CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

delivery-flow

Use when an engineering task must be carried to a verified, reviewed, PR-ready local change: an approved ticket or requirements, a feature, or a bug fix, including a failing test, a crash, or a bug a user reported.

74

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 exemplarily lean router skill: concrete stage-by-stage routing with exact skill names, explicit conditions and guardrails (never push/merge/PR without authorization), a built-in verification checkpoint, and a review-findings feedback loop. As an instruction-only skill under 50 lines with no external references, it satisfies every content dimension at the top anchor.

DimensionReasoningScore

Conciseness

The 29-line body is lean and efficient: every sentence is a routing rule or boundary condition ('Mentioning a skill or paraphrasing it is not equivalent to loading it' is an enforcement rule, not padding), with no explanations of concepts Claude already knows. Every token earns its place.

5 / 5

Actionability

Fully concrete guidance for an instruction-only skill: exact skill names to load (writing-plans, executing-plans, test-driven-development, systematic-debugging, verification-before-completion, requesting-code-review, receiving-code-review, finishing-a-development-branch), explicit conditions ('only when the user explicitly asks to integrate, push, or create a pull request'), fallbacks ('For a narrow task, record a concise working plan instead'), and edge-case coverage including explanation-only requests.

5 / 5

Workflow Clarity

A numbered 1–6 stage sequence with an explicit validation checkpoint (load verification-before-completion 'before claiming completion or recording final verification evidence') and an explicit feedback loop (review findings → receiving-code-review → address them → return to verification). Clear sequencing, checkpoints, and error-recovery loop match anchor 5.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and its content is organized into well-signaled sections (Required stage loading, Routing contract). Per the rubric's simple-skill guideline, this earns a 5 with just well-organized sections.

5 / 5

Total

20

/

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.

A strong description: it explicitly states the deliverable outcome, uses an explicit 'Use when' trigger clause with concrete, natural task-type phrases, and stays lean without buzzwords. The main gaps are a few missing common trigger synonyms and slight overlap risk with single-technique skills whose territory its bug/test triggers share.

DimensionReasoningScore

Specificity

Concrete deliverable ('verified, reviewed, PR-ready local change') plus a broad enumeration of concrete task types ('approved ticket or requirements, a feature, or a bug fix, including a failing test, a crash, or a bug a user reported'). It stops short of anchor 5 because the capability is framed as a single carried-to-delivery outcome rather than a list of multiple distinct actions.

4 / 5

Completeness

Explicitly answers 'when' with an 'Use when...' clause carrying concrete trigger phrases, and explicitly answers 'what' via the stated outcome 'carried to a verified, reviewed, PR-ready local change'. Both what and when are clearly and explicitly present with concrete triggers, matching anchor 5.

5 / 5

Trigger Term Quality

Natural trigger phrases users would say: 'approved ticket', 'feature', 'bug fix', 'failing test', 'crash', 'a bug a user reported'. Good coverage, but common synonyms such as 'error', 'issue', 'regression', or 'defect' are absent, keeping it below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The end-to-end delivery framing ('verified, reviewed, PR-ready local change') carves a distinct niche, but triggers like 'a failing test, a crash, or a bug a user reported' overlap with dedicated debugging/TDD-type skills — minor overlap risk with closely related skills, matching anchor 4.

4 / 5

Total

17

/

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

tesslio/tessl-eval-demo

Path

00-activation-testing/before/plugins/sdlc-router/skills/delivery-flow/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.