CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

architect

Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.

71

Quality

89%

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

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.

An exemplary orchestration skill body: lean and dense prose, a crisply sequenced five-phase workflow with real feedback loops, and clean progressive disclosure into three verified one-level-deep reference files. The only gap is partial dependence on external ecosystem skills and a rule file, mitigated by explicit fallbacks.

DimensionReasoningScore

Conciseness

Every phase is prescriptive and dense ("Naming a file isn't grounding", "The synthesized sketch is the contract", "Complexity in the data is not complexity in the design") with zero padding, and detail is delegated to sibling skills and reference files rather than re-explained. Lean and efficient — every token earns its place, matching anchor 5.

5 / 5

Actionability

Guidance is consistently concrete for an instruction-only skill: run named skills (**how**, **why**, **arena**, **interrogate**), "Pass `references/runner-prompt.md` as each runner's prompt", explicit fallback runners ("claude-opus-5-5-xhigh" and "grok-4.7-xhigh-fast"), explicit skip conditions, and concrete scrap tells. Not anchor 5 because execution depends on external skills and a `pstack-models.mdc` rule outside the bundle, so it is not fully self-contained even with the fallback.

4 / 5

Workflow Clarity

Five named phases (Ground, Sketch, Agree, Implement, Scrap) sequenced with a prescribed todolist, an explicit Phase A skip rule, a clear default-vs-opt-in checkpoint, and strong feedback loops: deviations are "signal to surface", human pushback re-enters Phase A, and scrap tells trigger re-ground → redesign → return to Phase B. Clear sequence with explicit validation signals and error-recovery loops — anchor 5.

5 / 5

Progressive Disclosure

The body is a genuine overview that splits detail into three real, one-level-deep reference files (design-red-flags.md linked; runner-prompt.md and rationale-template.md cited by path in actionable context), verified to exist with no nested reference chains. Content is appropriately split and navigation is easy — anchor 5.

5 / 5

Total

19

/

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: concrete third-person actions, an explicit "Use for" clause with natural trigger phrases, and a clear design-before-code niche. The only weaknesses are minor — a few missing trigger synonyms and slight overlap risk with generic planning/design skills.

DimensionReasoningScore

Specificity

"Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in" names several concrete third-person actions with only minor coverage gaps (e.g., synthesis and scrap phases are unmentioned). It lists more than the 1-2 actions of anchor 3 but is not the comprehensive coverage of anchor 5.

4 / 5

Completeness

It clearly answers "what" (sketch types, signatures, and module structure, then stay in the loop during implementation) and "when" via an explicit "Use for" clause with concrete trigger phrases. This matches the anchor-5 example structure of explicit what AND when with concrete triggers.

5 / 5

Trigger Term Quality

Triggers "/architect", "'architect this'", "'design this'", and "non-trivial work where jumping to code would lock in the wrong shape" are natural phrases a user would say, but common synonyms like "plan the architecture" or "sketch the design" are missing. Good coverage with a few natural terms absent — anchor 4, not the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The design-first niche (types and module shape before code) is mostly distinct with clear triggers, but "design this" and the broad "non-trivial work" condition could overlap with general planning or UI-design skills. Minor overlap risk with closely related skills — anchor 4, not the minimal-conflict clarity of anchor 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

cursor/plugins

Path

harness/pstack/claude-code/skills/architect/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.