across conversation history, system prompts, and active rules" names the domain and enumerates several concrete components, but the core action remains a single verb (estimate) rather than multiple distinct actions, leaving minor coverage gaps.	4 / 5
Completeness	It clearly states what it does (estimate token usage and cost across named components) and provides an explicit "Use when..." clause with multiple concrete trigger phrases, satisfying both what and when.	5 / 5
Trigger Term Quality	"how much context or how many tokens are in use", "audit context size", and "estimate session cost" are natural user phrases with good coverage, though common variants like "context window" or "token limit" are absent.	4 / 5
Distinctiveness Conflict Risk	Token/context-cost estimation is a distinct niche with specific triggers, but broad phrases like "audit context size" carry minor overlap risk with general analysis skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai-engineering/skills/analyze-context/SKILL.md
Commit: ad81ae6

Reviewed: 8 hours 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.