sprint-plan

New or updated sprint plan from the current milestone, completed work, and available capacity.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/sprint-plan/SKILL.md

Quality

Content

73%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 strong, well-sequenced operational skill: concrete commands, templates, prompts, and verdicts with genuine validation gates and feedback loops. Its main weaknesses are redundant review-mode exposition (explained in Phase 0, Phase 4, and Phase 6) and a few implicit details around capacity derivation and design-document scanning.

Suggestions

Consolidate the review-mode resolution and semantics into a single section (or a referenced doc) and have Phases 4 and 6 point to it instead of restating the chain and mode meanings.

Specify how capacity is derived (sprint length in working days, team size, the 20% buffer calculation) so the Capacity block of the template is computable rather than placeholder-only.

Make the design-document scan step concrete — what to extract from a GDD or game brief and how it feeds story selection/estimates — or move the template blocks into a references file to shorten the inline body.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight, project-specific rules with no generic concept explanations, but review-mode semantics and the resolution chain are explained three times (Phase 0, the Phase 4 mode check, and the Phase 6 "Review mode configuration" paragraph), and the "Never write a review mode" block is wordy. This matches anchor 3 — could be tightened — rather than anchor 4's "minor instances".	3 / 5
Actionability	Guidance is largely executable: exact Glob/Grep commands, copy-paste markdown and yaml templates, exact AskUserQuestion prompts and options, and an exact write ask. Minor gaps remain — how capacity totals ("Total days: [X]", the 20% buffer) are derived and what "Scan design documents... for additional context" concretely does are left implicit — so it falls short of anchor 5's fully executable coverage.	4 / 5
Workflow Clarity	Six clearly sequenced phases with explicit validation checkpoints (PR-SPRINT producer gate, QA plan gate), explicit verdicts (UNREALISTIC / NOT ASSESSED / CONCERNS / BLOCKED / COMPLETE), feedback loops (revise and re-present, re-run the gate after supplying missing input), and explicit wait ordering between the QA question and the write ask. This matches anchor 5 including its feedback-loop requirement.	5 / 5
Progressive Disclosure	No bundle files exist, and the body delegates gate, automation-mode, and config-resolution detail to clearly signaled one-level-deep project docs (`.claude/docs/director-gates/[gate-id].md`, `automation-modes.md`, `config-resolution.md`) — the parent is even told not to read the spawned agent's gate file. Minor gaps: the full output templates and the thrice-repeated review-mode logic are inlined and could partially live in a reference file, keeping it at anchor 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

61%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.

The description concretely states what the skill produces and from which inputs, with relevant natural keywords, but it omits any explicit "when to use" trigger guidance and frames capabilities as a noun phrase rather than a list of actions. It is serviceable but below the quality of the good examples, which pair a concrete what with an explicit Use-when clause.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to plan a sprint, update a sprint plan, or check sprint status."

State the concrete capabilities as actions and include the modes, e.g., "Creates, updates, or reports status for sprint plans..." so the new/update/status surface is discoverable from the description.

Include common trigger variations such as "plan a sprint", "sprint planning", and "sprint backlog" alongside the existing keywords.

Dimension	Reasoning	Score
Specificity	The description names the domain and 1-2 concrete deliverables ("New or updated sprint plan from the current milestone, completed work, and available capacity") but is a single noun phrase without a list of specific actions — the new/update/status modes and concrete planning actions never appear. It sits at anchor 3, not 4, because it does not enumerate several specific actions.	3 / 5
Completeness	It answers "what" clearly (produces a new or updated sprint plan from three named inputs) but provides no "when" — there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is concrete, not vague.	3 / 5
Trigger Term Quality	Terms like "sprint plan", "milestone", "completed work", and "available capacity" are ones users would naturally say when they need this skill. A few natural variations are missing ("plan a sprint", "sprint planning", "sprint backlog"), so it fits anchor 4 rather than the comprehensive coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The sprint-plan/milestone/capacity niche is mostly distinct from other skills, with only minor overlap risk against closely related skills in the same suite (e.g., /sprint-status, /create-stories). It lacks the explicit distinct trigger phrases of anchor 5.	4 / 5
	Total	14 / 20 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/sprint-plan/SKILL.md
Commit: b21fa0f

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.