estimate

Estimates task effort by analyzing complexity, dependencies, historical velocity, and risk factors. Produces a structured estimate with confidence levels.

Quality

76%

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 ./.claude/skills/estimate/SKILL.md

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, highly actionable, and clearly sequenced with appropriate gating for a read-only estimation skill. Its main weakness is progressive disclosure: everything lives in one file with a large inline template and no external references.

Suggestions

Extract the estimate markdown template into a reference file (e.g. references/estimate-template.md) and link to it from Phase 4, keeping SKILL.md as a lean overview.

Add a brief 'Inputs / Prerequisites' note pointing clearly to the CLAUDE.md, design/gdd/, and production/sprints/ sources so the reading path is signaled up front.

Dimension	Reasoning	Score
Conciseness	The body is lean: short phased bullet lists and an output template, with no explanation of concepts Claude already knows and no padded prose; the large markdown block is the deliverable rather than wasted context, so most tokens earn their place.	3 / 3
Actionability	For an instruction-only skill it gives concrete, specific guidance — exact paths ('design/gdd/', 'production/sprints/'), explicit rules ('Round to half-day increments', 'recommended budget should be the expected estimate'), and a complete fill-in template, which per the scoring notes is not penalized for lacking code.	3 / 3
Workflow Clarity	Phases 1–5 are clearly sequenced with an explicit clarification gate ('If the description is too vague... ask for clarification before proceeding') and confidence-based next steps; as a non-destructive, read-only skill it does not require the heavy validation feedback loops the rubric reserves for destructive/batch operations.	3 / 3
Progressive Disclosure	It is a single ~120-line file with no bundle references and well-organized sections, but the bulk is a large inline markdown template that could be split into a separate reference file, matching the 'content that should be separate is inline' anchor rather than the well-signaled one-level-deep reference pattern.	2 / 3
	Total	11 / 12 Passed

Description

60%

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 specific and clearly states what the skill does, but it omits any explicit 'when to use' trigger guidance and relies on somewhat technical vocabulary, which limits trigger-term quality and distinctiveness.

Suggestions

Add a 'Use when...' clause naming natural user triggers, e.g. 'Use when the user asks how long a task will take, wants an effort or time estimate, or needs story-point sizing.'

Soften jargon ('historical velocity', 'confidence levels') in favor of phrases users actually say, and add common variants like 'time estimate' or 'story points'.

Make the trigger explicit enough to distinguish this skill from generic project-management or sprint-planning skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'analyzing complexity, dependencies, historical velocity, and risk factors' and 'Produces a structured estimate with confidence levels' — matching the anchor that lists several specific actions rather than a vague domain reference.	3 / 3
Completeness	It clearly answers 'what' the skill does but contains no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some relevant terms ('task effort', 'complexity', 'risk factors') but leans on internal jargon ('historical velocity', 'confidence levels') and omits natural user phrasings like 'how long will this take', 'time estimate', or 'story points', so it has some keywords but not full coverage.	2 / 3
Distinctiveness Conflict Risk	Task-effort estimation is a recognizable niche, but without explicit triggers it could overlap with broader project-planning or sprint-management skills, matching the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/estimate/SKILL.md
Commit: 984023d

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.