CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

spec-feature

Spec a new feature — recall architecture knowledge, create a spec document, build an implementation plan, and break into tasks.

Quality

74%

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 ./skills/spec-feature/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

This is a highly actionable, well-sequenced process skill: every step carries exact commands, tool invocations, or templates, with user-review checkpoints and useful operational gotchas. Weaknesses are minor — some redundancy in the diagram mandate, a mechanism-heavy step-8 paragraph that belongs in the referenced handoff skill, and no explicit validation of the produced spec/diagrams before handoff.

Suggestions

Add an explicit validation checkpoint before retain/handoff, e.g. re-read docs/specs/<feature-name>.md to confirm all sections are filled and both diagram files exist on disk.

Trim the step-8 spawn_task/worktree mechanism detail to a short note and let the referenced devflow:phase-handoff skill own that behavior description.

State the diagram requirement once (either in the complexity callout or in step 4) to remove the duplicated mandate.

DimensionReasoningScore

Conciseness

The body is imperative and directive with no explanations of concepts Claude already knows, but has minor trim candidates: the step-8 mechanism narrative ("visible in the sidebar", "durable across worktree removal") and the diagram mandate stated twice ("REQUIRED for any non-trivial feature — this is the devflow default" then "Every non-trivial spec ships a rendered technical diagram AND an ELI5 diagram by default").

4 / 5

Actionability

Fully executable instruction-only guidance: exact bash snippet for the window title, an exact mark_chapter call with arguments, a ticket-ID regex, a complete copy-paste spec template at docs/specs/<feature-name>.md, an exact handoff invocation (devflow:phase-handoff --phase spec --next-phase plan), and specific operational gotchas like "one image per turn — batching an image Read with any other tool call suppresses the inline preview".

5 / 5

Workflow Clarity

Eight clearly numbered, dependency-ordered steps with explicit user checkpoints ("If arguments are vague, ask clarifying questions", "list them and ask the user to pick", step 6's present-for-review questions), but with minor validation gaps — no explicit verification that the diagrams rendered successfully or that the spec document is complete before retain/handoff.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so scoring is against structure and placement: sections are well-organized (Preamble / Steps / Important) and the template and one-liner commands belong inline; the only gap is the dense step-8 paragraph detailing spawn_task/worktree mechanics that would fit better in the referenced handoff skill than inlined here.

4 / 5

Total

17

/

20

Passed

Description

55%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 clearly communicates what the skill does through four concrete, sequenced actions, but it entirely lacks trigger guidance — no 'Use when...' clause and few natural user phrases or synonyms. Adding an explicit when-to-use clause with realistic trigger terms would lift completeness, trigger quality, and distinctiveness together.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. "Use when the user asks to spec, design, or plan a new feature before implementation, or mentions writing a spec or requirements document."

Include natural synonyms users would actually say ("write a spec", "feature design", "requirements", "break down into tasks") to improve trigger-term coverage and distinctiveness from generic planning skills.

Consider naming the concrete outputs (spec document at docs/specs/, task breakdown) in the description to sharpen the 'what' toward the comprehensive-specificity anchor.

DimensionReasoningScore

Specificity

Lists four concrete actions ("recall architecture knowledge", "create a spec document", "build an implementation plan", "break into tasks"), matching the several-specific-actions anchor; not anchor 5 since coverage has minor gaps and 'recall architecture knowledge' is somewhat abstract.

4 / 5

Completeness

The 'what' is clear (four concrete actions) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines — the 'when' is entirely absent rather than weakly implied.

3 / 5

Trigger Term Quality

Contains some natural terms ("Spec a new feature", "spec document", "implementation plan") but misses common variations and synonyms users would say ("write a spec", "design a feature", "requirements", "architecture doc"), matching the some-keywords-but-missing-variations anchor.

3 / 5

Distinctiveness Conflict Risk

"Spec a new feature" names a niche but overlaps with adjacent planning/design/requirements skills (the body itself hands off to a 'writing-plans' sibling), fitting the somewhat-specific-but-overlap-prone anchor rather than the mostly-distinct anchor.

3 / 5

Total

13

/

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: 2 missing

Warning

Total

15

/

16

Passed

Repository

AndreJorgeLopes/devflow

Path

skills/spec-feature/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.