CtrlK
BlogDocsLog inGet started
Tessl Logo

tessleng/sdlc-router

A lightweight router that composes planning, implementation, debugging, verification, review, and handoff skills into one delivery workflow.

65

Quality

82%

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

Overview
Quality
Evals
Security
Files

Quality

Content

92%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 tight, well-structured router skill that sequences delivery stages with explicit verification and review feedback loops. It is lean and assumes Claude's competence, with the only weakness being a lack of concrete executable artifacts typical of an instruction-only router.

DimensionReasoningScore

Conciseness

The body is lean (~25 lines) with no padding or explanation of concepts Claude already knows; every line is directive and earns its place.

5 / 5

Actionability

Concrete routing instructions name specific skills at specific triggers ('Load `writing-plans` when...', 'Load `systematic-debugging` when a test fails'), but as an instruction-only router it offers no executable code/commands, leaving minor gaps.

4 / 5

Workflow Clarity

A clear numbered 1-6 stage sequence with explicit verification (stage 4) and a review feedback loop ('If it returns valid findings... return to verification') plus a safety gate on integration (stage 6).

5 / 5

Progressive Disclosure

Under 50 lines with no bundle files needed; well-organized into 'Required stage loading' and 'Routing contract' sections and one-level references to named installed skills.

5 / 5

Total

19

/

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 clearly answers what and when in third person with a specific niche, but it relies on end-states rather than enumerating concrete actions and misses common synonym trigger terms users would naturally say.

Suggestions

Add a few concrete action verbs to the description (e.g., plan, implement, test, verify, review) so it lists specific actions rather than only end-states.

Broaden trigger terms with natural synonyms users say, such as 'implement a task', 'build a feature', or 'deliver a change'.

Consider adding one or two more concrete trigger phrases in the 'when' clause to reach the comprehensive, multi-trigger phrasing of the top anchor.

DimensionReasoningScore

Specificity

Names the domain and concrete end-states ('verified, reviewed, PR-ready local change') but describes the journey rather than listing several specific concrete actions, fitting the 'names domain and 1-2 concrete actions' anchor rather than the multi-action anchor at 4.

3 / 5

Completeness

Explicit 'Use when...' clause gives a clear trigger and the 'what' (carry an approved task to a PR-ready change) is clear, but the 'when' is a single condition rather than multiple concrete trigger phrases as in the 5 anchor.

4 / 5

Trigger Term Quality

Contains some relevant natural terms (PR-ready, reviewed, verified) but misses common variations or synonyms (implement, build, deliver, ship) users would actually say.

3 / 5

Distinctiveness Conflict Risk

A clear niche (routing an approved engineering task through staged delivery skills) with mostly distinct triggers, but 'engineering task to PR-ready change' could overlap with general implementation skills.

4 / 5

Total

14

/

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.

Reviewed

Table of Contents