CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

adopt

Brownfield audit — do existing artifacts actually work? Numbered migration plan. Unlike /project-stage-detect, checks compliance not existence.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/adopt/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

The body is a well-orchestrated, token-efficient overview that delegates all phase detail to seven real, one-level-deep reference files with clear per-phase routing. Its only flaws are minor: a repeated compaction clause across every phase section and deferral of audit specifics to the references.

DimensionReasoningScore

Conciseness

The body is lean: no concept explanations, compact argument-mode bullets, and two-sentence phase sections. It falls short of anchor 5 only because "Read it again if the conversation was compacted or resumed during this phase" is repeated verbatim across all seven phase sections and could be stated once.

4 / 5

Actionability

Guidance is concrete and executable for an orchestration skill: exact routing ("Read references/2-format-audit.md now and follow it"), a real command resolving specific config keys, explicit argument modes, and a specific output path (docs/adoption-plan-[date].md). It is below anchor 5 only because the actual audit criteria and examples are deferred to the reference files, leaving minor gaps within the body itself.

4 / 5

Workflow Clarity

Seven phases are explicitly sequenced, each mapped to one reference file, with an explicit checkpoint before the only write operation (Phase 5: "Present Summary and Ask to Write"), a recovery path for compaction/resume, and guardrails ("Never regenerate existing artifacts"). This matches anchor 5's clear sequence with explicit validation steps and feedback loops; the destructive-operation cap does not apply because the audit is read-only and the write is gated.

5 / 5

Progressive Disclosure

The body is a pure overview with well-signaled, one-level-deep references — all seven referenced files (references/1-detect.md through 7-first-action.md) exist, and none point to further nested bundle files. Content is appropriately split (routing and mode semantics inline; all phase steps external), matching anchor 5 exactly.

5 / 5

Total

18

/

20

Passed

Description

57%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 establishes a clear, well-differentiated niche and a concrete "what", but lacks any explicit "when to use" trigger guidance and leans on jargon ("brownfield") over natural user phrasing. It is serviceable but would be materially improved by an explicit trigger clause.

Suggestions

Add an explicit trigger clause, e.g. "Use when adopting this template into a project that already has GDDs, ADRs, or stories, or when the user asks to check whether existing artifacts will work with the template's skills."

Replace or gloss the jargon term "brownfield" with natural phrasing users would actually say, such as "existing project" or "already-started project".

Enumerate the concrete audit actions more fully (e.g. "audits GDD, ADR, story, and infrastructure formats; classifies gaps by severity") to lift specificity beyond two abstract actions.

DimensionReasoningScore

Specificity

Quotes "Brownfield audit" and "Numbered migration plan" name the domain plus two concrete actions (audit artifacts, produce a migration plan), but "do existing artifacts actually work?" stays abstract and no further actions are enumerated. It sits at anchor 3 rather than 4 because it does not list several specific actions with only minor gaps.

3 / 5

Completeness

The "what" is clear (audit existing artifacts for compliance, output a numbered migration plan), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines. The /project-stage-detect contrast only weakly implies a "when".

3 / 5

Trigger Term Quality

Terms like "audit", "migration plan", and "compliance" are relevant, but "brownfield" is technical jargon and natural user phrasings ("adopt this template", "check my existing project") are absent. It is above anchor 2 (which has only generic keywords) but below anchor 4's good natural-term coverage.

3 / 5

Distinctiveness Conflict Risk

"Unlike /project-stage-detect, checks compliance not existence" explicitly differentiates the skill from its nearest neighbor, establishing a clear niche (format-compliance auditing) with minimal conflict risk. This matches anchor 5; no neighboring anchor fits better because the explicit contrast is exactly what prevents wrong-skill triggering.

5 / 5

Total

14

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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/adopt/SKILL.md

Reviewed

Table of Contents

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.