CtrlK
BlogDocsLog inGet started
Tessl Logo

spec-driven-development

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope, or when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a capability map of modules before specifying.

80

2.36x
Quality

81%

Does it follow best practices?

Impact

97%

2.36x

Average score across 2 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 strong, highly actionable workflow skill: gated phases, explicit validation checkpoints, feedback loops, and copy-paste-ready templates. Its weaknesses are moderate verbosity in motivational sections and an inconsistent external-reference convention, both fixable without restructuring.

Suggestions

Trim the 'Common Rationalizations' table to the 3-4 highest-value rows and cut 'When to Use' bullets that duplicate the frontmatter description, tightening the conciseness score.

Standardize external skill references to a single format (either all bare skill names in backticks or all paths) — the current mix of 'skills/incremental-implementation/SKILL.md' and 'planning-and-task-breakdown' is inconsistent.

Move the full spec template and capability-map example into a references/ file, keeping only a condensed skeleton inline, to improve progressive disclosure and reduce token cost per invocation.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but the 'When to Use' section repeats the frontmatter description, the eight-row 'Common Rationalizations' table is largely persuasive padding, and Phase 0 prose ('exists for the exception, not the rule, and it puts no hierarchy on single-capability features') could be tightened. This fits anchor 3: mostly efficient but with unnecessary material that could be trimmed.

3 / 5

Actionability

Copy-paste-ready markdown templates for the spec, task list, and capability map, plus concrete worked examples (the ASSUMPTIONS block, the 'Make the dashboard faster' reframe, full build/test/lint commands). Per the rubric's scoring notes, an instruction-only skill is not penalized for lacking code when guidance is this concrete; examples cover the common cases, matching anchor 5.

5 / 5

Workflow Clarity

A gated four-phase workflow (plus Phase 0 scope check) with an ASCII diagram, the explicit rule 'Do not advance to the next phase until the current one is validated', human-review gates at every phase, and a final verification checklist. The assumptions prompt ('Correct me now or I'll proceed with these') provides an explicit feedback loop, matching anchor 5.

5 / 5

Progressive Disclosure

Well-sectioned single-file skill with clearly signaled cross-skill references and explicit precedence rules ('planning-and-task-breakdown takes precedence'). Minor gaps: the large inline templates could be split into reference files, and external skill pointers are formatted inconsistently (some as 'skills/.../SKILL.md' paths, some as bare names), fitting anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

82%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 well-crafted description with explicit third-person 'what' and multiple concrete, natural 'Use when...' triggers that carve out a distinct niche. Its main weakness is that the capability statement is brief relative to the detailed trigger coverage, leaving the 'what' slightly under-specified.

Suggestions

Expand the 'what' clause from 'Creates specs before coding' to name the key artifacts produced (e.g., 'Creates specification documents with objectives, boundaries, and testable success criteria before coding') to raise specificity.

Add one or two common synonyms users say for this need, such as 'design doc' or 'acceptance criteria', to broaden trigger coverage.

Consider briefly naming the downstream artifacts (implementation plan, task breakdown) so the skill's full scope is visible without reading the body.

DimensionReasoningScore

Specificity

The description names the domain ('Creates specs before coding') with one or two concrete actions (creating specs, decomposing into a capability map of modules), but the 'what' is thin relative to the extensive trigger coverage. It does not list several specific actions as anchor 4 requires.

3 / 5

Completeness

Explicitly answers both 'what' ('Creates specs before coding') and 'when' with three concrete 'Use when...' clauses covering project starts, PRD drafting, and multi-capability decomposition. The 'when' is fully explicit with concrete trigger phrases, matching anchor 5 rather than anchor 4.

5 / 5

Trigger Term Quality

Strong natural trigger phrases users would actually say: 'starting a new project', 'drafting a PRD', 'requirements document', 'requirements are unclear, ambiguous, or only exist as a vague idea'. A few common synonyms (e.g., 'design doc', 'acceptance criteria', 'tech spec') are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

Spec creation is a clear niche, and the guard 'no specification exists yet' plus PRD/requirements triggers minimize overlap with planning or implementation skills. Distinct triggers give minimal conflict risk, matching anchor 5.

5 / 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
addyosmani/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.