rate-complexity

Use when an issue needs its complexity declared — proposing a rating from the issue body alone and getting the owner to confirm or amend it, or backfilling a rating onto an existing unrated issue. Invoked by new-feat at issue-creation time; also the backfill path for issues opened before the label existed.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/rate-complexity/SKILL.md

Quality

Content

76%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-crafted, actionable skill body with copy-paste commands and a clear rubric, hurt mainly by the batch backfill path lacking a validation checkpoint. Conciseness and structure are solid.

Suggestions

Add a verification step to Mode B's batch backfill — e.g., re-list the issues after labeling to confirm each gained a complexity: label and that none were skipped — so the batch path has an explicit validate/feedback loop.

Make the Mode A confirm/amend checkpoint an explicit validation gate (only apply the label after the owner confirms, and re-read the issue to confirm the label landed) to lift workflow_clarity above the batch cap.

Tighten the "Why the timing is the whole point" prose by trimming the editorializing about contaminated ratings, preserving the behavioral rule (rate before work, never rate your own work) in fewer tokens.

Dimension	Reasoning	Score
Conciseness	Lean and behavior-shaping with real commands and a compact rubric table; it assumes Claude's competence, with only light editorializing ("the number gets talked into agreeing with the spend") that keeps it just shy of the fully-lean 5.	4 / 5
Actionability	Fully executable, copy-paste-ready `gh issue edit`/`gh issue list` commands with real flags and a jq filter, plus a concrete rubric table — specific examples cover the common apply-label, backfill, and exclude-unconfirmed cases.	5 / 5
Workflow Clarity	Mode A is a clear numbered sequence with an owner confirm/amend checkpoint, but Mode B is a batch operation ("Do them in one pass over a listing") with no validation/verification step, so the batch-operation cap holds it at 3.	3 / 5
Progressive Disclosure	No bundle files exist; the body is well-organized into purposeful sections and external references (wiki/observability/session-metrics.md, @tools/pr-metrics) are clearly signaled, with only minor organization gaps keeping it below a 5.	4 / 5
	Total	16 / 20 Passed

Description

80%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 both capability and trigger conditions for a well-scoped niche. Trigger-term quality is the relative weak spot because the natural-language cues are specialized and machine-invocation-oriented rather than user-spoken.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "proposing a rating from the issue body alone and getting the owner to confirm or amend it, or backfilling a rating onto an existing unrated issue" — with only minor coverage gaps, fitting the "lists several specific actions" anchor rather than the comprehensive 5.	4 / 5
Completeness	It explicitly answers both what (propose/confirm/amend/backfill a rating) and when ("Use when an issue needs its complexity declared"; "Invoked by new-feat at issue-creation time; also the backfill path for issues opened before the label existed") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Relevant domain keywords ("complexity", "rating", "issue") appear, but the triggers are workflow-internal and machine-invoked ("Invoked by new-feat"), missing the natural user phrases and synonym/extension coverage that would mark a 4.	3 / 5
Distinctiveness Conflict Risk	A clear, narrow niche — declaring Fibonacci complexity labels on issues in a specific repo workflow — with distinct triggers ("complexity:unconfirmed", "new-feat") and minimal realistic overlap with other skills.	5 / 5
	Total	17 / 20 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: xchromo/osn
Path: .claude/skills/rate-complexity/SKILL.md
Commit: 5438649

Reviewed: ~10 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.