CtrlK
BlogDocsLog inGet started
Tessl Logo

reproduce

Reproduce a cloudflare/agents GitHub issue by scaffolding a minimal Agents/Worker project and deploying it to a temporary Cloudflare account, then report findings back on the issue.

60

Quality

70%

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 ./agent-think/skills/reproduce/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 skill is highly actionable with a clearly sequenced, validated workflow for reproducing and reporting cloudflare/agents issues, but it is long and inlines a large frontend template that would benefit from being split into a referenced file.

Suggestions

Move the 7-file minimal-frontend recipe into a references/ file (e.g. references/frontend-template.md) and keep only the key rules + a pointer in SKILL.md.

Trim explanatory phrasing such as 'House style: one flat project...' and rationale sentences that do not change the action.

Condense the repeated deploy/verify bash snippets into a single canonical block per step to reduce token load.

DimensionReasoningScore

Conciseness

The body is dense with niche operational specifics that earn their tokens, but at ~345 lines it is noticeably verbose — the 7-file frontend recipe and phrasing like 'House style: one flat project...' could be tightened, matching 'mostly efficient but could be tightened' rather than the lean 4.

3 / 5

Actionability

Fully executable, copy-paste-ready bash commands and complete file templates with clearly marked placeholders cover the common repro cases end-to-end, matching the 'fully executable; copy-paste ready' anchor.

5 / 5

Workflow Clarity

A clear numbered sequence (steps 0–8) with explicit validation checkpoints (sanity-check build, verify-the-reproduction curl probes), feedback loops (fix scaffold and retry on deploy failure), and decision gates (skip non-reproducible issues), satisfying the top anchor including for the outward-facing deploy/post/push operations.

5 / 5

Progressive Disclosure

Sections are well-headed, but no bundle files exist and the large inlined 7-file frontend recipe plus deploy/publish blocks are content that belongs in a separate reference file, fitting 'some structure but content that should be separate is inline' rather than the well-split 4.

3 / 5

Total

16

/

20

Passed

Description

62%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 specific and highly distinct, nailing a clear niche, but it omits an explicit 'Use when...' trigger clause and relies on domain jargon, which caps completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming the triggering situation (e.g. 'Use when asked to reproduce a cloudflare/agents issue or validate a bug report against the Agents SDK').

Soften the jargon with natural user-facing phrasing such as 'bug report' or 'repro' alongside 'Agents/Worker project'.

Consider stating the deliverable up front ('posts a repro comment on the issue') so the outcome is unambiguous.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'scaffolding a minimal Agents/Worker project', 'deploying it to a temporary Cloudflare account', 'report findings back on the issue' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the comprehensive 5.

4 / 5

Completeness

The 'what' is clear (reproduce by scaffolding, deploying, reporting) but there is no 'Use when...' clause or equivalent trigger guidance, so per the rubric completeness is capped at 3.

3 / 5

Trigger Term Quality

Relevant domain keywords like 'reproduce', 'GitHub issue', and 'Cloudflare' are present, but the phrasing leans on technical jargon (Agents/Worker, temporary account) and lacks common user-facing synonyms, matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

It targets a single narrow niche — cloudflare/agents GitHub issue reproduction with a temporary Cloudflare account — giving it distinct triggers and minimal conflict risk with other skills.

5 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cloudflare/agents
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.