CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

An exceptionally actionable, well-sequenced workflow: executable commands, complete scaffold templates, explicit verification checkpoints, and error-recovery loops throughout. Its only structural weakness is that everything lives inline in one long file rather than splitting the scaffold recipe into a one-level-deep reference file.

DimensionReasoningScore

Conciseness

The body is directive and assumes competence — every section instructs rather than explains — with only minor trimmable redundancy ('vite build must run first' is repeated in steps 3, 4, and the Rules) and rot-prone pinned dev-dependency versions. Efficient but not the every-token-earns-its-place leanness of a 5, and well above the padding of a 3.

4 / 5

Actionability

Fully executable throughout: concrete git/gh/npm/wrangler/curl commands, complete 7-file scaffold templates whose placeholders (<APP_NAME>, <AGENT_CLASS>) carry explicit substitution rules (kebab-case binding mapping, today's compatibility_date), and a ready-to-run publish script. Copy-paste ready with specific examples covering the common cases.

5 / 5

Workflow Clarity

A clearly numbered 0-8 sequence with explicit validation checkpoints (sanity-check 'npx vite build' before deploy, curl verification of the deployed URL, 'Only set reproduced: true if you observed the bug'), feedback loops ('If it fails for an unrelated reason, fix the scaffold and retry'), and fallbacks (branch-protection rejection handling). Matches the validate-fix-retry anchor exactly.

5 / 5

Progressive Disclosure

Sections are well-organized, but the skill is a single monolithic ~345-line file with no references/scripts/assets bundle at all; the ~150-line scaffold recipe (7 file templates plus rules) is inline content that clearly belongs in a separate reference file. This is the 'some structure but content that should be separate is inline' case — not the 2 anchor's absent structure, but short of the 4 anchor's appropriate splitting.

3 / 5

Total

17

/

20

Passed

Description

70%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, action-oriented, and highly distinct thanks to naming the exact repository and deployment target. Its main weakness is the complete absence of a 'when to use this' clause, which caps completeness and slightly weakens trigger coverage.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when an agent-think run targets a cloudflare/agents GitHub issue that needs an end-to-end reproduction.'

Include natural trigger synonyms such as 'bug', 'repro', and 'reproduction steps' alongside 'reproduce' to broaden keyword coverage.

Mention the possible verdicts (reproduced / could not reproduce / skipped) so the scope of the reporting behavior is explicit in the description.

DimensionReasoningScore

Specificity

Names 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 gaps (verification and repro-branch publishing are not mentioned). It is more comprehensive than the 3 anchor's 1-2 actions but not the full coverage of a 5.

4 / 5

Completeness

The 'what' is clear (reproduce an issue by scaffolding, deploying, and reporting back), but there is no 'Use when...' clause or equivalent explicit trigger guidance. Per the judging guidelines, a missing 'when' caps completeness at 3.

3 / 5

Trigger Term Quality

'Reproduce', 'GitHub issue', 'Cloudflare', 'deploy' are natural phrases a user or agent would say when needing this skill, but common variations like 'bug', 'reproduction steps', or 'repro' are missing. Good coverage, a few natural terms absent — a 4, not the synonym-and-extension completeness of a 5.

4 / 5

Distinctiveness Conflict Risk

Pins the exact target ('cloudflare/agents GitHub issue'), the Agents/Worker stack, and temporary Cloudflare accounts — a clear niche with distinct triggers and minimal overlap with other skills. Confirmed against the 4 anchor: there is no meaningful overlap risk with closely related skills here.

5 / 5

Total

16

/

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

cloudflare/agents

Path

agent-think/skills/reproduce/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.