retrospective

Generates a sprint or milestone retrospective by analyzing completed work, velocity, blockers, and patterns. Produces actionable insights for the next iteration.

Quality

83%

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

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, highly actionable multi-phase workflow with explicit checkpoints, error-recovery branches, and a copy-paste-ready output template, all delivered concisely without padding.

Dimension	Reasoning	Score
Conciseness	The body is lean and procedural throughout — no preamble explaining what a retrospective is or generic concepts Claude already knows; every phase gives specific guidance (exact paths, commands, an output template), so it matches the score-3 'lean and efficient; every token earns its place' anchor rather than the 'could be tightened' level 2.	3 / 3
Actionability	Provides concrete, executable guidance — exact glob patterns ('production/retrospectives/retro-[sprint-slug]-*.md'), a runnable git command, AskUserQuestion prompts with enumerated options, and a copy-paste-ready output template — meeting the score-3 'fully executable; copy-paste ready' anchor; absence of code is fine for this instruction skill per scoring_notes.	3 / 3
Workflow Clarity	Six phases are clearly sequenced with explicit checkpoints and error-recovery branches — Phase 1b checks for an existing file, Phase 2 handles missing data via a BLOCKED verdict with a manual-data fallback, and Phase 5 gates the write with a COMPLETE/BLOCKED verdict — matching the score-3 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; the skill is a single self-contained document organized into clearly labeled phases with no nested/deep references, and the inline Phase 4 template is the core deliverable rather than deferrable reference material, fitting the 'well-organized sections with no need for external references' guidance for score 3.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 specific and occupies a clear, distinctive niche, but it omits an explicit 'Use when...' trigger clause and lacks common term variations like 'retro', which caps completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when running a sprint or milestone retrospective, or when the user asks for a retro, post-sprint review, or iteration review.'

Include common trigger variations users would actually say — 'retro', 'post-mortem', 'iteration review' — alongside 'retrospective' to improve trigger-term coverage.

Tie the 'when' explicitly to natural prompts like 'do a retro' or 'review the sprint' so the skill is unambiguously selected at invocation time.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'analyzing completed work, velocity, blockers, and patterns' and 'Produces actionable insights for the next iteration' — naming the domain and several specific operations, matching the score-3 anchor.	3 / 3
Completeness	It clearly answers 'what' (generates a retrospective by analyzing work/velocity/blockers) but 'when' is only implied with no explicit 'Use when...' trigger guidance, which the guidelines cap at 2; it is not a 1 because the 'what' is strong.	2 / 3
Trigger Term Quality	Uses relevant natural terms ('sprint', 'milestone', 'retrospective', 'velocity', 'blockers') but misses common variations a user would actually say (e.g. 'retro') and lacks an explicit 'Use when...' trigger clause, so it sits at the score-2 'some relevant keywords but missing common variations' anchor rather than 3.	2 / 3
Distinctiveness Conflict Risk	'sprint or milestone retrospective' is a clear, narrow niche with distinct triggers unlikely to conflict with other skills, matching the score-3 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/retrospective/SKILL.md
Commit: 984023d

Reviewed: 3 days 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.