CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-specs

Use when producing a technical design spec for a feature or Jira story. Enforces consistent spec structure covering data model, API surface, permissions, offline-sync rules where applicable, and web/mobile UI. Run before writing-plans.

64

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/sdlc/skills/writing-specs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a solid, domain-specific skill for producing technical design specs with good actionability through its concrete template, table structures, and TypeScript examples. Its main weaknesses are moderate verbosity from repeated 'see project-context' references and overlapping coverage of offline sync rules across multiple sections, plus a workflow that could be more explicitly sequenced. The template is well-structured but the skill would benefit from splitting the large template into a separate reference file.

Suggestions

Consolidate offline sync guidance into a single authoritative section rather than repeating rules across Mobile UI, Offline Sync, Project-Specific Rules, and Anti-Patterns sections.

Add an explicit numbered workflow at the top (1. Fetch Jira ticket, 2. Fill template, 3. Run self-review checklist, 4. Save/branch/PR, 5. Post breadcrumb) to make the overall process scannable.

Consider extracting the spec template into a separate reference file (e.g., refs/spec-template.md) and keeping SKILL.md as a concise overview with workflow steps and key rules.

DimensionReasoningScore

Conciseness

The skill is fairly long (~200+ lines) and contains some repetition — e.g., 'see project-context' is repeated many times, and the offline sync rules appear in multiple sections (Mobile UI, Offline Sync section, Project-Specific Rules, Anti-Patterns). However, most content is genuinely instructive template material rather than explaining concepts Claude already knows. The anti-patterns table and self-review checklist add value but overlap with inline instructions.

3 / 5

Actionability

The skill provides a concrete, copy-paste-ready spec template with specific table structures, TypeScript interface examples, file path conventions, and bash commands for Jira comments. Minor gaps: many sections say 'see project-context' without specifying what to do if project-context is unavailable, and the template uses placeholders that require significant contextual judgment rather than mechanical filling.

4 / 5

Workflow Clarity

The workflow is reasonably clear: fetch Jira ticket → fill template → run self-review checklist → save to specific path → create PR → post breadcrumb comment. The guard ('If you did not successfully fetch the Jira ticket... STOP') and the self-review checklist serve as validation checkpoints. However, the overall sequence isn't presented as a numbered step-by-step workflow — it's scattered across sections (output file, guard, template, checklist), requiring the reader to assemble the sequence mentally.

4 / 5

Progressive Disclosure

The skill references external files (plugins/sdlc/refs/artifact-encoding.md, project-context) but no bundle files are provided, making it impossible to verify these references resolve. The content is entirely self-contained in one large file with no splitting of the lengthy template into separate reference files. The template itself is ~100 lines and could benefit from being a separate referenced file, with the SKILL.md serving as a concise overview.

3 / 5

Total

14

/

20

Passed

Description

87%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.

This is a strong description that clearly communicates both what the skill does and when to use it. It lists specific coverage areas and provides explicit trigger guidance including workflow ordering. Minor improvements could include adding synonym trigger terms like 'tech spec' or 'design doc' and slightly more concrete action verbs.

DimensionReasoningScore

Specificity

Lists several specific areas covered: data model, API surface, permissions, offline-sync rules, and web/mobile UI. It also mentions enforcing consistent spec structure. Minor gaps exist—it doesn't elaborate on concrete actions like 'generates diagrams' or 'creates API endpoint definitions'—but coverage is good.

4 / 5

Completeness

Clearly answers both 'what' (produces a technical design spec covering data model, API surface, permissions, offline-sync rules, web/mobile UI) and 'when' (when producing a technical design spec for a feature or Jira story, run before writing-plans). The trigger guidance is explicit and concrete.

5 / 5

Trigger Term Quality

Includes natural terms like 'technical design spec', 'Jira story', 'feature', 'data model', 'API', 'permissions', 'offline-sync', and 'web/mobile UI'. Missing some synonyms users might say like 'tech spec', 'design doc', 'architecture document', or 'RFC'.

4 / 5

Distinctiveness Conflict Risk

Highly distinctive—targets a specific artifact type (technical design spec) with a clear niche covering specific domains (data model, API, permissions, offline-sync, UI). The mention of running before 'writing-plans' further distinguishes it in a workflow. Minimal conflict risk with other skills.

5 / 5

Total

18

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
whimzyLive/nightshift-ai
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.