CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

setup-wizard-generator

Generate a bash wizard guiding a human through manual setup.

Quality

70%

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 ./optional-skills/devops/setup-wizard-generator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 tight, well-sequenced procedural skill with excellent conciseness and validation discipline — the static-trace verification approach and pitfalls list are genuinely non-obvious guidance. Its one material defect is that the bundle ships only SKILL.md: the templates/template.sh prerequisite the whole procedure depends on is absent, breaking both actionability and the disclosure structure.

Suggestions

Ship templates/template.sh in the skill bundle (or, if intentional, inline the helper function signatures and a minimal example stage in SKILL.md so the wizard can be authored without the missing file).

Add one short executable example of a authored stage (bash) showing how a stage composes open_url, ask_secret, and write_env, so the helper list translates directly into code.

Add an explicit fix-and-retry loop for the verification step (e.g. 'if bash -n or shellcheck fails, fix and re-run before handoff') to complete the error-recovery cycle.

DimensionReasoningScore

Conciseness

The body is lean and dense: no general bash/wizard explanations, every section carries project-specific information Claude could not infer (e.g. 'The library above the STAGES marker is identical in every wizard — never hand-edit it', 'A wizard is ephemeral by default', the pitfalls list). It assumes competence and every token earns its place, matching the 'lean and efficient' anchor exactly.

5 / 5

Actionability

The guidance names concrete helpers (stage, ask_secret, write_env, set_secret, open_url, confirm), an exact example click path ('Dashboard → Developers → API keys → Reveal test key → copy'), and exact verification commands (`bash -n`, `shellcheck`, `chmod +x`). However, the central executable artifact — 'templates/template.sh (from this skill's directory)' — is referenced twice but absent from the bundle (no templates/, references/, scripts/, or assets/ directories exist), leaving helper signatures and stage syntax undocumented. This is 'some concrete guidance but incomplete; missing key details' — not 4, because the copy-the-template step cannot actually be executed as bundled.

3 / 5

Workflow Clarity

The four numbered steps are clearly sequenced with explicit validation throughout: user sign-off on the stage list in step 1 ('they may add, drop, or reorder. Done when...'), doc-verification for uncertain UI paths in step 2, and step 4 devoted to validation (`bash -n`, shellcheck, static tracing of every captured value and every set_secret name) plus a final Verification checklist. Feedback loops and a checklist are both present, matching the top anchor.

5 / 5

Progressive Disclosure

Sections are well-organized (When to Use, Prerequisites, Procedure, Pitfalls, Verification) and the one external reference is clearly signaled, but the sole referenced bundle file — templates/template.sh — does not exist in the actual bundle, so the reference is broken and the library it should disclose is missing entirely. Per the guideline to score against the actual bundle structure, this lands at 'some structure but could be better organized' rather than 4-5, since navigation leads to a nonexistent file.

3 / 5

Total

16

/

20

Passed

Description

53%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 communicates the skill's essence concisely in third person, but it is a single clause with no trigger guidance and limited capability detail. It reads as a compressed summary rather than a routing description — users asking to 'walk through setting up Stripe' or 'set up CI secrets' would not reliably surface it.

Suggestions

Add an explicit 'Use when...' clause naming the trigger scenarios, e.g. 'Use when provisioning third-party services (Stripe, Supabase, OAuth apps), setting up CI secrets/repo variables, or running one-off human-gated migrations.'

Include natural trigger phrases users would actually say — 'walk me through', 'step by step', 'onboarding a teammate', 'credentials', '.env', 'GitHub secrets' — to improve trigger term coverage.

Enumerate one or two more concrete capabilities (opens each URL, captures values, writes them to .env or GitHub secrets, confirms each stage) to lift specificity from one action toward comprehensive coverage.

DimensionReasoningScore

Specificity

The description names the artifact ('a bash wizard') and one concrete action ('Generate') plus its purpose ('guiding a human through manual setup'), but omits the specific capabilities the body delivers — opening URLs, capturing values, writing .env/GitHub secrets, confirming stages. This matches the anchor 'names domain and 1-2 concrete actions, but not comprehensive'; a 4 would require several specific listed actions.

3 / 5

Completeness

The 'what' is clear (generate a bash wizard guiding a human through manual setup) but there is no 'Use when...' clause or equivalent trigger guidance — 'when' is only weakly implied by 'manual setup'. Per the judging guideline, a missing 'Use when...' clause caps completeness at 3; a 4 would require an explicit, if imperfect, 'when'.

3 / 5

Trigger Term Quality

'bash wizard', 'manual setup', and 'human' are natural terms a user might say, but common phrasings users actually use are missing — 'walk me through', 'step by step', 'onboarding', 'credentials', 'secrets', '.env'. This fits 'some relevant keywords but missing common variations or synonyms'; not 2 (more than one relevant keyword present) nor 4 (coverage is not good — most natural trigger phrases are absent).

3 / 5

Distinctiveness Conflict Risk

Human-in-the-loop setup wizards are a clear niche with distinct triggers, but 'manual setup' broadly overlaps with general environment-setup requests the agent could perform itself, giving minor overlap risk with closely related setup/config skills. Not 5 (overlap risk is real for generic 'set up my project' asks) and clearly not 3 (the wizard/human-guided framing is far more specific than 'works with document files').

4 / 5

Total

13

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/devops/setup-wizard-generator/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.