CtrlK
BlogDocsLog inGet started
Tessl Logo

provider-configuration

Implement Terraform provider configuration and authentication with the Plugin Framework: provider schema for credentials (Optional + Sensitive attributes), environment variable fallbacks, credential provider chains (static config, then environment variables, shared credentials file, and platform identity), unknown-value guards in Configure(), secret redaction, configure-time credential validation, and diagnostics that name every source tried. Use when implementing or reviewing a provider's Configure method or provider schema, adding authentication options (API keys, tokens, profiles, credentials files, assume-role), deciding how a provider should resolve credentials, debugging "no valid credential sources" or missing-credentials errors, or unit testing credential resolution.

77

Quality

96%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 production-quality skill body: complete executable Go for the schema and Configure path, concrete operational details throughout, a well-sequenced workflow with explicit validation and error-recovery branching, and clean two-file progressive disclosure verified against the actual bundle. The only weakness is minor — a few motivational/rationale sentences could be trimmed for token efficiency.

Suggestions

Trim the motivational framing (the 'Poor authentication UX is the first thing every user of a provider hits...' sentence and similar rhetoric) — the guidance stands on its own without it.

Condense a few 'why each step matters' bullets (e.g. the secrets-pasted-into-config debugging anecdote) to their one-line technical point to save tokens.

DimensionReasoningScore

Conciseness

The body is largely efficient — domain-specific failure-mode reasoning (set-vs-field resolution, sentinel-error design, unknown-value semantics) is knowledge Claude does not have for free, and code blocks carry no boilerplate. A few tokens are trimmable, e.g. the motivational opener 'Poor authentication UX is the first thing every user of a provider hits; a well-designed credential provider chain is what separates a production-grade provider from a demo' and flourishes like 'Collapsing them into one message is how providers end up with users pasting secrets into config to debug'.

4 / 5

Actionability

Both the Schema and Configure examples are complete, compilable Plugin Framework code with real diagnostic strings, attribute paths, and a docs URL; supporting guidance is equally concrete ('chmod 0600', 'info.Mode().Perm()&0o077 != 0', 't.Setenv', 't.TempDir() fixtures', a getenv func field). The only deferred piece — the Chain implementation — is delegated to a complete, verified reference file rather than left as pseudocode.

5 / 5

Workflow Clarity

The Configure workflow is explicitly numbered ('1. Guard against unknown values... 2. Resolve credentials through the chain... 3. Build the client once') with validation checkpoints after each stage ('if resp.Diagnostics.HasError() { return }'), an error-recovery branch on errors.Is(err, credentials.ErrNoCredentials) that selects the right message, and a closing 12-item checklist. The testing section sequences the tests that matter by category.

5 / 5

Progressive Disclosure

A well-signaled 'References (load when needed)' block up front annotates both reference files and what each contains; both exist, are one level deep, and are non-overlapping (complete implementation vs. case studies). The body keeps only the decision-level content and correctly pushes the full chain implementation and tests to references/credential-chain.md, which contains them.

5 / 5

Total

19

/

20

Passed

Description

100%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.

An exemplary description: dense, third-person, and specific, listing the full capability surface (schema design, chain precedence, guards, redaction, validation, diagnostics) alongside an explicit and varied 'Use when' clause covering implementation, review, debugging, and testing scenarios. No fluff or over-claims; every clause is a distinct capability or trigger.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete capabilities — 'provider schema for credentials (Optional + Sensitive attributes)', 'credential provider chains (static config, then environment variables, shared credentials file, and platform identity)', 'unknown-value guards in Configure()', 'secret redaction', 'configure-time credential validation', and 'diagnostics that name every source tried'. Coverage is comprehensive with no material gaps, matching the anchor-5 example's breadth.

5 / 5

Completeness

It explicitly answers both questions: 'what' via the enumerated implementation capabilities and 'when' via 'Use when implementing or reviewing a provider's Configure method or provider schema, adding authentication options..., debugging "no valid credential sources" or missing-credentials errors, or unit testing credential resolution.' Both halves carry concrete trigger phrases, exactly matching the anchor-5 example.

5 / 5

Trigger Term Quality

It includes natural terms and their synonyms — 'API keys, tokens, profiles, credentials files, assume-role' — plus the exact error strings a user would encounter ('no valid credential sources', 'missing-credentials') and the API surface name ('Configure method'). This meets the comprehensive-with-synonyms anchor rather than the 'a few natural terms missing' anchor at 4.

5 / 5

Distinctiveness Conflict Risk

The niche is tightly scoped to Terraform provider configuration/authentication with distinct triggers ('Configure method', credential resolution errors, assume-role). Related sibling skills (provider schema/resources, provider scaffolding) target different surfaces, so conflict risk is minimal; anchor 4's 'minor overlap risk with closely related skills' is not a better fit because the trigger set is unique to this skill.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
hashicorp/agent-skills
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.