CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

technical-specification

Creates detailed technical specifications for software projects covering requirements, architecture, APIs, and testing strategies. Use when planning features, documenting system design, or creating architecture decision records.

Quality

83%

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

75%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 body is highly actionable — a complete copy-paste specification template with concrete best-practice Do/Don't lists — and it references a real, well-signaled, one-level-deep bundle file. Its main weakness is redundancy: the large inline template substantially duplicates references/template.md, inflating token cost without adding guidance, and the drafting workflow lacks an explicit review/validation loop.

Suggestions

Trim the inline 'Specification Template' to a short skeleton (section names plus one representative hint each) and point to references/template.md for the full version, eliminating the ~50% duplication between the body and the reference file.

Add a brief workflow for producing a spec (gather requirements → draft using the template → review against the Success Criteria checklist → iterate with stakeholders), making the implicit checkpoints explicit.

Add 2-3 lines of guidance on how to prioritize filling sections (e.g., always complete Non-Goals and Success Criteria first) so the template's placeholders translate into a drafting order.

DimensionReasoningScore

Conciseness

There is no explanation of concepts Claude already knows, but the ~75-line inline 'Specification Template' substantially duplicates references/template.md (metadata, requirements tables, API design, implementation plan, risks), which is unnecessary duplication that could be tightened. This fits 'mostly efficient but includes some unnecessary... content that could be tightened' rather than anchor 4's 'minor instances'.

3 / 5

Actionability

The body provides a complete, copy-paste markdown template with placeholder hints (e.g., '[2-3 sentences: What problem does this solve?]', 'FR-1 | [Description] | P0') plus concrete Do/Don't guidance ('Quantify performance targets', 'Don't use vague requirements ("fast", "scalable")'). Per the scoring notes for instruction-only skills, this concrete template guidance is fully actionable.

5 / 5

Workflow Clarity

The template sections impose a clear sequence (metadata → summary → goals → requirements → design → plan → testing → risks → success criteria) and include checkpoints like 'Get stakeholder review before implementation' and a Success Criteria checklist. It stays at 4 rather than 5 because there is no explicit drafting/review/validation loop for the spec-writing process itself, and at 4 rather than 3 because checkpoints are present, if implicit.

4 / 5

Progressive Disclosure

The bundle reference (references/template.md) exists, is one level deep, and is clearly signaled with a bulleted list of its contents ('Complete metadata section', 'Security threat analysis', etc.). It does not reach 5 because the inline template heavily duplicates the referenced file, so the split between body and reference is not as clean as 'content appropriately split'.

4 / 5

Total

16

/

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.

The description is strong: it uses third-person voice, states concrete coverage areas, and includes an explicit 'Use when...' trigger clause with natural phrases like 'architecture decision records'. Its only weaknesses are mild — a single core action rather than several distinct ones, and a few missing synonyms like 'design doc' or 'tech spec'.

DimensionReasoningScore

Specificity

The description names its domain ('technical specifications for software projects') and enumerates concrete coverage areas ('requirements, architecture, APIs, and testing strategies'), matching the anchor 'lists several specific actions; minor gaps in coverage'. It falls short of a 5 because it describes a single core action (creating specs) rather than multiple distinct actions.

4 / 5

Completeness

It clearly answers 'what' in third person ('Creates detailed technical specifications for software projects covering...') and 'when' with an explicit 'Use when...' clause containing three concrete trigger phrases, matching the anchor for explicitly answering both.

5 / 5

Trigger Term Quality

'Use when planning features, documenting system design, or creating architecture decision records' includes natural user phrases, notably the real-world term 'architecture decision records'. A few natural synonyms users would say ('design doc', 'tech spec', 'write a spec') are missing, so it does not reach anchor 5's comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The spec-writing/ADR niche is mostly distinct with specific triggers, but 'planning features' and 'documenting system design' are broad enough to overlap with generic planning or documentation skills, fitting 'mostly distinct; minor overlap risk'.

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

secondsky/claude-skills

Path

plugins/technical-specification/skills/technical-specification/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.