Tessl • The package manager for agent skills

SkillPublic

brief

Write or update `brief.md` for shaping. Use when asked to create a project or feature brief, a 1-2 pager, or to turn rough inputs into goals, non-goals, scope, risks, and open questions.

Quality

82%

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

Quality

Content

72%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 exceptionally lean and well-organized for a simple single-purpose skill, but its guidance is underspecified for execution: no brief template or example, undefined jargon, and a workflow with broken step numbering and no validation checkpoint. Fixing those would lift actionability and workflow clarity substantially.

Suggestions

Add a short `brief.md` template (section headings for problem, appetite, goals/non-goals, perimeter, risks, open questions) so the output structure is unambiguous.

Fix the workflow step numbering (two steps are labeled "4)" and "5)" is skipped) and turn the "Ensure" list into an explicit validation step (re-check the drafted brief against each item and revise before returning).

Briefly define opaque terms like "perimeter", "de-scope", and "shaping decision placeholder", or show them as headings in the template.

Dimension	Reasoning	Score
Conciseness	The body is lean with zero padding — purpose, inputs, a short workflow, and the output file — and assumes Claude's competence throughout, matching the "every token earns its place" anchor.	5 / 5
Actionability	The workflow and checklist ("risks/unknowns (<=10), open questions (<=10)") give some concrete guidance, but there is no template or example of `brief.md`'s structure and terms like "perimeter", "de-scope", and "shaping decision placeholder" are unexplained — key details for producing the artifact are missing.	3 / 5
Workflow Clarity	The sequence (read inputs, clarify, draft, constrain, return) is present, but the step numbering is broken (two steps labeled "4)", no "5)") and the "Ensure" checklist is not framed as a validation checkpoint with a fix-and-recheck loop.	3 / 5
Progressive Disclosure	This is a simple, single-purpose skill under 50 lines with well-organized sections (Purpose, Inputs, Workflow, Output) and no need for external references, so the simple-skill exception applies and the structure scores full marks.	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.

A strong description that clearly states what the skill does and when to use it, with natural trigger phrases like "project or feature brief" and "1-2 pager". It could be marginally improved by adding synonyms (one-pager, charter) and broadening action coverage.

Dimension	Reasoning	Score
Specificity	"Write or update `brief.md`" and "turn rough inputs into goals, non-goals, scope, risks, and open questions" name several concrete actions and the exact artifact, but coverage is narrower than the comprehensive multi-action anchor 5 example.	4 / 5
Completeness	It explicitly answers both: what ("Write or update `brief.md` for shaping") and when ("Use when asked to create a project or feature brief, a 1-2 pager, or to turn rough inputs into...") with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Natural user phrases like "project or feature brief", "1-2 pager", "goals, non-goals", "scope", "risks", and "open questions" are present; a few common synonyms (e.g., "one-pager", "charter") are missing, so it falls just short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The `brief.md`/shaping niche is mostly distinct with specific triggers, but the generic word "brief" leaves minor overlap risk with general writing or planning skills, so it sits at anchor 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: marchatton/agent-skills
Path: .agents/skills/02-shape/brief/SKILL.md
Revision: a0eadb2

Reviewed: 13 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.

brief

Table of Contents

Is this your skill?