CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

product-capability

Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ECC-native PRD-to-SRS lane instead of vague planning prose.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/product-capability/SKILL.md
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.

A well-structured, reasonably lean instruction skill: a clear four-step workflow, concrete constraint taxonomies, and a literal output template make it actionable. Its main gaps are the absence of a worked example artifact and implicit rather than explicit validation checkpoints between steps.

Suggestions

Add a short worked example (a filled-in CAPABILITY/CONSTRAINTS/HANDOFF block for a small sample feature) so the output format is unambiguous in practice, boosting actionability.

Insert an explicit validation checkpoint after step 1 or 2 (e.g., "re-read the restated capability against the source PRD; if it cannot be traced to stated intent, revise before proceeding") to strengthen workflow clarity.

Trim editorial lines like "These are the things that often live only in senior-engineer memory" and the "The goal is not to create another planning stack" sentence to tighten token efficiency.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (enumerated bullets, a literal template, no re-explanation of known concepts), with only minor trimmable editorial lines ("These are the things that often live only in senior-engineer memory", "The goal is not to create another planning stack"), fitting the efficient-with-minor-trims anchor rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

As an instruction-only skill it provides concrete, specific guidance — a 4-step workflow, enumerated constraint categories, a literal output-format template, and a template file path — but lacks a worked example of a filled-in capability plan, which the anchor-5 "specific examples cover the common cases" bar requires.

4 / 5

Workflow Clarity

The sequence (restate → resolve constraints → define contract → translate into execution) is clear and ends with an explicit handoff triage gate and a conflict-check rule, but intermediate validation checkpoints (e.g., verifying the restated capability against the source PRD) are implicit rather than explicit, matching anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The SKILL.md is a well-sectioned overview with the detailed artifact correctly externalized to a one-level-deep, clearly signaled template path ("docs/examples/product-capability-template.md"); no bundle files exist, and minor organization gaps (the bare next-lane enumeration) keep it below the clean split-and-navigation of anchor 5.

4 / 5

Total

16

/

20

Passed

Description

75%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 strong, specific description that clearly states what it produces and when to use it. Its main weaknesses are single-verb action coverage, missing common synonyms (requirements doc, spec), and a when-clause phrased in ecosystem jargon ("ECC-native PRD-to-SRS lane") rather than natural user language.

Suggestions

Add one or two more concrete action verbs beyond "Translate" (e.g., "extract constraints and invariants, define interfaces and states") to strengthen specificity and approach comprehensive coverage.

Rewrite the when-clause in natural user phrasing, e.g., "Use when the user mentions a PRD, product requirements doc, roadmap item, or asks to turn product intent into a technical spec or implementation plan".

Add common synonyms such as "requirements doc", "spec", and "feature request" to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain and enumerates concrete deliverables ("implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions"), but the action list reduces to a single verb ("Translate"), leaving minor gaps in coverage versus the comprehensive multi-action anchor.

4 / 5

Completeness

Both what ("Translate PRD intent... into an implementation-ready capability plan...") and when ("Use when the user needs an ECC-native PRD-to-SRS lane instead of vague planning prose") are explicitly present; the when-clause is concrete enough to exceed anchor 3 but too jargon-heavy and circular to match the concrete-trigger-phrase bar of anchor 5.

4 / 5

Trigger Term Quality

"PRD intent", "roadmap asks", and "product discussions" are natural terms users would say, giving good keyword coverage, though common synonyms ("requirements doc", "spec", "feature request") are absent and the when-clause leans on internal jargon ("ECC-native PRD-to-SRS lane").

4 / 5

Distinctiveness Conflict Risk

The PRD-to-SRS capability-planning niche with its specific vocabulary is clearly distinguishable, with only minor overlap risk against generic planning or spec-writing skills, fitting the "mostly distinct" anchor rather than the minimal-conflict anchor 5.

4 / 5

Total

16

/

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

ysyecust/everything-claude-code

Path

.agents/skills/product-capability/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.