project-skill-builder

Create project-specific Claude Code skills tailored to particular codebases, domains, or organizations. Workflow for analyzing project context, identifying skill opportunities, designing project-specific patterns, and building custom skills. Use when creating skills for specific projects, capturing project knowledge, building team-specific workflows, or developing domain-specific skill toolkits.

Quality

66%

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/project-skill-builder/SKILL.md

Quality

Content

53%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 concise and well-structured as an overview, but it stays at a high level of abstraction: it tells Claude what to consider rather than giving concrete commands, templates, or worked examples, and its validation step is vague. Adding executable guidance and a concrete validation checkpoint would most improve it.

Suggestions

Add at least one concrete, copy-pasteable artifact — e.g., a skeleton SKILL.md template or a sample project-context document — so the workflow steps have executable output rather than only bullet hints.

Make Step 5's validation concrete: specify how to test the built skill in the real project (e.g., run it on a representative task, check trigger phrasing against the project's actual commands) instead of 'Validate: Effective for team/project.'

De-duplicate the workflow: the 5 steps appear in Overview, the Workflow section, and Quick Reference — keep the full version in one place and reference it, freeing token budget for actionable detail.

Dimension	Reasoning	Score
Conciseness	The body is lean and bullet-driven without explaining concepts Claude already knows, but the 5-step workflow is restated three times (Overview, Workflow section, Quick Reference), which is minor repetition that could be trimmed, fitting 'efficient; minor instances of over-explanation' rather than the every-token-earns-its-place top anchor.	4 / 5
Actionability	Guidance is high-level hints only ('Understand: Codebase architecture', 'Find: Repetitive tasks', 'Use: development-workflow with project context') with no concrete code, commands, or real worked examples, matching 'minimal concrete guidance; high-level hints but missing the specific steps to execute.'	2 / 5
Workflow Clarity	The 5 steps are clearly sequenced with a named output per step, but validation is only vaguely invoked in Step 5 ('Validate: Effective for team/project') with no concrete checkpoint or feedback loop, fitting 'steps listed but validation gaps; checkpoints missing or implicit.'	3 / 5
Progressive Disclosure	Content is well-organized into clear sections (Overview, When to Use, Workflow, Examples, Quick Reference) with no bundle files needed, but the all-inline structure and repeated workflow summary leave minor organization gaps, fitting 'good structure; minor organization gaps' rather than the cleanly-split top anchor.	4 / 5
	Total	13 / 20 Passed

Description

78%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 well-constructed description that clearly states both purpose and trigger conditions with good natural-language keywords. Its main weakness is that the named actions are abstract process phases rather than concrete operations, which limits the specificity score.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several actions ('analyzing project context, identifying skill opportunities, designing project-specific patterns, and building custom skills'), but these are abstract process phases rather than concrete operations, so it sits between the 1-2-action and several-concrete-action anchors.	3 / 5
Completeness	It explicitly answers both 'what' (create project-specific skills via a 4-part workflow) and 'when' (Use when creating skills for specific projects, capturing project knowledge, building team-specific workflows, or developing domain-specific skill toolkits) with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The 'Use when' clause supplies natural phrases ('creating skills for specific projects, capturing project knowledge, building team-specific workflows'), giving good keyword coverage with only a few synonyms missing, fitting the 'good coverage, a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The project-specific skill-building niche is mostly distinct with concrete triggers, but it carries minor overlap risk with a generic skill-builder skill, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict top anchor.	4 / 5
	Total	16 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/project-skill-builder/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.