CtrlK
BlogDocsLog inGet started
Tessl Logo

feature-spec

Build a non-ambiguous, complete, provenance-tagged product spec for a feature area — the behavioral oracle that prove-behavior tests against. Researches every reachable source (code, live product, sibling specs, Jira, Confluence, Slack, git history) to build a mental map, then interrogates the user exhaustively to resolve EVERY ambiguity before writing. Use when: (1) user says 'feature-spec', 'write the spec for X', 'build the product spec', 'spec out this feature', (2) before running prove-behavior on a feature that has no spec yet, (3) onboarding onto a feature and wanting the ground-truth contract. One spec per feature AREA (e.g. all of the settings screen, or checkout, or the text editor). Output: docs/features/<area>/product-spec.md.

73

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 methodology skill with a clear phased workflow, explicit validation checkpoints and feedback loops, and clean progressive disclosure into three real reference files. The main weakness is moderate verbosity in the rules and worked examples.

Suggestions

Tighten the Lenses worked examples — the two paragraph-length anecdotes could be condensed to one line each while preserving the 'question the primitive, not the behavior' lesson.

Consider collapsing the HARD RULES into a tighter checklist format; the current blockquote-with-emphasis form repeats the same prohibition multiple ways.

The Self-improvement and Changelog sections are valuable but long; a one-line summary pointing to detail could reclaim context-window budget.

DimensionReasoningScore

Conciseness

Mostly efficient and free of padding about concepts Claude already knows, but the emphatic HARD RULES and long worked examples in the Lenses section add length that could be trimmed without losing meaning.

4 / 5

Actionability

Concrete and executable for a methodology skill — named phases, exact provenance tag formats like [verified-from-code], and specific reference files — though it stops short of copy-paste-ready commands, which is appropriate for an instruction-only skill.

4 / 5

Workflow Clarity

Clear Phase 0 through Phase 8 sequence with explicit validation checkpoints (frame lock in Phase 2, completeness gate, ambiguity-lint loop back to Phase 5) and feedback loops for error recovery.

5 / 5

Progressive Disclosure

SKILL.md is a well-organized overview with clearly signaled one-level-deep references to real bundle files (references/themes.md, references/research-sources.md, references/spec-template.md), each appropriately split out.

5 / 5

Total

18

/

20

Passed

Description

96%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 concretely states what the skill does, names its research sources, and gives explicit natural-language trigger phrases with a clear output path. Minor overlap risk with sibling documentation skills is the only weak point.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — researches every named source (code, live product, sibling specs, Jira, Confluence, Slack, git history), builds a mental map, interrogates the user, and writes a provenance-tagged spec — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (build a provenance-tagged product spec via research and interrogation) and 'when' with three concrete numbered trigger conditions, plus the output path.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say — 'feature-spec', 'write the spec for X', 'build the product spec', 'spec out this feature' — covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Clear niche (the behavioral oracle for prove-behavior) with distinct triggers, but acknowledged overlap with the knowledge-harvester documentation skill keeps it just below a 5.

4 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mayank-arora/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.