demand-first-review

Use when reviewing a PR, API, IPC channel, endpoint, parameter, type, config, or architectural extension point that adds or expands shared surface area, especially when consumers are absent, exports are unused or speculative, existing consumers are hack-heavy, forward compatibility is claimed, or multiple similar APIs may express one demand.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%

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 tight, highly actionable review methodology with a clear sequenced workflow and built-in validation checkpoints, scoring top marks on conciseness, actionability, and workflow clarity. The only gap is progressive disclosure: everything lives in one file with no external reference structure.

Suggestions

Extract the consumer-legitimacy taxonomy (Step 2) and the rationalization guard table into a referenced file (e.g. REFERENCES.md) and signal them from SKILL.md, so the overview stays lean while detail is one level deep.

Consider moving the two Calibration examples into a separate calibration file and linking them, demonstrating the abstract rules on concrete cases without bloating the main body.

Add a one-line pointer at the top of the workflow indicating where extended examples or per-surface checklists live, even if the core remains single-file.

Dimension	Reasoning	Score
Conciseness	The body is dense and lean, assuming competence without explaining what a PR, API, or IPC channel is; every section (principle, workflow, guards, red flags, calibration) earns its tokens with no padding.	3 / 3
Actionability	As an instruction-only skill it provides concrete, actionable guidance: a 4-class consumer taxonomy, an explicit five-part architectural test, a 7-outcome decision list, and a rationalization guard table, all specific enough to drive execution.	3 / 3
Workflow Clarity	A clear 7-step numbered sequence includes an explicit five-part validation checkpoint (Step 5) and a decide-then-review feedback loop (Step 7), plus Red Flags that trigger restart, satisfying the anchor for explicit checkpoints.	3 / 3
Progressive Disclosure	Content is a single self-contained file with well-organized sections but no signaled references to deeper material and no bundle files to split into; it is structured yet monolithic, so it is not the level-3 multi-file split nor the level-1 nested-reference anti-pattern.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 precise, trigger-led, and clearly scoped to a distinct niche, answering both what and when with concrete enumerated targets and conditions. It is strong across all dimensions with no first/second-person voice issues.

Dimension	Reasoning	Score
Specificity	Enumerates concrete review targets ("PR, API, IPC channel, endpoint, parameter, type, config, or architectural extension point") and concrete trigger conditions ("consumers are absent, exports are unused or speculative, existing consumers are hack-heavy"), listing multiple specific actions rather than vague language.	3 / 3
Completeness	Explicitly answers both what (reviewing shared-surface additions/expansions) and when ("Use when reviewing..." with named trigger conditions), matching the anchor that requires an explicit trigger clause.	3 / 3
Trigger Term Quality	Opens with a natural "Use when reviewing a PR..." trigger and surfaces terms users actually say ("unused", "hack-heavy", "forward compatibility"); coverage is broad even if slightly jargon-dense, which keeps it at 3 rather than 2.	3 / 3
Distinctiveness Conflict Risk	The demand-first-review niche is highly specific and tied to shared-surface extension points, making it unlikely to fire for unrelated skills; it occupies a clear, distinct niche.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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: CherryHQ/cherry-studio
Path: .agents/skills/demand-first-review/SKILL.md
Commit: f7139a2

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

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.