CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

new-project

Use when invoked as $new-project or when creating a brand-new repository or project from scratch — scaffolds mise-pinned tools, a just task surface, the standard repo files, and CI for Python (uv), TypeScript (bun), Rust (cargo), or Go.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/new-project/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 a harness-generated redirect stub: maximally lean, but it delegates 100% of the skill's substance to an external path that does not ship with the bundle. As written, it provides no workflow, no task guidance, and no verifiable reference structure. The conciseness is exemplary, but actionability, workflow clarity, and progressive disclosure all suffer from the total absence of in-bundle content.

Suggestions

Inline a concise overview of the scaffolding workflow (key steps and per-language tooling table) in SKILL.md so the skill remains useful when the shared path `~/.agents/skills/new-project/SKILL.md` is unavailable.

Replace the absolute home-directory reference with a bundled, relative reference (e.g., copy the shared content into references/ and link it), and remove or fix the dangling `scripts/agent-harnesses.py` mention so all referenced files actually exist in the skill.

Add a post-scaffold validation step (e.g., run `just` tasks or lint the generated CI) so the workflow includes a checkpoint after the batch file-creation operation.

DimensionReasoningScore

Conciseness

The body is two lines — a generation comment and a single load instruction — with zero padding and no re-explanation of concepts Claude already knows. Every token present earns its place, matching anchor 5 exactly; anchor 4 would require trimmable over-explanation that does not exist here.

5 / 5

Actionability

The one instruction — "Load and follow the shared skill at `~/.agents/skills/new-project/SKILL.md`" — is concrete and executable, but all guidance for the actual scaffolding task is delegated away, leaving key details absent from the body. This is anchor 3 (some concrete guidance but incomplete) rather than 4, since the body contains no actionable direction for the task itself, and above anchor 2 because the directive is specific, not a high-level hint.

3 / 5

Workflow Clarity

No sequence for the multi-step scaffolding process appears in the body — only a single coherent delegation directive with no validation checkpoints. It sits above anchor 1 because the one instruction present is unambiguous, but below anchor 3 because no actual work steps are listed at all, leaving many gaps as in anchor 2.

2 / 5

Progressive Disclosure

The reference is clearly signaled and one level deep, but the body is a pure redirect with no overview content, and neither referenced path exists in the bundle (`~/.agents/skills/new-project/SKILL.md` is outside the skill and unverifiable; `scripts/agent-harnesses.py` is absent). This matches anchor 3 (some structure, organization concerns) rather than 4, since content is not appropriately placed or split within the skill itself.

3 / 5

Total

13

/

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.

The description is strong: it states concrete, tool-specific capabilities and pairs them with an explicit 'Use when' clause containing natural trigger phrases. Its only weaknesses are the unspecified "standard repo files" and missing synonyms like "scaffold" or "set up". Conflict risk is low given the distinctive toolchain naming.

DimensionReasoningScore

Specificity

Lists several concrete, named actions — "scaffolds mise-pinned tools, a just task surface, ... and CI for Python (uv), TypeScript (bun), Rust (cargo), or Go" — but "the standard repo files" is unspecified, leaving a minor coverage gap. This matches anchor 4 (several specific actions, minor gaps) rather than 5, and is well above anchor 3's 1-2 actions.

4 / 5

Completeness

Explicitly answers "when" with a concrete "Use when invoked as $new-project or when creating a brand-new repository or project from scratch" clause and "what" with specific scaffolding actions and named per-language tooling. This clearly matches anchor 5 (both what and when with concrete trigger phrases); the 4 anchor requires a weaker or less explicit 'when', which does not apply.

5 / 5

Trigger Term Quality

Natural triggers like "creating a brand-new repository or project from scratch" and "invoked as $new-project" are present, but common variations users might say — "scaffold", "set up", "initialize", "boilerplate", "starter" — are missing. Good coverage without being comprehensive puts this at anchor 4, above anchor 3's partial keyword set and below anchor 5's full synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The from-scratch scaffolding niche with a named toolchain (mise, just, uv/bun/cargo/Go CI) and the distinct "$new-project" invocation make it mostly distinct with only minor overlap risk against generic project-setup or language-specific init skills. Anchor 4 fits better than 5 because "creating a brand-new repository or project" remains somewhat broad as a trigger.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

phatblat/dotfiles

Path

.claude/skills/new-project/SKILL.md

Reviewed

Table of Contents

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.