CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lean-ai-adoption-coach

Guide AI adoption decisions in software development using Lean, Extreme Programming, and pragmatic simplicity. Use when evaluating AI tools, agents, workflows, prompts, automations, or rollout guardrails; deciding whether to automate or keep work manual; detecting tool sprawl, prompt graveyards, or low-value AI assets; or defining team standards for AI usage.

Quality

79%

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 ./.agents/skills/lean-ai-adoption-coach/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 well-organized and token-efficient with a clear workflow and useful decision defaults, but its progressive disclosure contract is broken: the only referenced file, playbook.md, does not exist, leaving key operational details (simplicity checks, evaluation template, metrics) unavailable and one section ('Response Modes') without meaning.

Suggestions

Add the referenced playbook.md to the bundle (containing the principles, anti-patterns, evaluation template, metrics, and simplicity policy) or remove the 'Detailed Guidance' section — the link currently points to a file that does not exist.

Inline or briefly summarize the simplicity checks referenced by the Decision Defaults ('fails two or more simplicity checks'), since that decision rule is currently unresolvable without the missing playbook.

Either explain when and how to use each of the four 'Response Modes' (Quick evaluation, Leadership decision, Ecosystem hygiene, Strategic reflection) or delete the section, as the bare labels provide no actionable guidance.

DimensionReasoningScore

Conciseness

The body is lean, well-sectioned, and assumes Claude's competence without explaining known concepts, but the 'Use This Skill When' section duplicates the frontmatter description and 'Response Modes' contributes four bare labels with no content.

4 / 5

Actionability

Offers a concrete 5-step workflow, seven diagnostic questions, a named output template, and thresholds ('fails two or more simplicity checks', '2-4 weeks with one owner, one primary metric'), but the simplicity checks, evaluation template, and metrics are promised in playbook.md which does not exist in the bundle, and 'Response Modes' is an inert list with no guidance on when or how to use each mode.

3 / 5

Workflow Clarity

The numbered sequence (define problem, classify work, apply heuristic, choose adoption level, define guardrails) is clear, and the guardrails checklist with rollback criteria, review date, and retirement path plus explicit exit criteria serve as checkpoints — but 'Apply the Lean/XP heuristic' defers its substance to the missing playbook.

4 / 5

Progressive Disclosure

The single reference is clearly signaled and one level deep ('See playbook.md for principles, anti-patterns, evaluation template, metrics, simplicity policy, and example usage'), but playbook.md is absent from the bundle, so the link is dead and all detailed guidance is unreachable — navigation fails at the first hop.

2 / 5

Total

13

/

20

Passed

Description

91%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 description with an explicit 'Use when' clause covering four concrete trigger scenarios and rich natural keywords. The main cap on specificity is the abstract headline verb, and there is minor overlap risk with broad automation-decision skills.

DimensionReasoningScore

Specificity

Enumerates several specific actions ('evaluating AI tools, agents, workflows, prompts, automations', 'detecting tool sprawl, prompt graveyards, or low-value AI assets', 'defining team standards'), but the headline 'Guide AI adoption decisions' is abstract and most concrete actions sit in the when-clause, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ('Guide AI adoption decisions in software development using Lean, Extreme Programming, and pragmatic simplicity') and when ('Use when evaluating...; deciding whether...; detecting...; or defining...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural-language coverage across four trigger scenarios with synonyms ('AI tools', 'agents', 'workflows', 'prompts', 'automations', 'rollout guardrails', 'tool sprawl', 'prompt graveyards', 'low-value AI assets', 'team standards', 'automate or keep work manual') — the phrases a user would naturally say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

The Lean/XP adopt-vs-retire framing and terms like 'prompt graveyards' carve a distinct niche, but 'deciding whether to automate' and 'defining team standards' carry minor overlap risk with general automation or process-coaching skills.

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

saski/arnesto

Path

.agents/skills/lean-ai-adoption-coach/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.