CtrlK
BlogDocsLog inGet started
Tessl Logo

talk-martinelli-spec-driven-development

Answers questions about, summarises key insights from, and helps apply concepts from Simon Martinelli's talk "Lessons from Spec-driven Development" — providing verbatim-grounded explanations, audits, and artifact drafts. Use when the user asks about the AI Unified Process, system use cases as specs (vs user stories), self-contained systems vs microservices, skills/MCP servers/guardrails, AI-assisted ERP modernization, drift management, how architecture style impacts AI coding agents, or applying his spec-driven approach to current work.

71

Quality

87%

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 a well-structured, actionable reference skill with clear workflows and explicit verification checkpoints, assuming Claude's competence throughout. Main gap: the referenced bundle files (outline.md, transcript.md, quote.md) are not present in the bundle, so progressive disclosure cannot be fully verified.

Suggestions

Place outline.md, transcript.md, and quote.md under ./references/ so the referenced sources actually exist in the bundle and progressive-disclosure navigation can be verified.

Consolidate the repeated 'Start with LOOKUP' refrains into a single referenced procedure to trim the mild verbosity across the task-workflow sections.

Provide a copy-paste system-use-case template (Actor / Preconditions / Main success scenario / Alternative flows / Postconditions) to push actionability from concrete guidance to fully executable.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — no basic-concept padding — with minor over-explanation in the repeated LOOKUP refrains and a safety section that partly restates the grounding rules. It is above the anchor-3 ('mostly efficient but includes some unnecessary explanation') but not fully lean at anchor-5.

4 / 5

Actionability

Concrete, specific guidance throughout: ordered audit dimensions, an exact artifact structure (Actor, Preconditions, Main success scenario, Alternative flows, Postconditions), verbatim-quote anchoring, and line-range citation rules. Minor gaps (no copy-pace template file) keep it below the fully-executable anchor-5.

4 / 5

Workflow Clarity

A shared LOOKUP first step followed by clearly sequenced per-task workflows, with explicit checkpoints ('If the answer isn't in the transcript, say so explicitly', 'If a dimension doesn't apply, say so'). It is below anchor-5 because the checkpoints are stop-and-flag rather than a validate→fix→retry feedback loop, and above anchor-3 because sequence and checkpoints are clearly present.

4 / 5

Progressive Disclosure

Sections are well organized and references to outline.md, transcript.md, and quote.md are clearly signaled one level deep via the LOOKUP procedure. It is below anchor-5 because no references/, scripts/, or assets/ bundle directory exists, so the referenced files are not actually present in the bundle to verify; it is above anchor-3 because structure and signaling are good, not buried.

4 / 5

Total

16

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities, provides a rich 'Use when...' trigger clause with natural synonyms, answers both what and when, and occupies a distinct, low-conflict niche. No substantive weaknesses.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Answers questions about, summarises key insights from, and helps apply concepts... providing verbatim-grounded explanations, audits, and artifact drafts' — giving comprehensive coverage of what the skill does. It exceeds the anchor-4 example (which has minor gaps) by enumerating five distinct action types.

5 / 5

Completeness

It explicitly answers both 'what' (answers, summarises, applies, audits, drafts artifacts) and 'when' with a concrete 'Use when the user asks about...' trigger clause, matching the anchor-5 example exactly in structure.

5 / 5

Trigger Term Quality

The 'Use when' clause lists natural user phrases and synonyms across the talk's topics (AI Unified Process, system use cases as specs vs user stories, self-contained systems vs microservices, skills/MCP servers/guardrails, ERP modernization, drift management), matching the comprehensive-synonym anchor. No common variation is obviously missing for this niche.

5 / 5

Distinctiveness Conflict Risk

A named-speaker, single-talk niche with highly specific trigger terms creates a clear niche with minimal conflict risk. Voice is third person ('Answers', 'summarises'), so no first/second-person penalty applies.

5 / 5

Total

20

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
jscraik/Agent-Skills
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.