Tessl • The management layer for AI agent skills

SkillPublic

estimate

Use when planning a feature and need to understand token cost, time estimate, or complexity before committing to implementation.

Quality

67%

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 ./skills/estimate/SKILL.md

Quality

Content

60%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 content is well-structured with a clear five-step workflow and useful tables, but it has notable gaps: the scope-analysis step contains only pseudocode comments instead of executable search commands, and the Anti-Rationalization section is non-actionable padding. Undefined comparison targets ('Superpowers', 'Specialist Agent') and undated volatile pricing further weaken actionability and conciseness.

Suggestions

Replace the comment-only pseudocode in Step 1 with actual executable commands using the declared tools (e.g., Glob patterns to find affected files, Grep to count matching lines), since allowed-tools already permits them.

Remove or drastically trim the Anti-Rationalization section — it argues for the skill's value rather than instructing Claude how to execute it.

Define or remove the undefined comparison fields ('Superpowers estimate', 'Specialist Agent estimate') and consider moving the volatile model-pricing tables to a reference file so stale prices don't clutter the main skill.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient tables and templates, but the 'Anti-Rationalization' section ("Rough estimates beat no estimates", "Every token has a cost...") is motivational padding that adds no instruction Claude needs. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' — not 4 because that section is several lines of pure filler.	3 / 5
Actionability	Steps 2-5 provide concrete tables and output templates, but Step 1's scope analysis is comment-only pseudocode ("# Find affected files", "# Count existing lines") with no actual Glob/Grep commands despite allowed-tools declaring them, and the 'Superpowers estimate'/'Specialist Agent' comparison fields are undefined. This matches 'some concrete guidance but incomplete; pseudocode instead of executable code'.	3 / 5
Workflow Clarity	The five steps (Analyze Scope, Classify Complexity, Break Down Costs, Compare Models, Provide Recommendations) are clearly sequenced with concrete criteria at each stage. Not 5 because there are no validation or sanity-check checkpoints (e.g., cross-checking counted files/lines against the complexity table before classifying), though the read-only nature of the skill makes this a minor gap.	4 / 5
Progressive Disclosure	The skill is a single self-contained file with clear section headers and no nested or buried references, and at ~150 lines the inline placement of most content is appropriate. Not 5 only because the Cost Reference pricing tables (per-1M-token prices, typical task costs) are volatile reference data that could live in a separate one-level-deep reference file.	4 / 5
	Total	14 / 20 Passed

Description

61%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 has a strong, explicit 'Use when...' trigger with reasonably natural keywords, but it defines only when to use the skill and never states what the skill actually does. Adding an explicit capability statement and a few natural synonyms would raise both completeness and trigger coverage.

Suggestions

Add an explicit 'what' clause, e.g., 'Estimates token usage, cost, and complexity for a proposed feature... Use when planning a feature and you need a cost, time, or complexity estimate before committing to implementation.'

Include natural trigger variations users would say, such as 'estimate', 'budget', 'how much will this cost', 'how long', or 'effort', to broaden keyword coverage.

Tighten distinctiveness by leading with the skill's unique function (cost/token estimation) rather than the broad framing 'planning a feature', which overlaps with general planning skills.

Dimension	Reasoning	Score
Specificity	The description names the domain and concrete deliverables ("understand token cost, time estimate, or complexity") but lists no concrete actions the skill performs. It matches the anchor 'names domain and 1-2 concrete actions, but not comprehensive' — not 4 because no capability verbs are given, and not 2 because three specific outputs are named rather than generic language.	3 / 5
Completeness	The 'when' is explicit ("Use when planning a feature... before committing to implementation") but the 'what' is only implied — the description never states what the skill does (e.g., 'Estimates token usage and cost...'). This sits between anchor 2 (only 'when' present without 'what') and anchor 4 (both explicit), so it lands at 3.	3 / 5
Trigger Term Quality	Phrases like "planning a feature", "token cost", "time estimate", and "complexity" are terms a user would naturally say when needing this skill, giving good keyword coverage. Not 5 because common synonyms and variations ("estimate", "budget", "effort", "how much", "how long") are missing.	4 / 5
Distinctiveness Conflict Risk	Token-cost/time/complexity estimation for feature planning is a mostly distinct niche with clear triggers. Minor overlap risk remains with general planning or architecture skills via the broad terms "planning a feature" and "complexity".	4 / 5
	Total	14 / 20 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: fernandezbaptiste/specialist-agent
Path: skills/estimate/SKILL.md
Revision: cd716d9

Reviewed: 8 days ago

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.

estimate

Table of Contents

Is this your skill?