CtrlK
BlogDocsLog inGet started
Tessl Logo

new-feat

Start a feature or fix in the English Street Ventures website repository. Clarify the observable result, inspect the Astro and Cloudflare setup, plan the files and verification, then implement on the current task branch.

62

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

78%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.

A lean, actionable, well-sequenced instruction skill with repo-specific invariants and honest reporting requirements. Its main structural gap is discoverability: the bundled skills-routing reference is never linked from the body, and verification commands are left unspecified.

Suggestions

Reference references/skills-routing.md from the body (e.g., in Before implementation) so the bundled routing guidance is discoverable rather than orphaned.

Give one or two concrete verification commands or check types (e.g., build/preview command) instead of the abstract "the checks that will verify it".

Add a short fix-and-re-verify loop in the Finish section so failed checks have an explicit recovery path.

DimensionReasoningScore

Conciseness

The body is 24 lean lines across three sections with zero padding: no explanation of what Astro, Cloudflare, or Wrangler are, and every sentence carries an instruction or a repo-specific constraint. It assumes Claude's competence and every token earns its place, matching anchor 5.

5 / 5

Actionability

Guidance is concrete for an instruction-only skill: exact files to inspect ("package.json, astro.config.mjs, wrangler.jsonc"), an exact invariant ("Astro output is dist; wrangler.jsonc serves that directory"), and precise rules (no client JavaScript, no unrequested deploys). It falls short of anchor 5 because the verification checks are named abstractly ("the checks that will verify it") with no example command or check type.

4 / 5

Workflow Clarity

A clear three-phase sequence (numbered "Before implementation" steps → "Implementation" constraints → "Finish") with checkpoints like "agree on the intended direction before building" and "Do not report an unrun check as passing". It misses anchor 5 because there is no explicit validate-fix-retry feedback loop or checklist around the verification steps.

4 / 5

Progressive Disclosure

Sections are well organized, but the bundle's reference file (references/skills-routing.md, routing to TDD, cloudflare, frontend-design and other skills) is never mentioned in the body — relevant reference content exists but is buried and not signaled. Per the guideline to score against the actual bundle structure, this matches anchor 3 ("references present but not clearly signaled") rather than the under-50-lines exception to 5.

3 / 5

Total

16

/

20

Passed

Description

66%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, concrete description that names the domain and specific workflow actions, but it lacks any "Use when..." trigger clause, capping completeness. Adding explicit trigger phrases and the finish/reporting step would round it out.

Suggestions

Add an explicit trigger clause, e.g. "Use when starting a new feature, bug fix, or change in this repository" to satisfy the 'when' half of completeness.

Include natural trigger variations users would say — "bug fix", "new feature", "change" — to broaden keyword coverage.

Mention the finish phase (summarize changes and verification results) so the described actions comprehensively cover the skill's workflow.

DimensionReasoningScore

Specificity

The description lists several concrete actions ("Clarify the observable result", "inspect the Astro and Cloudflare setup", "plan the files and verification", "implement on the current task branch") anchored to a named domain. It sits at anchor 4 rather than 5 because the finish/reporting phase of the workflow is omitted, leaving minor gaps in coverage.

4 / 5

Completeness

The "what" is explicit and concrete (clarify, inspect, plan, implement), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The "when" is only weakly implied by "Start a feature or fix", not 4-level explicit.

3 / 5

Trigger Term Quality

Natural terms users would say are present — "feature", "fix", "Astro", "Cloudflare", "implement" — but common variations like "bug", "new feature", or "build" are missing. Good coverage with a few natural terms absent matches anchor 4.

4 / 5

Distinctiveness Conflict Risk

Scoping to "the English Street Ventures website repository" with Astro and Cloudflare specifics creates a clear niche with minimal conflict risk. However, generic feature-work phrasing ("Start a feature or fix") without explicit trigger scoping leaves minor overlap risk with general development skills, matching anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Validation

100%

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
englishstreetventures/englishstreetventures.com
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.