story-readiness

Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.

Quality

77%

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/story-readiness/SKILL.md

Quality

Content

81%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 highly actionable, well-sequenced validation workflow with exact commands, templates, and validation checkpoints throughout. Its weaknesses are verbosity — self-referential design-commentary blocks and duplicated precedence rules — and a monolithic structure that could offload detail to reference files.

Suggestions

Delete the changelog-style meta-commentary ("Note what made this survive: NOT ASSESSED was already in this skill's vocabulary...", "This half of the rank has to be stated...") — it explains past edits, not how to run the skill.

State the verdict precedence once (Section 4) and reference it from the top instead of restating it in the opening blockquote.

Move the workflow-tier matrices and per-tier ADR rules in Section 3 into a reference file, keeping SKILL.md as the checklist overview with a pointer.

Dimension	Reasoning	Score
Conciseness	The checklist rules are dense and operational, but the body carries padded meta-commentary with no execution value — "Note what made this survive: NOT ASSESSED was already in this skill's vocabulary... It is a recurring shape — a correct fix that did not reach one surface", "This half of the rank has to be stated...", and the verdict precedence stated twice (top blockquote and Section 4). Mostly efficient with some unnecessary explanation, not severely padded.	3 / 5
Actionability	Guidance is copy-paste ready throughout: exact Grep invocations (e.g. `Grep pattern="^## Status" glob="docs/architecture/adr-*.md" output_mode="content" -A 3`), verbatim output templates for single and aggregate reports, exact Fix strings per gap, and concrete routing commands for every failure path.	5 / 5
Workflow Clarity	Phases 0–8 are clearly sequenced with explicit validation checkpoints and error-recovery loops: the mandatory zero-scope stop, the ADR-scan denominator check ("0 matches with N > 0 means malformed ADRs"), first-match-wins verdict precedence, and the QL-STORY-READY gate's ADEQUATE/GAPS/INADEQUATE/NOT ASSESSED handling with retry and override rules.	5 / 5
Progressive Disclosure	The body is well-sectioned and its references to external docs (`.claude/docs/director-gates.md`, `workflow-modes.md`, `automation-modes.md`, per-gate files read only by the spawned agent) are clearly signaled and one level deep. No bundle files exist to nest. It remains a monolithic 510-line file — the tier matrices and ADR status rules could live in reference files — so structure is good rather than exemplary.	4 / 5
	Total	17 / 20 Passed

Description

66%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 crisp, third-person description that concretely states what the skill checks and its four verdicts, with good natural trigger terms. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness at 3 despite a strong "what".

Suggestions

Add an explicit trigger clause, e.g. "Use when preparing to assign a story, planning a sprint, or when the user asks whether a story is ready to implement."

Mention the remaining check areas (scope boundaries, estimates, dependencies, asset references, test evidence) so the description reflects the body's full coverage.

Include a couple of user-natural synonyms ("ready to implement", "sprint-ready") to widen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Checks clear acceptance criteria, open questions, ADR refs" names the domain plus three concrete check actions, but omits other capabilities the body covers (scope boundaries, estimates, dependencies, asset refs, test evidence) — several specific actions with minor gaps, not comprehensive coverage.	4 / 5
Completeness	The "what" is clear (checks listed plus the verdict vocabulary READY/NEEDS WORK/BLOCKED/NOT ASSESSED), but there is no "Use when..." clause or equivalent explicit trigger guidance — the rhetorical question "Is a story implementation-ready?" only weakly implies when to use it, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural terms like "story", "implementation-ready", "acceptance criteria", "open questions", and "ADR" are present and would be said by a user needing this check, but common variations such as "sprint", "ready to implement", or "estimate" are missing.	4 / 5
Distinctiveness Conflict Risk	The verdict vocabulary and story/ADR framing carve a distinct niche unlikely to trigger the wrong skill, but it could still overlap with adjacent planning skills (sprint planning, story creation) in the same workflow toolkit — minor overlap risk.	4 / 5
	Total	15 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (519 lines); consider splitting into references/ and linking	Warning
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	13 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/story-readiness/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.