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

79%

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.

A compact, well-structured skill with executable guidance and a clear procedure, and the calculation script is appropriately externalized and referenced. The main drag is mild over-explanation of concepts Claude already knows and a slightly hand-wavy overhead-estimation step.

Suggestions

Trim definitional padding (e.g. 'The core instructions defining the agent's behavior', '(often a significant overhead)') since Claude already knows what system prompts and tool definitions are.

Tighten or shorten the worked example, or move the verbose numeric breakdown into the body's report format rather than restating the arithmetic step by step.

Make the 'Overhead' estimation step more concrete (e.g. a per-tool token estimate) so the workflow's one soft step becomes a crisp checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with clear formula, multiplier, and procedure, but includes some unnecessary explanation of concepts Claude already knows (e.g. 'The core instructions defining the agent's behavior', '(often a significant overhead)') and a relatively padded worked example, matching the 'mostly efficient but could be tightened' anchor rather than the lean one above.	3 / 5
Actionability	Provides an executable script command ('deno run scripts/count_tokens.ts "TEXT_snippet"'), an explicit manual formula, and a fully worked numeric example; falls short of 5 because the bundled script only counts a snippet rather than producing the breakdown, so the real method is the manual calculation.	4 / 5
Workflow Clarity	A clear five-step procedure (Conversation, System/Rules, Overhead, Total, Report) that is well-sequenced for a non-destructive estimation task; the 'Overhead' step's heuristic buffer is hand-wavy rather than a crisp checkpoint, which keeps it just below the top anchor.	4 / 5
Progressive Disclosure	A compact, well-organized single file under 50 lines with clearly labeled sections, and the calculation logic is correctly split into a referenced bundle script (scripts/count_tokens.ts) that exists and is invoked inline, matching the simple-skill exception for a top score.	5 / 5
	Total	16 / 20 Passed

Description

87%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 description that clearly states what the skill does and when to use it, with natural trigger phrasing and a distinct niche. The only minor weakness is that the action vocabulary is somewhat narrow (estimate), keeping specificity just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain (token usage and cost) and enumerates several concrete components ('conversation history, system prompts, and active rules'), but the action set is essentially one verb (estimate) applied across targets rather than many distinct actions, so it falls just short of comprehensive.	4 / 5
Completeness	Explicitly answers both 'what' ('Estimate total token usage and cost across...') and 'when' ('Use when the user asks how much context or how many tokens are in use...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural user-facing phrases are well covered ('how much context', 'how many tokens are in use', 'audit context size', 'estimate session cost'), matching the 'good keyword coverage, a few natural terms missing' anchor; not a 5 because there are no additional synonyms or variant phrasings.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (context/token cost estimation) with distinct triggers that are unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	18 / 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: b4ba256

Reviewed: ~20 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.